RU2666275C1 - Device and method of coding moving image, long term data-storage computer recorded medium which image coding program is recorded on - Google Patents

Abstract

FIELD: data processing.SUBSTANCE: group of inventions relates to technologies for encoding / decoding moving images. Device for encoding moving image is proposed. Device comprises output unit of the first prediction information that performs process of outputting one or more candidates to the first interframe prediction information from interframe prediction information. Device also includes output unit for the second prediction information that performs process of outputting candidate for the second interframe prediction information. Device also includes encoding unit that encodes index indicating interframe prediction information used for interframe prediction of the second block being encoding object.EFFECT: technical result is enhancement of prediction accuracy for block being object of encoding.3 cl, 44 dwg

Description

FIELD OF TECHNOLOGY

The present invention relates to a motion picture coding and decoding technology, and more particularly, relates to a motion picture coding and decoding technology that uses motion compensation prediction.

KNOWN LEVEL OF TECHNOLOGY

A typical coding standard for moving image compression is MPEG-4 AVC / H.264. MPEG-4 AVC / H.264 uses motion compensation when each image frame is divided into several rectangular blocks, a frame that has already been encoded or decoded is used as a reference frame, and motion is predicted from this reference frame. A method that predicts compensation for this motion is referred to as inter-frame prediction, or motion compensation prediction. According to the MPEG-4 AVC / H.264 inter-frame prediction, several frames can be used as reference frames, and from these several reference frames, for each block, the most suitable reference frame is selected and motion compensation prediction is performed. In this case, a reference index is assigned to each reference frame, and a reference frame is specified by this reference index. For a B frame, up to two frames can be selected from the already decoded reference frames, which will be used for inter-frame prediction. Two types of prediction are distinguished, which are respectively based on these two reference frames, one of them is L0 prediction (prediction from list 0), which is used mainly for predicting the previous frame, and the other L1 prediction (prediction from list 0), which is accordingly used mainly to predict the next frame.

In addition, a bi-prediction is also determined using both types of inter-frame prediction (i.e., L0 prediction and L1 prediction). In the case of bi-prediction, the prediction is performed in both directions in time, the inter prediction signals predicted by the L0 prediction and the L1 prediction are respectively multiplied by the weighting coefficient, the offset value is added, and the signals are convolved to form the full inter prediction signal. The value of the weighting coefficient used for weighted prediction, and the offset value are set by typical values in units of frames for each reference frame of each list, and encoded. The coding information related to inter-frame prediction comprises: a prediction mode, which is divided into L0 prediction, L1 prediction and bi-prediction for each block, a reference index that specifies a reference frame of each reference list of each block, and a motion vector that represents direction of movement and the amount of movement of the block. This encoding information is encoded and / or decoded.

Further, in accordance with MPEG-4 AVC / H.264, a direct mode is determined when inter-prediction information of a block being encoded or decoded is generated from inter-frame prediction information of an already decoded block. Since, in the direct mode, encoding of inter prediction information becomes unnecessary, the direct mode increases the encoding efficiency.

With reference to FIG. 42, an explanation will be given of a forward time mode in which time correlation of inter prediction information is used. A frame whose reference index in L1 is registered as 0. is used as the base colPic frame. A block that is identical to the position of the block that is being encoded or decoded in the base frame colPic is taken as the base block.

If the base block is encoded using L0 prediction, then the motion vector of the base block in L0 is taken as the base motion vector mvCol. If this base block is not encoded using L0 prediction, but encoded using L1 prediction, then the motion vector in L1 of this base block is taken as the base motion vector mvCol. The frame referenced by the base motion vector mvCol is adopted as a reference frame in L0 in time-direct mode, and the base frame colPic is taken as a reference frame in L1 in time-direct mode.

The motion vector mvL0 in L0 and the motion vector mvL1 in L1 in the direct time mode are derived from the base motion vector mvCol by a scale calculation operation.

By subtracting the POC of the reference frame in L0 in the time-direct mode, the distance td between the image frames is derived from the POC of the base frame colPic. Here, the POC is defined as a variable that is associated with a frame that is the object of encoding, and is set to a value that increases in the order that frames appear. The difference between the ROS of two frames shows the distance between frames along the time axis. In the time-direct mode td = POC of the base frame colPic - POC of the reference frame in L0.

Subtracting the POC of the reference frame in L0 in the time-direct mode from the POC of the frame being the object of encoding or decoding, the distance tb between the frames

tb = POC of the frame being the object of encoding or decoding, is the POC of the reference frame in L0 in the time-direct mode.

The motion vector mvL0 in L0 in the time-direct mode is derived from the base motion vector mvCo1 by the scale calculation process.

mvL0 = tb / td * mvCo1

The motion vector mvL1 in L1 is derived by subtracting the basic motion vector mvCo1 from the motion vector mvL0 in L0 in a time-direct mode.

mvL1 = mvL0-mvCo1

LIST OF RELATED LEVEL OF TECHNOLOGY

Patent document

[Patent Document 1] Japanese Patent Application Published Under No. 2004-129191

SUMMARY OF THE INVENTION

However, in accordance with the conventional method, in some cases, the prediction accuracy for the block being the encoding object and for the block being the decoding decreases and the encoding efficiency with the time-direct mode does not improve.

In such a situation, the present inventors have recognized the need to further compress encoding information and reduce the total code size in a moving image encoding method that uses motion compensation prediction.

The present invention solves the aforementioned problem, and an object of the invention is to provide a moving picture coding and decoding technology for reducing a code size of information for coding by computing candidates for coding information, and thereby improving coding efficiency.

In order to solve the above problem, in accordance with one aspect of the present invention, a moving picture coding apparatus is provided. This device divides the first block, which is obtained by dividing each frame, into one or more second blocks, and encodes a moving image using inter-frame prediction. The device comprises: an output unit of first prediction information (130), which outputs a candidate for the first inter prediction information from inter prediction information of a third block adjacent to the second block that is the object of encoding, inside the frame that is the object of encoding; an output unit of the second prediction information (132), which outputs the candidate for the second inter prediction information from the inter prediction information of the fourth block, which is in a position identical to the position of the second block that is the encoding object, or in its vicinity, inside a frame other than the frame, being the object of encoding; a candidate list building unit (133) that generates a candidate list for prediction information containing candidates for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this derived candidate for the first inter-frame prediction information is added, and in the case when a candidate for the second inter-frame prediction information is output, accordingly, this derived candidate for the second inter-frame prediction information is added; a selection unit (136) that selects a candidate for inter prediction information used for inter prediction of the second block to be encoded from one or more prediction information candidates in the prediction information candidate list, and determines an index that indicates inter prediction information ; an encoding unit (110) that encodes an index indicating inter-prediction information used for inter-prediction of a second block that is being encoded. In this case, the output unit of the first prediction information (130) does not use the encoding information of the fifth block contained in the block identical to the first block containing the second block that is the object of encoding as a candidate for the first inter prediction information.

In accordance with another aspect of the present invention, a moving picture coding apparatus is also provided. This device divides the encoding block into one or more prediction blocks in accordance with the division mode, and performs motion compensation prediction. The device comprises: a reference index output unit (131), which is in the merge mode, where the inter prediction information, defined as a time merge candidate, is derived from the inter prediction information of the prediction unit, which is in a position identical to the position of the prediction unit that is encoding , or in its vicinity, inside an encoded frame that is different in time from the prediction block that is the object of encoding, and based on the inferred inter-frame prediction information about uschestvlyaetsya prediction interframe prediction block which is the object of coding, displays the information on the reference index merging candidate time as the reference index information that specifies a reference frame used in the prediction block, which is the object of encoding; and a time merge candidate generation unit (132) that outputs inter-prediction information of the time merge candidate based on the derived information of the reference index. In the case where the separation mode is a mode where the coding unit is divided by a horizontal border into vertical prediction units, the reference index output unit (131) assigns the time merge candidate reference index information to the reference index information of the encoded prediction unit adjacent to the left side block prediction, which is the object of encoding, and provides this information of the reference index, and in the case where the separation mode is a mode where the block is encoded It is divided by a vertical border into horizontal prediction blocks, the reference index output unit (131) assigns the time merge candidate reference index information to the reference index information of the encoded prediction block adjacent to the upper side of the prediction block being the encoding object, and outputs this information reference index.

In accordance with another embodiment of the present invention, a method for encoding a moving image is provided. In this method, the first block, which is obtained by dividing each frame, is divided into one or more second blocks, and a moving image is encoded using inter-frame prediction. The method comprises: a stage in which a candidate for first inter-prediction information is derived from inter-prediction information of a third block adjacent to a second block that is an encoding object, inside a frame that is an encoding object; the stage at which the candidate for the second inter-prediction information is derived from the inter-prediction information of the fourth block, which is in a position identical to the position of the second block that is the encoding object, or in its vicinity, inside a frame different from the frame that is the encoding object; the stage at which a list of candidates for prediction information is constructed containing candidates for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this derived candidate for the first inter-frame prediction information is added, and in the case when a candidate for the second inter prediction information, respectively, this derived candidate for the second inter prediction information is added; a step in which a candidate for inter-prediction information used for inter-prediction of the second block to be encoded is selected from one or more prediction information candidates in the prediction information candidate list, and an index that indicates inter-prediction information is determined; a step at which an index is encoded indicating inter-prediction information used for inter-prediction of the second block to be encoded. Moreover, the stage at which the first prediction information is displayed does not use the encoding information of the fifth block contained in the block identical to the first block containing the second block that is the encoding object as a candidate for the first prediction information.

In accordance with one aspect of the present invention, a moving picture decoding apparatus is provided. This device decodes the bitstream, where the first block, which is obtained by dividing each frame, is divided into one or more second blocks, and the moving image is encoded using inter-frame prediction. The device comprises: a block for outputting the first prediction information (230), which outputs a candidate for the first inter prediction information from the inter prediction information of the third block adjacent to the second block that is the decoding object within the frame that is the decoding object; an output unit of the second prediction information (232), which outputs the candidate for the second inter prediction information from the inter prediction information of the fourth block, which is in a position identical to the position of the second block that is the object of decoding, or in its vicinity, inside a frame other than the frame, decoding subject; a decoding unit (202) that decodes an index indicating inter-prediction information used for inter-prediction of a second block to be decoded; a candidate list building unit (233) that generates a list of candidates for prediction information containing candidates for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this derived candidate for the first inter-frame prediction information is added, and in the case when a candidate for the second inter-frame prediction information is output, accordingly, this derived candidate for the second inter-frame prediction information is added; and a selection unit (236) that selects a candidate for inter prediction information used for inter prediction of the second block that is the decoding object indicated by the index from one or more prediction information candidates in the prediction information candidate list. In this case, the output unit of the first prediction information (230) does not use the encoding information of the fifth block contained in the block identical to the first block containing the second block that is the object of decoding as a candidate for the first prediction information.

In accordance with another aspect of the present invention, a moving picture decoding apparatus is also provided. This device divides the decoding unit into one or more prediction blocks in accordance with the separation mode, and performs motion compensation prediction. The device comprises: a reference index output unit (231), which is in the merge mode, where the inter prediction information determined as a time merge candidate is derived from the inter prediction information of the prediction unit, which is in a position identical to that of the prediction unit that is the decoding object , or in its vicinity, inside a decoded frame that is different in time from the prediction block that is the object of decoding, and from the output inter prediction information inter-frame prediction of the prediction block being the decoding object is performed, outputting the merge candidate reference index information as reference information that specifies a reference frame used in the prediction block being the decoding object; and a time merge candidate generation unit that outputs inter-prediction information of the time merge candidate based on the derived information of the reference index. In this case, in the case where the separation mode is a mode where the decoding unit is divided by a horizontal border into vertical prediction units, the reference index output unit (231) assigns the time merge candidate reference index information to the reference index information of the decoded prediction unit adjacent to the left side of the prediction block that is the object of decoding, and provides this information of the reference index, and in the case where the separation mode is a mode, where the decoding unit is divided by a vertical border into horizontal prediction units, the reference index output unit (231) assigns the time merge candidate reference index information to the reference index information of the decoded prediction unit adjacent to the upper side of the prediction unit being the decoding object, and outputs this reference index information.

In accordance with another feature of the invention, a method for decoding a moving image is provided. This method decodes the encoded bitstream, where the first block, which is obtained by dividing each frame, is divided into one or more second blocks, and the moving image is encoded using inter-frame prediction. The method comprises: a stage in which a candidate for first inter-prediction information is derived from inter-prediction information of a third block adjacent to a second block that is a decoding object within a frame that is a decoding object; the stage at which the candidate for the second inter prediction information is derived from the inter prediction information of the fourth block, which is in a position identical to the position of the second block that is the decoding object, or in its vicinity, inside a frame different from the frame that is the decoding object; a step of decoding an index indicating inter-prediction information used for inter-prediction of the second block to be decoded; the stage at which a list of candidates for prediction information is constructed containing candidates for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this derived candidate for the first inter-frame prediction information is added, and in the case when a candidate for the second inter prediction information, respectively, this derived candidate for the second inter prediction information is added; and a step in which a candidate for inter-prediction information used for inter-prediction of the second block that is the decoding object indicated by the index is selected from one or more prediction information candidates in the prediction information candidate list. The stage at which the candidate for the first inter-frame prediction information is displayed does not use the encoding information of the fifth block contained in a block identical to the first block containing the second block that is the decoding object as a candidate for the first inter-frame prediction information.

As additional forms of the present invention, arbitrary combinations of the aforementioned constituent elements and the implementation of this invention in the form of methods, apparatus, systems, recording media, computer programs, etc. can also be used in practice.

According to the present invention, the value of the generated code of the transmitted encoding information can be reduced, and the encoding efficiency can be improved.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a block diagram illustrating a structure of a moving image coding apparatus in which a motion vector prediction method is executed in accordance with an embodiment;

FIG. 2 is a block diagram illustrating a structure of a moving image decoding apparatus in which a motion vector prediction method is executed in accordance with an embodiment;

FIG. 3 illustrates a tree block and a coding block;

FIG. 4 illustrates partitioning modes of a prediction block;

FIG. 5 illustrates prediction blocks that are adjacent to a prediction block that is being processed as spatial merge candidates in a merge mode;

FIG. 6 illustrates prediction blocks that are adjacent to a prediction block that is being processed as spatial merge candidates in a merge mode;

FIG. 7 illustrates prediction blocks that are adjacent to a prediction block being an object of processing as spatial merge candidates in a merge mode;

FIG. 8 illustrates prediction blocks that are adjacent to a prediction block being an object of processing as spatial merge candidates in a merge mode;

FIG. 9 illustrates the prediction blocks that are referenced when deriving candidates for a time merge in merge mode;

FIG. 10 illustrates layer-level bitstream syntax related to merge mode;

FIG. 11 illustrates the syntax of a bitstream at a prediction block level related to a merge mode;

FIG. 12 illustrates an example of entropy code for a syntax element of a merge index;

FIG. 13 is a block diagram showing a detailed configuration of an inter prediction information outputting unit of the moving image encoding apparatus of FIG. one;

FIG. 14 is a block diagram showing a detailed configuration of an inter prediction information outputting unit of a moving image decoding apparatus in FIG. 2;

FIG. 15 illustrates prediction blocks adjacent to a prediction block being an object of processing in a merge mode;

FIG. 16 is a flowchart illustrating a processing procedure for sequentially processing a merge candidate withdrawal process and a merge candidate list building process;

FIG. 17 is a flowchart illustrating a processing procedure in parallel processing of a merger candidate withdrawal process and a merge candidate list building process;

FIG. 18 is a flowchart illustrating a procedure for a merge candidate withdrawal process in a merge mode and a merge candidate list building process;

FIG. 19 is a flowchart illustrating a process for deriving spatial merge candidates in a merge mode;

FIG. 20 illustrates adjoining blocks that are referenced during derivation of reference indices of merge candidates in time, in accordance with a first exemplary embodiment of the present embodiment;

FIG. 21 is a flowchart illustrating a process for outputting reference indices of time merge candidates in a merge mode, in accordance with the method of the first exemplary embodiment;

FIG. 22 illustrates adjoining blocks that are referenced during derivation of reference indices of merge candidates in time, in accordance with a second exemplary embodiment of the present embodiment;

FIG. 23 is a flowchart illustrating a process for outputting reference indices of time merge candidates in a merge mode, in accordance with the method of the second exemplary embodiment;

FIG. 24 illustrates adjoining blocks that are referenced in a derivation process of time indices of candidate merge candidates in accordance with a third exemplary embodiment of the present embodiment;

FIG. 25 is a flowchart illustrating a process for outputting reference indices of time merge candidates in a merge mode, in accordance with the method of the third exemplary embodiment;

FIG. 26 illustrates adjoining blocks that are referenced during derivation of reference indices of merge candidates in time, in accordance with a fourth exemplary embodiment of the present embodiment;

FIG. 27 is a flowchart illustrating a process for outputting reference indices of time merge candidates in a merge mode, in accordance with the method of the fourth exemplary embodiment;

FIG. 28 illustrates adjoining blocks that are referenced during derivation of reference indices of merge candidates in time, in accordance with a fifth exemplary embodiment of the present embodiment;

FIG. 29 is a flowchart illustrating a process for outputting reference indices of time merge candidates in a merge mode, in accordance with the method of the fifth exemplary embodiment;

FIG. 30 is a flowchart illustrating a process for outputting reference indices of time merge candidates in a merge mode, in accordance with a method of a sixth exemplary embodiment;

FIG. 31 illustrates adjoining blocks that are referenced during derivation of reference indices of merge candidates in time, in accordance with a seventh exemplary embodiment of the present embodiment;

FIG. 32 is a flowchart illustrating a process for outputting reference indices of time merge candidates in a merge mode, in accordance with a method of a seventh exemplary embodiment;

FIG. 33 - illustrates adjoining blocks that are referenced in the process of deriving reference indices of NxN-partitioned coding blocks;

FIG. 34 is a flowchart illustrating a process for outputting candidates for a time merge in a merge mode;

FIG. 35 is a flowchart illustrating a process of outputting a frame of another moment in time in a merge mode;

FIG. 36 is a flowchart illustrating a process for outputting prediction blocks of a frame of another moment in fusion mode;

FIG. 37 is a flowchart illustrating a process for outputting candidates for a time merge in a merge mode;

FIG. 38 is a flowchart illustrating a process for outputting candidates for merge in time in a merge mode;

FIG. 39 is a flowchart illustrating a process of calculating a motion vector scale;

FIG. 40 is a flowchart illustrating a process of calculating a scale of a motion vector;

FIG. 41 is a flowchart illustrating a process for constructing a list of merge candidates in a merge mode;

FIG. 42 illustrates a time-direct mode in accordance with the traditional MPEG-4 AVC / H.264 standard;

FIG. 43 illustrates adjoining blocks that are referenced during derivation of reference indices of merge candidates in time, in accordance with an eighth exemplary embodiment of the present embodiment, and

FIG. 44 is a flowchart illustrating a process for outputting reference indices of time merge candidates in a merge mode in accordance with a method of the eighth exemplary embodiment.

MODES FOR CARRYING OUT THE INVENTION

In accordance with this embodiment, for encoding moving images, and more specifically, to increase the encoding efficiency of a moving image, where each image frame is divided into rectangular blocks of arbitrary size and arbitrary shape, and motion compensation between frames in units of blocks from motion vectors is carried out blocks adjacent to the block that is the object of encoding, or several motion vector predictions are derived from the motion vectors of the blocks of the previously encoded frame In this case, the difference vector between the motion vector of the block being the encoding object and the selected motion vector prediction is calculated, and this difference vector is encoded, thereby reducing the code value. Alternatively, using coding information of blocks adjacent to the block that is the object of encoding, or blocks of a previously encoded frame, information is output for encoding the block that is the object of encoding, thereby reducing the code amount. In the case of decoding a moving image, several motion vector predictions are computed from the motion vectors of the blocks adjacent to the block being the decoding object or from the motion vectors of the blocks of the previously decoded frame and from the difference vector decoded from the bitstream, and the vector is calculated from the selected motion vector prediction the movement of the block that is the object of decoding, what is the decoding of the block that is the object of decoding. Alternatively, using coding information of blocks adjacent to the block that is the decoding object, or from the blocks of the previously decoded frame, coding information of the block that is the decoding object is output.

First, definitions will be given of technologies and technical terms used in the present embodiment.

Tree block and coding block

According to an embodiment, as shown in FIG. 3, the frame is divided in units of squares having the same arbitrary size. This unit is defined as a tree block and is used as the basic addressing control unit for specifying the block that is the object of encoding or decoding (hereinafter, “the block that is the object of encoding or decoding is used in the sense of the block that is the object of encoding, in the case of the encoding process, and is used in the sense of the block that is the object of decoding, in the case of the decoding process, unless otherwise specified), in the frame. The tree block contains one luminance signal and two color difference signals, except in the case of a monochrome image. The size of the tree block can be determined arbitrarily in units of two, in accordance with the size of the frame and / or texture inside the frame. To optimize the coding process in accordance with the texture inside the frame, the tree-like block can be hierarchically divided into four blocks (divided into two, both vertically and horizontally), which have a smaller block size, by dividing, as necessary, the luminance signal and color-difference signals inside tree block. These blocks are respectively defined as coding blocks and are taken as the basic processing unit when encoding and decoding. The coding unit also contains one luminance signal and two color difference signals, except in the case of a monochrome image. The maximum size of the coding block is the same as the size of the tree block. The coding block of the minimum size is called the minimum coding block, and its size can be set arbitrarily in units of a multiple of two.

In FIG. 3, coding block A is defined as one coding block, without splitting the tree block. Coding block B is a coding block obtained by dividing a tree block into four blocks. Coding block C is a coding block obtained by further dividing the block, which is obtained by dividing the tree block into four, into four more blocks. The coding block D is a coding block obtained by further dividing the block, which is obtained by dividing the tree block into four, four blocks by double hierarchical division. The coding block D is a coding block of a minimum size.

Prediction mode

The mode switches between intra-frame prediction (MODE_INTRA) and inter-frame prediction (MODE_INTER) in units of coding units. In intra-frame prediction, prediction is performed from the surrounding encoded or decoded signals of the image blocks within the frame that is being encoded or decoded. (In the case of the encoding process, “decoded” is used for a decoded frame that was encoded during the encoding process, for a decoding prediction block that was encoded during the encoding process, for a decoded frame signal that was encoded during the encoding process, etc., and in the case of The decoding process “decoded” is used for a decoded frame, for a decoded prediction block, for a decoded frame signal, etc. Below everything is used in this sense, unless otherwise specified the opposite is indicated). This mode, which distinguishes between intra prediction (MODE_INTRA) and inter prediction (MODE_INTER), is defined as prediction mode (PredMode). The prediction mode (PredMode) takes as the value an intra-frame prediction (MODE_INTRA) or an inter-frame prediction (MODE_INTER), and can select the type of prediction when encoding.

Split Mode, Prediction Block, and Prediction Unit

In the case of dividing the frame into blocks and performing intra-frame prediction (MODE_INTRA) and inter-frame prediction (MODE_INTER), the prediction is performed by dividing the encoding block, as necessary, into parts, in order to specify a smaller unit for switching between intra-frame prediction and inter-frame prediction. This mode, in which the method of separating the luminance signal and the color difference signals of the coding unit is different, is defined as a separation mode (PartMode). In addition, the block thus separated is defined as a prediction block. As shown in FIG. 4, in accordance with a method for separating a luminance signal of a coding unit, eight types of separation modes (PartMode) are determined.

Partition mode (PartMode), when the luminance signal of the coding block is not divided and is considered as one prediction block, as shown in FIG. 4 (a), is defined as a 2Nx2N partition (PART_2Nx2N). Partition modes (PartMode), when the luminance signal of a coding block is divided into two prediction blocks arranged vertically, as shown in FIG. 4 (b), 4 (c) and 4 (d) are defined as 2NxN separation (PART_2NxN), 2NxnU separation (PART_2NxnU) and 2NxnD separation (PART_2NxnD), respectively. 2NxN separation (PART_2NxN) is a separation mode when the block is divided vertically with a ratio of 1: 1, 2NxnU separation (PART_2NxnU) is a separation mode when the block is divided vertically with a ratio of 1: 3, and 2NxnD separation (PART_2NxnD) is split mode, when the block is divided vertically with a ratio of 3: 1. Partition modes (PartMode), when the luminance signal of the encoding block is divided into two prediction blocks arranged horizontally, as shown in FIG. 4 (e), 4 (f) b 4 (g) are defined as the Nx2N partition (PART_Nx2N), nLx2N partition (PART_nLx2N) and nRx2N partition (PART_nRx2N), respectively. Nx2N split is a split mode when the block is split horizontally with a 1: 1 ratio, nLx2N split (PART_nLx2N) is a split mode when the block is split horizontally with a 1: 3 ratio, and nRx2N split (PART_nR2N) is a split mode, when the block is split horizontally with a ratio of 3: 1. Partition mode (PartMode), when the luminance signal of a coding block is divided vertically and horizontally into four blocks, as shown in FIG. 4 (h) is defined as the NxN partition (PART_NxN).

For each separation mode (PartMode), the color difference signal is also divided in the same way and with the same vertical and horizontal separation ratio as the luminance signal.

In the coding block, to identify each prediction block, the prediction block in this coding block is assigned a number starting in 0 in the coding order. This number is defined as the partition index PartIdx. The number recorded in each prediction block in the coding blocks shown in FIG. 4, indicates a partition index PartIdx of the prediction block. For the 2NxN separation (PART_2NxN), 2NxnU separation (PART_2NxnU) and 2NxnD separation (PART_2NxnD) shown in FIG. 4 (a), 4 (c) and 4 (d), respectively, the partition index PartIdx of the upper prediction block is assigned the value 0, and the partition index PartIdx of the lower prediction block is assigned the value 1. For Nx2N partition (PART_Nx2N), nLx2N partition ( PART_nLx2N) and nRx2N separation (PART_nRx2N) shown in FIG. 4 (e), 4 (f) and 4 (g), respectively, the partition index PartIdx of the left prediction block is set to 0, and the partition index PartIdx of the right prediction block is set to 1. For the NxN partition (PART_NxN) shown in FIG. 4 (h), the division value index PartIdx of the upper left prediction block is set to 0, the division index PartIdx of the upper right prediction block is set to 1, the division index PartIdx of the lower left prediction block is set to 2, and the division index PartIdx of the lower right prediction block is set to 3.

In the case when the prediction mode (PredMode) is inter-frame prediction (MODE_INTER), then 2Nx2N separation (PART_2Nx2N), 2NxN separation (PART_2Nx2N), 2NxnU separation (PART_2NxnU), 2NxnD are determined as separation modes (PartMode) PART_2NxnD), Nx2N partition (PART_Nx2N), nLx2N partition (PART_nLx2N) and nRx2N partition (PART_nRx2N). Only in the case of the coding block D, which is the minimum coding block, can the NxN partition (PART_NxN) be defined as the partition mode (PartMode), in addition to the 2Nx2N partition (PART_2Nx2N), 2NxN partition (PART_2NxN), 2NxnU partition (PART2NxnU), 2NxnD split (PART_2NxnD), Nx2N split (PART_Nx2N), nLx2N split (PART_nLx2N) and nRx2N split (PART_nRx2N). However, in accordance with the present embodiment, it is assumed that the NxN partition (PART_NxN) is not defined as a partition mode (PartMode).

In the case, the prediction mode (PredMode) is an intra-frame prediction (MODE_INTRA), for blocks, only 2Nx2N separation (PART_2Nx2N) is determined as a partition mode (PartMode), with the exception of coding block D, which is the minimum coding block. Only in the case of the coding unit D, which is the minimum coding unit, as a partition mode (PartMode), in addition to the 2Nx2N partition (PART_2Nx2N), is the NxN partition (PART_NxN) determined. The reason why NxN partitioning (PART_NxN) is not defined, except for splitting the minimum coding block, is that the coding block other than the minimum coding block can be divided into four blocks, which are smaller coding blocks.

The position of the tree block, coding block, prediction block, and transform block

The position of each block, such as a tree block, a coding block, a prediction block, a transform block, and others, appears, in accordance with the present embodiment, to be a two-dimensional coordinate when the position of the uppermost left pixel of the brightness signal when reproducing brightness signals on the screen is determined by the origin (0,0) and the position of the uppermost left pixel of the luminance signal entering the region of each block is represented by the two-dimensional coordinate (X, Y). As for the directions of the coordinate axes, the positive directions are the horizontal direction to the right and the vertical direction down, respectively, and as for the scale unit, it is one pixel of the brightness signal. The position of each block of color difference signals is represented by the coordinates of the pixel of the luminance signal contained within the region of the block, and the pixel is a scale unit not only when the color difference format is 4: 4: 4, where the frame size (number of pixels) of the brightness and color difference signals are identical between each other, but also in the case when the color difference format is 4: 2: 0 or 4: 2: 2, where the frame size (number of pixels) of the brightness signals and color difference signals are different. By adopting such definitions, it becomes possible not only to identify the position of each block of color difference signals, but also to understand the positional relationship between the block of brightness signals and the block of color difference signals from a simple comparison of coordinate values.

Inter prediction mode and reference list

According to an embodiment of the invention, in inter-frame prediction, several decoded frames may be used as a reference frame, where the prediction is based on the image signals of the decoded frame. To identify a reference frame selected from several reference frames, a reference index is assigned to each prediction block. For the B layer, inter-frame prediction can be performed by selecting two arbitrary reference frames for each prediction block. Inter-frame prediction modes are L0 prediction (Pred_L0), L1 prediction (Pred_L1) and bi-prediction (Pred_BI). The reference frame is controlled by list L0 (reference list 0) and list L1 (reference list 1), which are list structures, and the reference frame can be identified by specifying a reference index in L0 or in L1. L0 prediction (Pred_L0) is an inter-frame prediction that refers to a reference frame controlled by an L0 list, L1 prediction (Pred_L1) is an inter-frame prediction that refers to a reference frame guided by an L1 list, and bi-prediction (Pred_BI) is inter-prediction where joint prediction — L0 prediction and L1 prediction — is performed, and one reference frame controlled by the L0 list and one reference frame controlled by the L1 list are accessed. In inter-frame prediction of the P layer, only L0 prediction can be used. In B-layer inter-frame prediction, L0 prediction, L1 prediction and bi-prediction can be used, in which the average values of L0 prediction and L1 prediction or their weighted values are summed. As for the constants and variables, to the ends of which in the subsequent processes the suffix LX is attached, it is assumed that the process is performed for each L0 and L1.

Merge Mode and Merge Candidates

The merge mode is not a mode that encodes or decodes information for inter-frame prediction (such as, for example, prediction modes, reference indices, motion vectors) of a prediction unit that is encoding or decoding, but is a mode in which inter-frame prediction is performed by outputting information for inter prediction block prediction unit, which is the object of encoding or decoding from information inter prediction: prediction block, which is located inside and the same frame as the prediction unit being the object of encoding or decoding, and which are in the vicinity of the prediction block, which is the object of encoding or decoding; or a prediction block, which are in a frame different in time from the frame of the prediction block, which is the object of encoding or decoding, and which are in a position identical to the position of the prediction block, which is the object of encoding or decoding, or in its vicinity (in the position adjacent to it ) The prediction block and its inter-frame prediction information, wherein the prediction block is inside the same frame as the prediction block that is the object of encoding or decoding, and is in the vicinity of the prediction block that is the object of encoding or decoding, is used as a candidate for spatial merging. The inter prediction information output from the prediction block and its inter prediction information, wherein the prediction block is in an encoded or decoded frame that is different in time from the frame of the prediction block being the object of encoding or decoding, and is in a position identical to the position of the block being the object of encoding or decoding, or in its vicinity (in the position adjacent to it), is used as a candidate for merging in time. Each merge candidate is registered in the list of merge candidates, and the merge candidate, which is used for inter-frame prediction, is specified by the merge index.

Adjacent Prediction Blocks

In FIG. 5, FIG. 6, FIG. 7 and FIG. 8 are illustrated (the derivation of spatial merge candidates and the prediction blocks that are referenced during the derivation of spatial merge candidates and the derivation of reference indices of the time merge candidates, with the prediction blocks being inside the same frame as the prediction block being the object of encoding or decoding, and adjacent to the prediction block, which is the object of encoding or decoding. Fig. 9 illustrates the prediction block, which is accessed by outputting a reference index of the candidate for merging in time, wherein the prediction block is in an encoded or decoded frame different in time from the prediction block being the object of encoding or decoding, and is in a position identical to the position of the prediction block being the object of encoding or decoding, or With reference to Fig. 5, Fig. 6, Fig. 7, Fig. 8 and Fig. 9, explanation will be given for prediction blocks adjacent in space to the prediction block that is the object of ation or decoding and prediction units in an identical position but differing in time.

As shown in FIG. 5, within the same frame with the prediction block being the object of encoding or decoding, the prediction block A adjacent to the left side of the prediction block being the encoding or decoding unit, the prediction block B adjacent to its upper side, prediction block C adjacent to its upper right vertex, prediction block D adjacent to its lower left vertex, and prediction block E adjacent to its upper left vertex.

As shown in FIG. 6, in the case where there are several prediction blocks, the sizes of which are smaller than the size of the prediction block, which is the object of encoding or decoding, and which are adjacent to the left side of the prediction block, which is the object of encoding or decoding, then from several prediction blocks adjacent to the left side, the prediction block A10, which is in its lowest position, is determined, in accordance with the present embodiment, as the prediction block A adjacent to the left side.

Similarly, if there are several prediction blocks whose sizes are smaller than the size of the prediction block being the object of encoding or decoding, and which are adjacent to the upper side of the prediction block that is the object of encoding or decoding, then from several prediction blocks adjacent to the upper side, the prediction block B10 located in the extreme right position is determined, in accordance with the present embodiment, as the prediction block B1 adjacent to the upper side.

As shown in FIG. 7, also in the case where the size of the prediction block F adjacent to the left side of the prediction block being the object of encoding or decoding will be larger than the size of the prediction block being the object of encoding or decoding, in accordance with the conditions described above, the block prediction A is defined as prediction block A, if prediction block A is adjacent to the left side of the prediction block being the object of encoding or decoding, defined as prediction block D, if prediction block D is adjacent to the lower left vertex of the prediction block that is the object of encoding or decoding, and is defined as the prediction block E if the prediction block E is adjacent to the upper left vertex of the prediction block that is the object of encoding or decoding. According to the example shown in FIG. 6, prediction block A, prediction block E and prediction block E are identical prediction blocks.

As shown in FIG. 8, also in the case where the size of the prediction block G adjacent to the upper side of the prediction block being the object of encoding or decoding is larger than the size of the prediction block being the object of encoding or decoding, in accordance with the conditions described above, the block prediction G is defined as prediction block B, if prediction block G is adjacent to the upper side of the prediction block being the object of encoding or decoding, defined as prediction block C, if prediction block Nia G adjacent to the upper right vertex prediction block, which is the object of encoding or decoding, and is defined as a prediction block E, if G prediction block adjacent to the upper left vertex prediction block, which is the object of encoding or decoding. According to the example shown in FIG. 8, prediction block B, prediction block C and prediction block E are identical prediction blocks.

As shown in FIG. 9, previously encoded or already decoded prediction blocks T0 and T1 in a frame different in time from the frame of the prediction block being the object of encoding or decoding, and at a position identical to the position of the prediction block being the object of encoding or decoding, or in its vicinity, are defined as prediction blocks in the same position, but at a different point in time.

ROS

POC is defined as a variable that is directly related to the encoded frame, and the value of which increases by one in the output order of the frames. From the value of the POC variable, it can be determined whether or not the frames are identical to each other, it can be determined whether the frame is previous or next relative to another frame in the output order, or the distance between the frames can be displayed. For example, in the case where the POC variables of two frames have the same values, it can be determined that the frames are identical. In the case when the POC variables of two frames have different values, the frame with a lower POC value is defined as the frame to be issued before another frame, and the difference between the POC variables of two frames represents the distance between these frames along the time axis.

Below with reference to the figures of the drawings will be given an explanation of an example embodiment of the invention. In FIG. 1 is a block diagram showing the structure of a moving image coding apparatus in accordance with an embodiment of the invention. A moving image encoding device, in accordance with an embodiment, comprises a frame memory 101, a motion vector detection unit 102, a motion vector difference calculation unit 103, an inter prediction information output unit 104, a motion compensation prediction unit 105, an intra prediction unit 106, a method determination unit predictions 107, residual signal generation unit 108, orthogonal transform / quantization unit 109, first bit stream generation unit 110, second generation unit of the ith bitstream 111, multiplexing unit 112, dequantization / inverse orthogonal transforming unit 113, convolution unit of decoded frame signals 114, encoding information storage memory 115 and decoded frame memory 116.

The frame memory 101 temporarily stores image signals of frames that are objects of encoding, the signals being received in the order of shooting and / or in the order of playback time. The frame memory 101 provides stored image signals of the encoding frame in units of predetermined pixel blocks to the motion vector detection unit 102, the prediction method determination unit 107 and the residual signal generation unit 108. In this process, image signals of frames stored in the shooting order and / or in order of playing time, reordered in coding order and issued from the frame memory 101 in units of pixel blocks.

The motion vector detection unit 102 detects motion vectors for a corresponding prediction block size and corresponding prediction modes for each prediction block, for example, block matching between a frame signal provided from frame memory 101 and a reference frame provided from decoded frame memory 116. Vector detection unit motion 102 provides the detected motion vector to the motion compensation prediction block 105, the motion vector difference calculator 103, and the block is determined prediction method 107.

Using the encoding information of the already encoded frame signal and the encoding information stored in the storage memory 115, the motion vector difference calculator 103 calculates several motion vector prediction candidates and stores these candidates in the motion vector prediction list, selects the optimal motion vector prediction from several vector prediction candidates motion, registered in the list of predictions of motion vectors, calculates the difference of motion vectors between vectors m of motion detected by the motion vector detecting unit 102 and predicting the motion vector and provides the calculated motion vector difference to the prediction method determining unit 107. Further, the motion vector difference calculating unit 103 provides the prediction method determining unit 107 to the motion vector prediction index that specifies the motion vector prediction selected from motion vector prediction candidates registered in the motion vector prediction list.

The inter prediction information output unit 104 outputs a merge candidate in the merge mode. Using the encoding information of the already encoded prediction unit and the encoding information stored in the storage memory 115, the inter prediction information output unit 104 outputs several merge candidates and registers these candidates in the merge candidate list, which will be described later, selects the appropriate merge candidate from several candidates to merge, registered in the list of candidates for merge, provides the motion compensation prediction unit 105 inter-frame prediction information (e.g. flags predFlagL0 [xP] [yP] and predFlagL1 [xP] [yP], indicating whether to use or not use L0 prediction and / or L1 prediction, reference indices refIdxL0 [xP] [yP] and refIdxL1 [xP] [yP], motion vectors mvL0 [xP] [yP] and mvL1 [xP] [yP], etc.) of each prediction unit of the selected merge candidate, and provides the prediction method determination unit 107 with a merge index that specifies the selected candidate for merger. Here, xP and yP are indices indicating the position of the upper left pixel inside the prediction block in the frame. The detailed configuration and operation of the inter prediction information output unit 104 will be presented later.

The motion compensation prediction unit 105 generates a frame prediction signal (motion compensation prediction) from the reference frame using the motion vector detected by the motion vector detection unit 102 and the inter prediction information output unit 104, and provides the frame prediction signal to the prediction method determination unit 107. In the L0 prediction and in the L1 prediction, one-direction prediction is performed. In the case of bi-prediction (Pred_BI), two-way prediction is performed, the corresponding predicted inter-frame prediction signals of the L0 prediction and L1 prediction are adaptively multiplied by a weighting factor, an offset value is added, and the signals are convolved to form a complete frame prediction signal.

The intra prediction unit 106 performs intra prediction for each intra prediction mode. The intra prediction unit 106 generates a frame prediction signal from the decoded frame stored in the decoded frame memory 211, selects an appropriate intra prediction mode from several intra prediction modes, and provides the prediction method determining unit 107 with the selected intra prediction mode and the frame prediction signal, in accordance with the selected intra prediction mode.

The prediction method determination unit 107 determines the PredMode prediction mode and the PartMode separation mode, which determines the inter-frame prediction (PRED_INTER) or the intra-frame prediction (PRED_INTRA) in units of optimal coding units from several prediction methods by evaluating the code value of the encoding information and the residual signal, the amount of distortion between the prediction signal frame and frame signal for corresponding prediction methods. In the case of inter-frame prediction (PRED_INTER), the prediction method determination unit 107 determines whether or not the mode is a merge mode, in units of the prediction blocks. In the case where the mode is a merge mode, the prediction method determination unit 107 determines the merge index, and in the case where the mode is not a merge mode, it determines the inter prediction mode, motion vector prediction index, reference indices in L0 and L1, the difference of motion vectors and other, and in accordance with the results of these definitions, provides the encoding information to the first bit stream 110 generation unit.

Further, for the prediction method determination unit 107, information indicating a specific prediction method and encoding information containing a motion vector corresponding to this specific prediction method are stored in the encoding information storage memory 115.

Here, the stored encoding information includes, for example: PredMode prediction mode and PatrMode separation mode of the respective encoding blocks, predFlagL0 [[xP] [yP] and predFlagL1 [xP] [yP] flags indicating whether to use or not use L0 prediction and L1 -prediction of each prediction block, reference indices refIdxL0 [xP] [yP] and refIdxL1 [xP] [yP] in L0 and L1, motion vectors mvL0 [xP] [yP] and mvL1 [xP] [yP] in L0 and L1. Here, xP and yP are indices indicating the position of the upper left pixel in the prediction block within the frame. In the case where the prediction mode PredMode is intra-frame prediction (MODE_INTRA), then both flags, predFlagL0 [xP] [yP], indicating whether to use or not using L0-prediction, and predFlagL1 [xP] [yP], indicating that whether or not to use L1 prediction are 0. On the other hand, in the case where the prediction mode PredMode is inter prediction (MODE_INTER) and the inter prediction mode is L0 prediction (Pred_L0), then the flag predFlagL0 [xP] [yP] indicating whether to use or not use L0 prediction is 1, and the flag predFlagL1 [xP] [yP], indicating whether to use or not using L1 prediction, is 0. In the case when the inter prediction mode is L1 prediction (Pred_L1), the flag predFlagL0 [xP] [yP], indicating whether to use or not use L0 prediction is 0, and the predFlagL1 [xP] [yP] flag indicating whether to use or not use L1 prediction is 1. In the case where the inter prediction mode is bi-prediction ( Pred_BI), then both flags, predFlagL0 [xP] [yP], indicating whether to use or not use L0 prediction, and f lag predFlagL1 [xP] [yP], indicating whether to use or not use L1 prediction, are 1. The prediction method determination unit 107 provides a residual signal generation unit 108 and a decoded signal convolution unit 114 with a frame prediction signal corresponding to a mode determined by it predictions.

The residual signal generating unit 108 generates a residual signal by performing a subtraction operation between the signal of the encoding frame and the frame prediction signal, and provides a residual signal to the orthogonal transform / quantize unit 109. The orthogonal transform / quantize unit 109 performs orthogonal transform and quantization of the residual signal to according to the quantization parameter, thereby generating an orthogonally transformed and quantized residual signal, and provided It is orthogonally transformed and quantized residual signal to generate a second block of the bit stream 111 and block dequantization / inverse orthogonal transformation 113. Further, the block orthogonal transformation / quantization 109 stores a quantization parameter in encoding information storage memory 115.

The generating unit of the first bitstream 110, in addition to the information of each sequence, each frame, each layer and each coding unit, encodes the information for coding, in accordance with the prediction method defined for each coding unit and for each prediction unit, the prediction method determining unit 107 More specifically, the generation unit of the first bit stream 110 for each encoding unit encodes information for encoding such as PredMode prediction mode, PartMo split mode de, a flag that determines whether or not the merge mode is in the case of inter prediction (PRED_INTER), the merge index in the case of a merge mode, the inter prediction mode in the case when the mode is not a merge mode, motion vector prediction index, information related to the difference of motion vectors and so on, in accordance with the prescribed syntax rule, which will be described later, thereby generating a first bit stream and providing this first bit stream to the multiplexing unit 112 .

The generation unit of the second bitstream 111 entropy encodes the orthogonally transformed and quantized residual signal in accordance with the prescribed syntax rule, thereby generating a second bitstream and providing this second bitstream to the multiplexing unit 112. In the multiplexing unit 112, the first bitstream and the second bitstream are combined in accordance with the prescribed syntax rule, thereby generating a bitstream.

The dequantization / inverse orthogonal transform unit 113 performs dequantization and inverse orthogonal transform of the orthogonally transformed and quantized residual signal provided from the orthogonal transform / quantize unit 109, thereby calculates the residual signal and provides this residual signal to the signal convolution unit of the decoded frames 114. The signal convolution unit decoded frames 114 performs the convolution operation of a predicted frame signal obtained in accordance with ultati determine the prediction method 107 by the determining unit, and the residual signal, which is the dequantized and inversely orthogonally transformed signal from the dequantization / inverse orthogonal transformation unit 113, thereby generates a decoded frame and stores the decoded frame in the memory of decoded frames 116. Depending on the circumstances, for a decoded frame, a filtering process is performed that reduces distortion, such as, for example, block distortion resulting from encoding, and this decoded frame is accordingly stored in the memory of the decoded frames 116.

In FIG. 1 is a block diagram showing the structure of a moving image decoding apparatus according to an embodiment of the invention, wherein the moving image decoding apparatus corresponds to the moving image encoding apparatus in FIG. 1. The moving image decoding device, in accordance with an embodiment, comprises a separation unit 201, a decoding unit for a first bit stream 202, a decoding unit for a second bit stream 203, a motion vector calculation unit 204, an inter prediction information output unit 205, a motion compensation prediction unit 206 , intraframe prediction unit 207, dequantization / inverse orthogonal transform unit 208, convolution unit of decoded frame signals 209, encoding information storage memory 210 and decoded frame memory 211.

The decoding process in the moving picture decoding apparatus of FIG. 2 corresponds to the decoding process carried out in the moving picture coding apparatus of FIG. 1. Therefore, the corresponding configurations of the motion compensation prediction unit 206, the dequantization / inverse orthogonal transform unit 208, the convolution unit of the decoded frame signals 209, the encoding information storage memory 210, and the decoded frame memory 211 in FIG. 2 have functions corresponding to the configurations of the motion compensation prediction block 105, the dequantization / inverse orthogonal transform block 113, the signal convolution block of the decoded frames 114, the encoding information storage memory 115, and the decoded frame memory 116 of the moving image encoding device of FIG. 1, respectively.

The bitstream provided to partition block 201 is partitioned in accordance with a prescribed syntax rule. The separated first bitstream is provided to the decoding unit of the first bitstream 202, and the separated second bitstream is provided to the decoding unit of the second bitstream 203.

The decoding unit of the first bitstream 202 decodes the provided encoded bitstream and obtains encoding information for each sequence, each frame, each layer and each encoding unit, as well as encoding information for each prediction unit. More specifically, the decoding unit of the first bit stream 202 decodes encoding information relating, for example, to the PredMode prediction mode, which for each coding block determines whether the prediction is inter-frame prediction (PRED_INTER) or intra-frame prediction (PRED_INTRA), determines the PartMode split mode, a flag that determines whether or not the mode is the merge mode in the case of inter prediction (PRED_INTER), the merge index in the case when the mode is the merge mode, inter prediction mode indications in the case when the mode is not a merge mode, the motion vector prediction index, the motion vector difference or the like, in accordance with the prescribed syntax rule, which will be described later, and provides encoding information to the motion vector calculation unit 204, the inter prediction information output unit 205 or intraframe prediction unit 207.

The decoding unit of the second bitstream 203 decodes the provided bitstream, thereby calculating the orthogonally transformed and quantized residual signal and provides the orthogonally transformed and quantized residual signal to the dequantization / inverse orthogonal transform unit 208.

When the prediction mode PredMode of the prediction unit that is the decoding object is inter prediction (PRED_INTER) and not the merge mode, the motion vector calculation unit 204, using the encoding information of the signal of the already decoded frame and stored in the encoding information storage memory 210, outputs several prediction candidates motion vectors and registers these candidates in the motion vector prediction list, which will be described later. The motion vector calculation unit 204 selects from several motion vector prediction candidates registered in the motion vector prediction list, the motion vector prediction in accordance with the motion vector prediction index, which is decoded in the decoding unit of the first bit stream 202 and provided to it, computes the motion vector from the difference the vector decoded by the decoding unit of the first bitstream 202, and from the selected motion vector prediction. The motion vector calculation unit 204 provides the motion compensation prediction unit 206 with a motion vector together with other information for encoding, and stores this motion vector and other information for encoding in the storage memory of the encoding information 210. Information for encoding the prediction unit provided and stored in this process, contains: PredMode prediction mode, PartMode split mode, predFlagL0 [xP] [yP] and predFlagL1 [xP] [yP] flags indicating whether to use or not use L0 prediction and L1 prediction, respectively Thus, the reference indices refIdxL0 [xP] [yP] and refIdxL1 [xP] [yP] in L0 and L1, the motion vectors mvL0 [xP] [yP] and mvL1 [xP] [yP] in L0 and L1, and so on. Here, xP and yP are indices indicating the position of the upper left pixel in the prediction block within the frame. In the case where the prediction mode PredMode is inter prediction (MODE_INTER) and the inter prediction mode is L0 prediction (Pred_L0), then the predFlagL0 flag indicating whether to use or not using L0 prediction is 1, and the predFlagL1 flag indicating whether to use or not use L1 prediction is 0. In the case where the inter prediction mode is L1 prediction (Pred_L1), the predFlagL0 flag indicating whether to use or not use L0 prediction is 0, and the predFlagL1 flag indicating whether or not to use L1 prediction is 1. In the case where the inter prediction mode is bi-prediction (Pred_BI), then the predFlagL0 flag indicating whether to use or not use L0 prediction and the predFlagL1 [xP] [yP flag ] indicating whether to use or not use L1 prediction, both are 1.

When the prediction mode PredMode of the prediction unit being the decoding object is inter prediction (PRED_INTER), and if the mode is the merge mode, then the inter prediction information output unit 205 outputs the merge candidate. By using the encoding information of the previously encoded prediction unit and the encoding information stored in the storage memory 115, the inter prediction information output unit 205 outputs several merge candidates and registers these candidates in the merge candidate list, which will be described later. The inter prediction information output unit 205 selects from several merge candidates registered in the list of merge candidates, a merge candidate corresponding to the merge index, which is decoded in the decoding unit of the first bit stream 202 and provided to them. The inter prediction information output unit 205 provides the motion compensation prediction unit 206 with inter prediction information of the selected merge candidate, such as the predFlagL0 [xP] [yP] and predFlagL1 [xP] [yP] flags indicating whether or not to use L0 prediction and L1 prediction, reference indices refIdxL0 [xP] [yP] and refIdxL1 [xP] [yP] in L0 and L1, the motion vectors mvL0 [xP] [yP] and mvL1 [xP] [yP] in L0 and L1, and etc., and stores inter prediction information in the encoding information storage memory 210. Here, xP and yP are indices, yk indicating the position of the upper left pixel in the prediction block inside the frame. Details of the configuration and operation of the inter prediction information output unit 205 will be given later.

The motion compensation prediction unit 206 generates a frame prediction signal by inter prediction (motion compensation prediction) using the inter prediction information computed in the motion vector calculation unit 204 or the inter prediction information output unit 205 from the reference frame stored in the memory of the decoded frames 211 , and provides this frame prediction signal to a convolution block of decoded frame signals 209. In the case of bi-prediction (Pred_BI), the signals of two prediction frames The motion compensation equations in L0 prediction and L1 prediction are adaptively multiplied by weights and a convolution of these signals is performed, thereby generating a complete frame prediction signal.

The intra prediction block 207 performs intra prediction when the PredMode prediction mode of the decoded prediction block is intra prediction (PRED_INTRA). The encoding information decoded in the decoding unit of the first bit stream comprises an intra-frame prediction mode. Based on this intra-frame prediction mode, a frame prediction signal is generated from the decoded frame signal stored in the decoded frame memory 211, which is provided to the convolution unit of decoded frame signals 209. Both flags, predFlagL0 [xP] [yP] and predFlagL1 [xP] [yP] indicating whether to use or not use L0 prediction and L1 prediction are set to 0 and stored in the encoding information storage memory 210. Here, xP and yP are indices indicating the position of the upper left pixel in the prediction block inside the frame.

The dequantization / inverse orthogonal transform unit 208 performs inverse orthogonal transform and dequantization of the orthogonally transformed and quantized residual signal, which is decoded in the decoding unit of the first bit stream 202, resulting in the inverse orthogonally transformed and dequantized residual signal.

The decoded frame signal reconciliation unit 209 decodes the decoded frame signal by convolution of the frame prediction signal, which is the inter prediction signal predicted by the motion compensation prediction unit 206, or the frame prediction signal, which is the intra prediction signal predicted by the intra prediction unit 207, and the residual signal, which is the inverse orthogonally transformed and dequantized signal received by the dequantization / inverse orthogon block conversion 208, and stores the received signal of the decoded frame in the memory of the decoded frames 211. When the decoded frame is stored in the memory of the decoded frames 211, then, depending on the circumstances, a filtering process is performed for the decoded frame, which reduces distortion, such as block distortion resulting from encoding, and this decoded frame is stored in the memory of the decoded frames 211.

Regarding the syntax

Next, an explanation will be given of the syntax, which is a general rule for encoding and decoding a moving image bitstream, which is encoded by a moving image encoding device using a motion vector prediction method in accordance with the present embodiment, and which is decoded by a decoding device.

In FIG. 10 shows a first syntax structure that is described in a layer header for each layer of a bitstream generated in accordance with the present embodiment. Only syntax elements related to the present embodiment are shown in the figure. In the case where the layer type is B-layer, the flag collocated_from_10_flag is set. This flag collocated_from_10_flag indicates which of the reference frames uses the colPic frame of another point in time, that is, the reference frame registered in the reference list in L0, or the reference frame registered in the reference list in L1 of the frame that contains the prediction block that is the object processing. The colPic frame of another point in time is used when deriving a candidate for predicting a motion vector in time or when deriving a candidate for merge. The collocated_from_10_flag flag will be described in detail later.

Further, the syntax elements described above can be set in the totality of the frame parameters, which describes the syntax elements defined for each frame.

In FIG. 11 shows the syntax structure described for each prediction block. In the case where the value of the prediction mode PredMode of the prediction block is inter-frame prediction (MODE_INTER), merge_flag [x0] [y0] is set, which indicates whether or not the mode is a merge mode. Here x0 and y0 are indices indicating the position of the upper left pixel in the prediction block inside the luminance signal frame, and merge_flag [x0] [y0] is a flag indicating whether or not the mode of the prediction block located with coordinates (x0, y0) inside the frame, by merge mode.

Further, in the case where merge_flag [x0] [y0] is 1, which indicates that the mode is a merge mode, the syntax element merge_idx [x0] [y0] of the merge list index is set, which is a list of merge candidates to which appeal is being made. Here x0 and y0 are indices indicating the position of the upper left pixel in the prediction block inside the frame, and merge_flag [x0] [y0] is the merge index of the prediction block located with coordinates (x0, y0) inside the frame. In FIG. 12 shows an example of the entropy code of the syntax element merge_idx [x0] [y0] of the merge index. According to the present embodiment, the number of merge candidates is set to 5. When the merge index is 0, 1, 2, 3, and 4, then the syntax code of the merge_idx [x0] [y0] merge index is '0', '10, '110', '1110' and '1111', respectively.

On the other hand, in the case when merge_flag [x0] [y0] is 0, then merge_flag [x0] [y0] indicates that the mode is not a merge mode, and in the case when the layer type is a B-layer, it is set syntax element inter_pred_flag [x0] [y0], which identifies the inter prediction mode. This syntax element distinguishes between L0 prediction (Pred_L0), L1 prediction (Pred_L1) and bi-prediction (Pred_BI). For each L0 and L1, the syntax elements of the reference index ref_idx10 [x0] [y0] and ref_idx_11 [x0] [y0] are specified for specifying the reference frame, and the syntax elements mvd_10 [x0] [y0] [j] and mvd_11 [x0] [y0 ] [j] the difference of the motion vectors, which is the difference between the motion vector of the prediction block derived by the detection of the motion vector and the motion vector prediction. Here, x0 and y0 are indices indicating the position of the upper left pixel in the prediction block within the frame. ref_idx_10 [x0] [y0] and mvd_10 [x0] [y0] [j] are the reference index and the difference of the motion vectors in L0 of the prediction block located with the coordinates (x0, y0) inside the frame, respectively. ref_idx_11 [x0] [y0], mvd_11 [x0] [y0] [j] are the reference index and the difference of the motion vectors in L1 of the prediction block located with coordinates (x0, y0) inside the frame, respectively. j indicates the components of the difference of the motion vectors. A value of 0 for j represents the component of x, and a value of 1 for j represents the component of y. Next, the syntax elements mvp_idx_10 [x0] [y0] and mvp_idx_11 [x0] [y0] of the motion vector prediction list index, which is a list of motion vector prediction candidate candidates, are set. Here, x0 and y0 are indices that indicate the position of the upper left pixel in the prediction block within the frame. mvp_idx_10 [x0] [y0] and mvp idx_11 [x0] are respectively the motion vector prediction index in L0 and L1 of the prediction block located with coordinates (x0, y0) inside the frame. In accordance with this embodiment, the number of candidates is set to 2.

The inter prediction information output method, in accordance with an embodiment, is implemented in the inter prediction information output unit 104 of the moving image encoding apparatus of FIG. 1 and in the inter prediction information output unit 205 of the moving picture decoding apparatus of FIG. 2.

Next, an explanation will be given of a method for outputting inter prediction information, in accordance with an embodiment, with reference to the drawings. A method for outputting inter prediction information is executed for each prediction block that forms a coding block on any of the coding processes or decoding processes. If the prediction mode PredMode of the prediction block is inter-frame prediction (MODE_INTER) and the mode is a merge mode, then in the case of encoding, a method is used when the prediction mode, the reference index and the motion vector of the prediction block being the encoding are output using the prediction mode, reference index and vector motion of the already encoded prediction block. In the case of decoding, a method is used when the prediction mode, the reference index and the motion vector of the prediction block that is the object of decoding are output using the prediction mode, the reference index and the motion vector of the already decoded prediction block.

In merge mode, the merge candidate is not only derived from five prediction blocks (i.e., prediction block A adjacent to the left, prediction block B adjacent to the top, prediction block C adjacent to the upper right, prediction block D adjacent to the lower left, and prediction block E adjacent top left) as shown in FIG. 5, FIG. 6, FIG. 7 and FIG. 8, but also from the prediction block in the prediction block Col (T0 or T1), which exists in the same position or in its vicinity, but at a different point in time, as shown in FIG. 9. The inter prediction information output unit 104 of the moving image encoding device and the inter prediction information output unit 205 of the moving image decoding device register these merge candidates in a list of merge candidates in a predetermined order, which is common for both encoding processes and processes decoding. The inter prediction information output unit 104 of the moving picture coding apparatus determines a merge index that specifies an candidate list element and encodes it by a first bit stream generating unit. The inter prediction information output unit 205 of the moving picture decoding apparatus selects the prediction block from the list of merge candidates in accordance with the merge index decoded in the decoding unit of the first bit stream 202 and transmitted from it, and conducts motion compensation prediction using inter prediction information ( for example, a prediction mode, a reference index, a motion vector or the like) of a selected merge candidate.

In FIG. 13 shows a detailed configuration of the inter prediction information output unit 104 of the moving picture coding apparatus of FIG. 1. In FIG. 14 shows a detailed configuration of the inter prediction information output unit 205 of the moving picture decoding apparatus of FIG. 2.

Parts bounded by the thick line rectangle in FIG. 13 and FIG. 14, an inter prediction information output unit 104 of a moving image encoding apparatus and an inter prediction information output unit 205 of a moving image decoding apparatus, respectively, are shown.

In addition, the parts surrounded by a thick dotted line in these rectangles show a merge candidate list building unit 120 of the moving image coding device and a merge candidate list building unit 220 of the moving image decoding device, respectively. The merger candidate list building block is also present in the moving image decoding device, which corresponds to the moving image encoding device, in accordance with an embodiment, so that the same output results can be obtained that do not create a conflict between encoding and decoding.

In accordance with the method for outputting inter prediction information, in the process of outputting the merge candidates and in the process of constructing the merge candidate list, the moving picture encoding device 120 and the merge candidate list building unit 220 of the moving image decoding device are received in in accordance with an embodiment that the process of withdrawing candidates for merger and the process of constructing a list of candidates for merger of the prediction block, which is Xia object processing is executed without referring to the block prediction contained in the coding block, identical coding block comprising the prediction unit being the object of processing. Similarly, when the partition mode (PartMode) of the encoding block is not a 2Nx2N partition (PART_2Nx2N), that is, when there are several prediction blocks inside the encoding block, the process of deriving merge candidates and the process of constructing a list of merge candidates the prediction block being the object of processing may be performed for each prediction block within the encoding block in parallel during encoding.

Using now FIG. 15, an explanation will be given of each separation mode (PartMode) in parallel execution of the process of constructing a list of candidates for merging the corresponding prediction block within the encoding block. In FIG. 15 illustrates prediction blocks that are adjacent to a prediction block that is a processing object for each partition mode (PartMode) of a prediction block that is a processing object. In FIG. 15, blocks A0, B0, C0, D0, and E0 show: prediction block A adjacent to the left side of the prediction block being the object of processing whose partition index PartIdx is 0, prediction block B adjacent to its upper side, prediction block C adjacent to its upper right vertex, the prediction block D adjacent to its lower left vertex, and the prediction block E adjacent to its upper left vertex, respectively. Blocks A1, B1, C1, D1 and E1 show: prediction block A adjacent to the left side of the prediction block being the object of processing, partition index PartIdx of which is 1, prediction block B adjacent to its upper side, prediction block C adjacent to its upper right vertex, prediction block D adjacent to its lower left vertex, and prediction block E adjacent to its upper left vertex, respectively. Blocks A2, B2, C2, D2, and E2 show: prediction block A adjacent to the left side of the prediction block being the object of processing, partition index PartIdx of which is 2, prediction block B adjacent to its upper side, prediction block C adjacent to its upper right vertex, prediction block D adjacent to its lower left vertex, and prediction block E adjacent to its upper left vertex, respectively. Blocks A3, B3, C3, D3 and E3 show: prediction block A adjacent to the left side of the prediction block being the object of processing, partition index PartIdx of which is 3, prediction block B adjacent to its upper side, prediction block C adjacent to its upper right vertex, prediction block D adjacent to its lower left vertex, and prediction block E adjacent to its upper left vertex, respectively.

In FIG. 15 (b), FIG. 15 (c) and FIG. 15 (d) adjoining prediction blocks are shown for cases where the partition mode (PartMode) is a 2NxN partition (PART_2NxN), 2NxnU partition (PART_2NxnU), or 2NxnD partition (PART_2NxnD), where the encoding block being processed is divided into two prediction blocks arranged vertically. Prediction block B1 adjacent to the prediction block that is the processing object, PartIdx of which is 1, is a prediction block whose PartIdx is 0. Therefore, the process of deriving merge candidates and the process of constructing a list of candidates for merging of the prediction block whose PartIdx is 1 is not can be performed by referring to the prediction block B1 until the process of outputting the candidates for merger and the process of constructing a list of candidates for merging the prediction block, which is the prediction block B1, belongs to It lives to the same encoding block and whose PartIdx is 0, it will not be completed and the used merge candidate will not be specified. Therefore, in the method for outputting inter prediction information, in accordance with an embodiment, in the case where the separation mode is 2NxN separation (PART_2NxN), 2NxnU separation (PART_2NxnU) or 2NxnD separation (PART_2NxnD), and in the case when the block PartIdx of the prediction being the object of processing is 1, the process of outputting candidates for merging and the process of constructing a list of candidates for merging two prediction blocks in a coding block can be performed in parallel with accessing the encoding information of the prediction blocks A1, C1, D1 and whether E1, which are not contained in the coding unit identical to the coding unit containing the prediction unit that is the object of processing, and the process of deriving merge candidates and the process of constructing a list of merge candidates of the prediction unit, PartIdx of which is 1, without accessing the coding information of the block prediction B1, which is a prediction block adjacent to the upper side of the prediction block being the object of processing, and is contained in a coding unit identical to the coding unit, zhaschemu prediction unit being the object of processing, and which is PartIdx 0.

In FIG. 15 (e), FIG. 15 (f) and FIG. 15 (g) adjoining prediction blocks are shown for cases where the partition mode (PartMode) is an Nx2N partition (PART_Nx2N), an nLx2N partition (PART_nLx2N) or an nRx2ND partition (PART_nRx2N), where the encoding block being processed is divided into two prediction blocks located horizontally. Prediction block A1 adjacent to the prediction block that is the processing object, PartIdx of which is 1, is a prediction block whose PartIdx is 0. Therefore, the process of deriving merge candidates and the process of constructing a list of candidates for merging of the prediction block whose PartIdx is 1 is not can be performed by referring to the prediction block A1 until the process of deriving the merge candidates and the process of constructing the list of merge candidates of the prediction block, which is the prediction block A1, belongs to the same coding block and whose PartIdx is 0, will not be completed and the merge candidate used will not be specified. Therefore, in the method for outputting inter prediction information, in accordance with an embodiment, in the case where the separation mode is Nx2N separation (PART_Nx2N), nLx2N separation (PART_nLx2N) and nRx2N separation (PART_nRx2N), and in the case when the block PartIdx of the prediction that is the object of processing is 1, the process of outputting candidates for merging and the process of constructing a list of candidates for merging the corresponding prediction blocks inside the coding block can be performed in parallel with accessing the coding information of the prediction blocks indications B1, C1, D1 or E1 that are not contained in the coding unit identical to the coding unit containing the prediction unit that is the object of processing and the process of deriving merge candidates and the process of constructing a list of merge candidates for the prediction unit, PartIdx of which 1, without reference to the encoding information of prediction block A1, which is a prediction block adjacent to the left side of the prediction block that is the processing object, and is contained in a coding block identical to the coding block Hovhan comprising prediction unit being the object of processing, and which is PartIdx 0.

Here, an explanation will be given of the parallel processing of the merger candidate withdrawal process and the merger candidate list building process. In FIG. 16 is a flowchart illustrating a process for deriving merge candidates and a process for constructing a list of merge candidates in sequential processing, and FIG. 17 is a flowchart illustrating a process for deriving merge candidates and a process for constructing a list of merge candidates in parallel processing.

In the sequential processing of the merger candidate withdrawal process and the merger candidate list building process shown in FIG. 16, a merge candidate is displayed and a list of merge candidates is constructed for the prediction block whose partition index PartIdx is 0, the encoding block that is the processing object (step S101). Further, in the case where the separation mode (PartMode) is a 2Nx2N partition (PART_2Nx2N) (not in step S102), the merge candidate withdrawal process and the merge candidate list construction process are completed. In the case where the partition mode (PartMode) is not 2Nx2N partition (PART_2Nx2N) (No in step S102), that is, in the case where the partition mode (PartMode) is 2NxN partition (PART_2NxN), 2NxnU partition (PART_2NxnU) , 2NxnD splitting (PART_2NxnD), Nx2N splitting (PART_Nx2N), nLx2N splitting (PART_nLx2N) or nRx2N splitting (PART_nRx2N), the merge candidate is displayed and the list of merge candidates is constructed for the prediction block whose splitting index PartIdx is 1 block coding, which is the object of processing (step S103), and the process of outputting candidates for merging and the process of building spi ska candidates for the merger ends, respectively.

In the parallel processing of the merger candidate withdrawal process and the merger candidate list building process shown in FIG. 17, a merge candidate is derived and a list of merge candidates is constructed for the prediction block whose partition index PartIdx is 0, the encoding block that is the processing object (step S101). In parallel with step S101, in the case where the partition mode (PartMode) is not 2Nx2N partition (PART_2Nx2N) (No in step S102) that is, in the case where the partition mode (PartMode) is 2NxN partition (PART_2NxN), 2NxnU- split (PART_2NxnU), 2NxnD split (PART_2NxnD), Nx2N split (PART_Nx2N), nLx2N split (PART_nLx2N) or nRx2N split (PART_nRx2N), the merge candidate is displayed and the list of split candidates is constructed for the merge index for which is 1, of the encoding unit that is the object of processing (step S103).

In the parallel processing of the merger candidate withdrawal process and the merger candidate list building process shown in FIG. 17, in the case where the partition mode (PartMode) is 2NxN partition (PART_2NxN), 2NxnU partition (PART_2NxnU), 2NxnD partition (PART_2NxnD), Nx2N partition (PART_Nx2N), nLx2N partition (PART_nRxN2) (PART_nRx2N), the process of deriving candidates for merger and the process of constructing a list of candidates for merging two prediction blocks, the partition index PartIdx of which are 0 and 1, respectively, can be started simultaneously by performing the output of candidates for merger and building a list of candidates for merging the prediction block, whose partition index PartIdx is It is 1, inside the same coding block, without accessing the prediction block, whose partition index PertIdx is 0.

Also in the sequential processing of the merger candidate withdrawal process and the merger candidate list building process shown in FIG. 16, a process for deriving merge candidates and a process for constructing a list of merge candidates for a prediction block whose partition index PartIdx is 1 can be performed without reference to a prediction block whose partition index PartIdx is 0.

Although, in accordance with the present embodiment, it is assumed that the NxN partition (PART_NxN) is not defined as the partition mode (PartMode), the NxN partition (PART_NxN) can also be determined. In FIG. 15 (h) adjoining prediction blocks are shown for the case where the partition mode (PartMode) is NxN partition (PART_NxN) in which the luminance signal of the encoding unit being processed is divided into four blocks vertically and horizontally. Prediction block B1 adjacent to the prediction block that is the processing object, PartIdx of which is 1, is a prediction block whose PartIdx is 0. Therefore, the process of deriving merge candidates and the process of constructing a list of candidates for merging of the prediction block whose PartIdx is 1, an appeal to the prediction block A1 cannot be carried out until the process of deriving the merge candidates and the process of constructing the list of candidates for the merger of the prediction block, which is the prediction block A1, belongs to the same coding block and whose PartIdx is 0, it will not be completed and the merge candidate used will not be specified. Therefore, in the method for outputting inter prediction information, in accordance with an embodiment, in the case where the separation mode is NxN separation (PART_NxN) and in the case where the PartIdx of the prediction unit being processed is 1, the merge candidate output process and the process of constructing a list of candidates for merging the corresponding prediction blocks inside the coding unit can be carried out in parallel, by executing the process of deriving candidates for merging and the process of constructing a list of candidates for prediction block, PartIdx of which is 1, without reference to encoding information of prediction block A1, PartIdx of which is 0. Prediction block B2, adjacent to the prediction block that is the processing object, PartIdx of which is 2, is a prediction block whose PartIdx is 0 , and prediction block C2 is a prediction block, PartIdx of which is 1. Therefore, the process of deriving merge candidates and the process of constructing a list of candidates for merging of the prediction block, PartIdx of which is 2 , access to the prediction blocks B2 and C2 cannot be carried out until the process of deriving the merge candidates and the process of constructing the list of candidates for merging the prediction blocks, which are the prediction blocks B2 and C2, belong to the same coding block and which PartIdx is 0 and 1, respectively, will not be completed and the merge candidate used will not be specified. Therefore, in the method for outputting inter prediction information in accordance with an embodiment, in the case where the separation mode is NxN separation (PART_NxN) and in the case where the PartIdx of the prediction unit being processed is 2, the merge candidate output process and the process of constructing a list of candidates for merging the corresponding prediction blocks inside the coding unit can be carried out in parallel, by executing the process of deriving candidates for merging and the process of constructing a list of candidates for the prediction block, PartIdx of which is 2, without reference to the encoding information of the prediction blocks B2 and C2, whose PartIdx is 0 and 1, respectively. Prediction block E3 adjacent to the prediction block that is the processing object, PartIdx of which is 3, is a prediction block whose PartIdx is 0, prediction block B3 is a prediction block, PartIdx of which 1, and prediction block A3 is a prediction block, of which PartIdx is 2. Therefore, the process of deriving candidates for merger and the process of constructing a list of candidates for merging a prediction block, PartIdx of which is 3, cannot be performed with the prediction blocks E3, B3, and A3 until Oh, until the process of deriving candidates for merging and the process of constructing a list of candidates for merging prediction blocks, which are prediction blocks E3, B3, and A3, belong to the same coding block and whose PartIdx is 0, 1, and 2, respectively, the merger candidate used has been completed and will not be specified. Therefore, in the method for outputting inter prediction information, in accordance with an embodiment, in the case where the separation mode is NxN separation (PART_NxN), and in the case where the PartIdx of the prediction unit being processed is 3, the merge candidate output process and the process of constructing a list of candidates for merging the corresponding prediction blocks in the coding unit can be carried out in parallel, by executing the process of outputting candidates for merger and the process of constructing a list of candidates for merger Lok prediction, PartIdx 3 which is, without reference to the prediction information encoding E3 blocks B3 and A3, PartIdx which is 0, 1, and 2, respectively.

Inter prediction information output unit 104 in FIG. 13 comprises a spatial merge candidate generation unit 130, reference index derivation unit 131, a time merge candidate generation unit 132, a merge candidate registration unit 133, a merge candidate equality determination unit 134, a merge candidate replenishment unit 135 and an information selection unit encoding 136.

The inter prediction information output unit 205 in FIG. 14 comprises a spatial merge candidate generation unit 230, a time merge candidate reference index output unit 231, a time merge candidate generation unit 232, a merge candidate registration unit 233, a merger candidate equality determination unit 234, a merge candidate replenishment unit 235 and an encoding information selection unit 236.

In FIG. 18 is a flowchart illustrating a merge candidate withdrawal process and a merge candidate list construction process, which is a common function for the inter prediction information output unit 104 of the moving image encoding device and the inter prediction information output unit 205 of the moving image decoding device, in accordance with with an example embodiment of the invention. Below we will sequentially explain these processes. Although an explanation will be given in the following for the case where the layer type slice_type is a B-layer, this explanation can also be applied to the case of a P-layer, unless otherwise stated. However, in the case where the slice_type layer type is a P layer, the inter prediction mode contains only L0 prediction (Pred_L0) and contains neither L1 prediction (Pred_L1) nor bi-prediction (Pred_BI). Therefore, the process regarding L1 may be omitted.

In the spatial merge candidate generation unit 130 of the inter prediction information output unit 104 of the moving image encoding device, and in the spatial merge candidate generation unit 230 of the inter prediction information output unit of the moving image decoding device 205 of the moving image decoding device, spatial merge candidates A, B, C and D and E from the corresponding prediction blocks A, B, C, D and E adjacent to the block that is the object of encoding or decoding. Next, N is determined which indicates A, B, C. D, E, or a candidate for spatial fusion of Co1. The availableFlagN flag is issued, indicating the possibility or impossibility of using inter-frame prediction information of the prediction block N as a spatial merge candidate N, the refIdxL0N reference index in L0 and the spatial merge candidate refIdxL1N in L1, the predFlagL0N prediction flag in L0, indicating whether L0 prediction is performed or not, and a predFlagL1N prediction flag in L1 indicating whether or not L1 prediction is executed, the motion vector mvL0N in L0 and the motion vector mvL1N in L1 (step S201). However, in accordance with the present embodiment, since the merge candidate is derived without reference to the prediction block contained in the encoding unit identical to the encoding unit that contains the prediction unit being processed, the spatial merge candidate contained in the encoding unit identical to a coding unit that contains a prediction unit that is the object of processing is not output. A detailed explanation will be given later on in the detailed processing procedure of step S201 with reference to the flowchart shown in FIG. 19.

Subsequently, in the output unit of reference indices 131 candidates for time merging of the inter prediction information output unit 104 of the moving image coding apparatus and in the output unit of reference indices 231 candidates for time merging of the inter prediction information output unit 205 of the moving image decoding device, it is outputted and output the reference index of the candidate for time merge from the prediction block adjacent to the block that is the object of encoding or decoding (step S202). However, in accordance with the present embodiment, the reference index of the time merge candidate is displayed without reference to the prediction block contained in the coding block identical to the coding block that contains the prediction block being processed. In the case where the slice_type layer type is a P-layer and inter-frame prediction is performed using the inter-frame prediction information of the time merge candidate, only the reference index in L0 is output for the purpose of conducting the L0 prediction (Pred_L0). In the case where the slice_type layer type is B-layer and inter-frame prediction is carried out using the inter-frame prediction information of the time merge candidate, the corresponding reference indices in L0 and L1 are output for bi-prediction (Pred_BI). A detailed explanation will be given later on in the detailed processing procedure of step S202 with reference to the flowcharts shown in FIG. 21, FIG. 23, FIG. 25, FIG. 27, FIG. 29, FIG. 30 and FIG. 32.

Following this, in the time merge candidate generation unit 132 of the inter prediction information output unit 104 of the moving image encoding device and in the time merge candidate generation unit 232 of the inter prediction information output unit 232 of the moving image decoding device 205, the time merge candidate is derived from frame of another moment in time and this candidate for time merging is issued. The availableFlagCo1 flag is issued, indicating whether it is possible or impossible to use the candidate for a time merger, the prediction flag predFlagL0Co1, indicating whether or not the L0 prediction of the candidate for a merge in time is conducted, and the prediction flag predFlagL1Co1 indicating whether or not the L1 prediction of the time merge candidate, the motion vector mvL0N at L0, and the motion vector mvL1N at L1 are not performed (step S203). A detailed explanation will be given later on in the detailed processing procedure of step S203 with reference to the flowchart shown in FIG. 34.

Following this, the merge candidate registration unit 133 of the inter prediction information output unit 104 of the moving image coding device and the merge candidate registration unit 233 of the inter prediction information output unit of the moving image decoding device 205 of the mergCandList merge candidate list is generated, and spatial merge candidates are added A, B, C, D, and E, and Co1 time merge candidate to the mergCandList list of merge candidates, which forms the final candidate list atov to merge mergCandList and the list of candidates for a merger mergCandList issued (step S204). A detailed explanation will be given later on in the detailed processing procedure of step S204 with reference to the flowchart shown in FIG. 41.

Following this, the merger candidate equality determination unit 134 of the inter prediction information output unit 104 of the moving image encoding device and the merge equality determination unit 234 of the inter prediction information output unit of the moving image decoding device 205 in the case when vectors are inside the mergeCandLis merge candidate list movements with the same reference indices of the merger candidates have the same values, all such merger candidates are deleted except HAND candidate for the merger, which is the earliest in order, and issued a list of candidates for merger mergeCandList (step S205).

Following this, the merge replenishment unit 135 of the inter prediction information outputting unit 104 of the moving image encoding device and the merging replenishment unit 235 of the inter prediction information outputting unit 205 of the moving image decoding device 205 is replenished with the merge candidate list so that the number of merge candidates, registered within the mergeCandList merge candidate list becomes equal to the specified number, and this mergeCandList merge candidate list is issued I (step S206). In accordance with this embodiment, the number of merger candidates is set to 5.

Although the upper limit of the number of merge candidates registered within the mergeCandList merge candidate list is set to 5, it adds a merge candidate whose prediction mode is bi-prediction (Pred_BI) and the candidate that is obtained by changing the combination of L0-prediction and L1- predictions between merger candidates that have already been registered, a merger candidate whose prediction mode is bi-prediction (Pred_BI), which has a different reference index and whose magnitude of the motion vector is be (0, 0) or others.

Following this, a detailed description will be given of a method for deriving a merge candidate N from the prediction blocks N that are adjacent to the prediction block being the object of encoding or decoding, which is the processing procedure of step S201 in FIG. 18. In FIG. 19 is a flowchart illustrating a procedure of a process for deriving a spatial merge candidate of step S201 in FIG. 18. N includes A (left), B (top), C (top right), D (bottom left) or E (top left), which show adjacent prediction blocks. According to this embodiment, up to four spatial merge candidates are derived from five adjacent prediction blocks.

In FIG. 18, assigning A to the value of the variable N, the coding information of the prediction block A adjacent to the left side of the prediction block that is the object of encoding or decoding is scanned, and the merge candidate A is displayed; assigning B to the value of the variable N, the coding information of the prediction block B adjacent to the upper side is scanned, and the merge candidate B is displayed; assigning C to the value of the variable N, the coding information of the prediction block C, adjacent to the top right, is scanned, and the candidate for merging C is displayed; assigning D to the value of the variable N, the coding information of the prediction block D adjacent to the bottom left is scanned, and the merge candidate D is displayed; and assigning E to the value of the variable N, the coding information of the prediction unit E adjacent to the upper left is viewed, and the merge candidate E is output (steps S1101-S1114).

First, in the case when the variable N is E and when the flags values availableFlagA, availableFlagB, availableFlagC and availableFlagD are added and their total amount is 4 (yes in step S1102), that is, in the case when four candidates for spatial merging are displayed, the flag merge candidate E availableFlagE is set to 0 (step S1107), both values of the motion vectors mvL0E and mvL1E are merged candidate E are set to (0, 0) (step S1108), both flag values of predFlagL0E and predFlagL1E of the merge candidate E are set to 0 ( step S1109) and therein the process of deriving a candidate for spatial merging th ends. According to the present embodiment, up to four candidates for spatial merging are derived from adjacent prediction blocks, therefore, in the case where four candidates for spatial merging have already been withdrawn, there is no need for a further process for deriving candidates for spatial merging.

On the other hand, in the case when the variable N is not E, or in the case when the flags values availableFlagA, availableFlagB, availableFlagC and availableFlagD are added, and their total amount is not equal to 4 (No in S1102), the process proceeds to step S1103. When the adjacent prediction block N is contained in a coding block identical to the coding block containing the prediction block being the output object (Yes in step S1103), the value of the availableFlagN flag of the merge candidate N is set to 0 (step S1107), both values of the motion vectors mvL0N and mvL1N the merge candidate N is set to (0, 0) (step S1108), and both of the flags predFlagL0N and predFlagL1N of the merge candidate N are set to 0 (step S1109). In the case where the adjacent prediction block N is contained in a coding block identical to the coding block containing the prediction block being the output object (Yes in step S1103), the value of the availableFlagN flag of the merger candidate N is set to 0 (step S1107) without accessing information encoding the adjacent prediction block N and setting the flag value availableFlagN of the merge candidate N to 0, and thereby not using it as a candidate for spatial merging, the process of deriving merge candidates and the process of constructing a list of channels Idate to merge the prediction for the respective blocks within the same coding block can be performed in parallel.

More specifically, the case of the prediction block B adjacent to the upper side of the prediction block being the output when the separation mode is 2NxN partition (PART_2NxN), 2NxnU partition (PART_2NxnU) or 2NxnD partition (PART_2NxnD) and when the PartIdx of the prediction block being the object of processing, is 1, corresponds to the case when the adjacent prediction block N is contained in a coding block identical to a coding block containing a prediction block which is an output object. In this case, the prediction block B adjacent to the upper side of the prediction block being the output object is a prediction block that is contained in a coding block identical to the coding block containing the prediction block which is the output object and whose PartIdx is 0. Therefore, not referring to the encoding information of the adjoining prediction block B and setting the flag value availableFlagB of the merge candidate B to 0, and thereby not using it as a candidate for spatial merge, the output process merge candidates and the process of constructing a list of merge candidates for respective prediction blocks within the same coding block can be conducted in parallel.

Further, the case of the prediction block A adjacent to the upper side of the prediction block being the output object when the separation mode is Nx2N partition (PART_Nx2N) nLx2N partition (PART_nLx2N) or nRx2N partition (PART_nRx2N) and when PartIdx of the prediction block being processed , is 1, also corresponds to the case where the adjacent prediction block N is contained in a coding block identical to a coding block containing a prediction block being an output object. Also in this case, the prediction block A adjacent to the left side of the prediction block being the output object is a prediction block that is contained in a coding block identical to the coding block containing the prediction block being the output object, and whose PartIdx is 0. Therefore, without referring to the coding information of the adjoining prediction block A and setting the flag availableFlagA of the merge candidate A to 0, and thereby not using it as a candidate for spatial merging, the process and candidates for merger, and the process of constructing the list of candidates for merger for respective prediction blocks within the same coding block may be performed in parallel.

Also in the case, although it is not defined in accordance with this embodiment, when the partition mode (PartMode) is NxN partition (PART_NxN), and when the PartIdx of the prediction block being processed are 1, 2, or 3, it happens that the adjacent prediction block N is contained in a coding block identical to a coding block containing a prediction block being an output object.

On the other hand, in the case where the adjacent prediction block N is not contained in a coding block identical to the coding block containing the prediction block being the output object (Yes in step S1103), the prediction block N adjacent to the prediction block being the encoding object or decoding, and in the case when the corresponding prediction blocks N can be used, information for encoding the pre-block is output from the encoding information storage memory 115 or from the encoding information storage memory 210 interrogations N (step S1104).

If the adjacent prediction block N cannot be used (No in step S1105) or the prediction mode PredMode of the prediction block N is intra-frame prediction (MODE_INTRA) (Yes in step S1106), then the value of the availableFlagN flag of the merge candidate N is set to 0 (step S1107) , the values of both motion vectors mvL0N and mvL1N of the merge candidate N are set to (0, 0) (step S1108), and the flags of both predFlagL0N and PredFlagL1N of the merge candidate N are set to 0 (step S1109). The case where the adjacent prediction block N cannot be used corresponds, for example, to the case when the adjacent prediction block N is located on the outside of the layer being encoded or decoded, as well as to the case when the encoding or decoding process has not been completed, because, for example, block N is delayed in order of execution of the encoding or decoding process.

On the other hand, in the case where the adjacent prediction block N is on the outside of the encoding block identical to the encoding block containing the prediction block being outputted (Yes in step S1104), the adjacent prediction block N can be used (Yes in step S1105), and in the case where the prediction mode PredMode of the prediction block N is not intra prediction (MODE_INTRA) (Yes in step S1106), then the inter prediction information of the prediction block N is used as the inter prediction information of the cand merge date N. The value of the availableFlagN flag of the merge candidate N is set to 1 (step S1110), the values of the motion vectors mvL0N and mvL1N of the merge candidate N are set to the identical values of the motion vectors mvL0N [xN] [yN] and mvL1N [xN] [yN] of the corresponding prediction block N (step S1111), the values of the reference indices refIdxL0N and refIdxL1N of the merger candidate N are set to the identical values of the reference indices refIdxL0 [xN] [yN] and refIdxL1 [xN] [yN] of the corresponding prediction block N (step S1112), and the flags merge candidate predFlagL0N and predFlagL1N are set as predFlagL0 [xN] [yN] and predFlagL1 [xN] [yN] flags N (step S1113) tvetstvuyuschego prediction block. Here, xN and yN are indices indicating the position of the upper left pixel in the prediction block N within the frame.

The above processes in steps S1102 to S1113 are repeated for N = A, B, C, D and E, respectively (step S1101 - step S1114).

Next, a detailed explanation will be given of a method for deriving a reference index of a time merge candidate in step S202 in FIG. 18. The corresponding reference indices in L0 and L1 of the candidate for time merger are derived.

According to the present embodiment, the reference index of the time merge candidate is derived using the reference index of the spatial merge candidate, that is, the reference index used in the prediction block adjacent to the prediction block being encoded or decoded. This is determined by the fact that in the case where a time merge candidate is selected, the reference index of the prediction block being the object of encoding or decoding has a high correlation with the reference index of the prediction block adjacent to the prediction block being the object of encoding or decoding, which will be the candidate on spatial fusion. In particular, in accordance with the present embodiment, only the reference index of the prediction block A adjacent to the left side of the prediction block being the output object or the prediction block B adjacent to its upper side is used, with the exception of the sixth embodiment and the seventh embodiment, which will be described later. This is determined by the fact that the prediction blocks A and B adjacent to the sides of the prediction block that is the object of encoding or decoding, of all the adjacent blocks A, B, C, D and E, which are also candidates for spatial fusion, have a higher correlation, than the prediction blocks C, D and E, adjacent only to the vertices. By restricting prediction blocks using only prediction blocks A and B and without using prediction blocks C, D, and E having a relatively low correlation, an effect of improving coding efficiency by outputting a reference index of a candidate for merging in time can be obtained, and the computation volume and frequency can be reduced. memory accesses associated with the process of deriving a reference index of a candidate for a time merge.

The first sample option

In the following, some exemplary embodiments will explain the present embodiment of the invention. First, an explanation will be given below of a first exemplary embodiment of the present invention. In FIG. 20 shows adjoining blocks that are referenced in the derivation process of reference indices of merge candidates in time, in accordance with a first exemplary embodiment of the present embodiment. In the first exemplary embodiment of the present embodiment, in accordance with the partition mode (PartMode), a switch is made to which of the prediction blocks is used: a prediction block adjacent to the left side of the prediction block that is the output object, or a prediction block adjacent to its upper side. They are addressed by a prediction block adjacent to the coding block from the outside. In the case where the partition mode (PartMode) is a 2Nx2N partition (PART_2Nx2N), as shown in FIG. 20 (a), a reference is made to the prediction block A0 adjacent to the left side of the prediction block being the output object, and the reference index in LX of the time merge candidate is assigned the value of the reference index in LX of the prediction block A0.

In the case where the separation mode (PartMode) is 2NxN separation (PART_2Nx2N), 2NxnU separation (PART_2NxnU) or 2NxnD separation (PART_2NxnD), when the encoding unit that is the processing object is divided into two prediction blocks arranged vertically, as shown in FIG. 20 (b), FIG. 20 (c) and FIG. 20 (d), reference is made to the prediction blocks adjacent to the left sides of the respective prediction blocks being output objects, and the corresponding reference indices in the LX time merge candidates are assigned the values of the reference indices in the LX prediction blocks adjacent to the left side of the corresponding prediction blocks being output objects. In the case of the prediction block being the output object whose partition index PartIdx is 0, a prediction block A0 adjacent to the left is accessed and the reference index in LX of the time merge candidate is assigned the value of the reference index in LX of the prediction block A0. In the case of the prediction block that is the output object, whose partition index PartIdx is 1, the prediction block A1 is adjoined to the left and the reference index in LX of the time merge candidate is assigned the value of the reference index in LX of the prediction block A1. Since both the prediction blocks A0 and A1 that are being accessed are located on the outside of the encoding block, the reference indices of the candidates for time merging of the two prediction blocks, the partition index of which PartIdx is 0 and 1, respectively, can be respectively output in parallel.

In the case where the partition mode (PartMode) is an Nx2N partition (PART_Nx2N), nLx2N partition (PART_nLx2N) or nRx2N partition (PART_nRx2N), when the encoding unit that is the processing object is divided into two prediction blocks arranged horizontally, as shown in FIG. 20 (e), FIG. 20 (f) and FIG. 20 (g), reference is made to the prediction blocks adjacent to the upper side of the prediction block being the output object, and the corresponding reference indices in the LX time merge candidates are assigned reference index values in the LX prediction blocks adjacent to the upper side of the corresponding prediction blocks, being output objects. In the case of the prediction block being the output object whose partition index PartIdx is 0, the prediction block B0 is adjoined from above and the reference index in LX of the time merge candidate is assigned the value of the reference index in LX of the prediction blocks B0 and / or B1. In the case of the prediction block that is the output object, whose partition index PartIdx is 1, the prediction block B1 adjacent to the top is referred to and the reference index in LX of the time merge candidate is assigned the value of the reference index in LX of the prediction block B1. Since both the prediction blocks B0 and B1 that are being accessed are located on the outside of the encoding block, the reference indices of the candidates for the time merger of the two prediction blocks, whose partition index PartIdx is 0 and 1, respectively, can be respectively output in parallel.

However, in the case where adjoining prediction blocks A and B do not perform LX prediction, the reference index in LX of the time merge candidate is assigned a default value of 0. The reason why the default value of the reference index in LX of the time merge candidate is set to 0 in the case where adjoining prediction blocks A and B do not perform LX prediction, it is that a reference frame corresponding to a reference index value of 0 is most likely to be selected in inter-frame prediction. However, the scope of the present invention is not limited to this example. The default value of the reference index may be assigned a value other than 0 (for example, 1, 2, etc.), or a syntax element may be generated in the bitstream at the sequence level, at the frame level or at the layer level The default is a reference index, so this syntax element can be passed and selected during encoding.

In FIG. 21 is a flowchart illustrating a process for outputting reference indices of time merge candidates in step S202 of FIG. 18, in accordance with a first exemplary embodiment of the present embodiment. First, in the case where the partition mode (PartMode) is not an Nx2N partition (PART_Nx2N), nLx2N partition (PART_nLx2N) or nRx2N partition (PART_nRx2N) (No in step S2101), that is, in the case of a 2Nx2N partition (PART_2Nx2N) , 2NxN partitions (PART_2NxN), 2NxnU partitions (PART_2NxnU), 2NxnD (PART_2NxnD) partitions, information for encoding the prediction block A adjacent to the left is output from the encoding information storage 115 or 210 (step S2111).

The subsequent processes from step S2113 to step S2115 are carried out respectively for L0 and L1 (step S2112 - step S2116). If the reference index is output in L0 of the candidate for a time merger, LX is specified as L0, and in the case of the reference index in L1 is a candidate for time merge, LX is specified as L1. However, in the case where the slice_type layer type is a P layer, the inter prediction mode contains only L0 prediction (Pred_L0) and contains neither L1 prediction (Pred_L1) nor bi-prediction (Pred_BI). Therefore, the process related to L1 may be omitted.

In the case where the predFlagLX [xA] [yA] flag indicating whether or not to conduct the LX prediction of prediction block A is not 0 (Yes in step S2113), the reference index refIdxLXCo1 in the time merge candidate LX is assigned a value identical to the value of the reference index refIdxLX [xA] [yA] in the LX of the prediction block A (step S2114). Here, xA and yA are indices indicating the position of the upper left pixel in prediction block A inside the frame.

According to the present embodiment, in the prediction block N (N = A, B) in the case where the prediction block N is on the outside of the layer being encoded or decoded, and cannot be used in the case when the prediction block N was not encoded, since the prediction block N is subsequent to the prediction block being the object of encoding or decoding, in the order of encoding or decoding, so that the prediction block N cannot be used, or in the case when m prediction PredMode is intra-frame prediction (MODE_INTRA), both flags, predFlagL0 [xN] [yN], indicating whether to use or not using L-prediction, and predFlagL1 [xN] [yN], indicating whether to use or not to use L1 prediction are 0. Here, xN and yN are indices indicating the position of the upper left pixel in the prediction block N inside the frame. In the case where the prediction mode PredMode of the prediction block N is inter prediction (MODE_INTER) and the inter prediction mode is L0 prediction (Pred_L0), the predFlagL0 flag [xN] [yN] indicating whether to use or not use the L0 prediction of the prediction block N is 1, and the predFlagL1 [xN] [yN] flag indicating whether to use or not use the L1 prediction of the prediction block N is 0. In the case where the inter-frame prediction mode of the prediction block N is L1 prediction (Pred_L1) , flag predFlagL0 [xN] [yN] indicating to use or not to use the L0 prediction of the prediction block N is 0, and the flag predFlagL1 [xN] [yN] indicating whether to use or not to use the L1 prediction of the prediction block N is 1. In the case where the block prediction mode is Prediction N is bi-prediction (Pred_BI), a flag predFlagL0 [xN] [yN] indicating whether to use or not use the L0 prediction of the prediction block N, and a flag predFlagL1 [xN] [yN] indicating whether to use do not use L1 prediction of the prediction block N, both are 1.

In the case where the predFlagLX [xA] [yA] flag indicating whether to conduct or not to conduct LX prediction of prediction block A is 0 (No in step S2113), the reference index refIdxLXCo1 in the time merge candidate LX is assigned a value of the default is 0 (step S2115).

The processes from step S2113 to step S2115 are performed for L0 and L1, respectively (step S2112 to step S2116), and the reference index derivation process is completed.

On the other hand, in the case where the partition mode (PartMode) is an Nx2N partition (PART_Nx2N), nLx2N partition (PART_nLx2N) or nRx2N partition (PART_nRx2N) (Yes in step S2101), then the encoding information storage memory 115 or 210 information is output for encoding the prediction block B adjacent to the prediction block being the output object from above (step S2117).

The subsequent processes from step S2119 to step S2121 are performed for L0 and L1, respectively (step S2118 - step S2122). If the reference index is output in L0 of the candidate for a time merger, LX is specified as L0, and in the case of the reference index in L1 is a candidate for time merge, LX is specified as L1. However, in the case where the slice_type layer type is a P layer, the inter prediction mode contains only L0 prediction (Pred_L0) and contains neither L1 prediction (Pred_L1) nor bi-prediction (Pred_BI). Therefore, the process related to L1 may be omitted.

In the case where the predFlagLX flag [xB] [yB] indicating whether or not to conduct the LX prediction of prediction block B is not 0 (Yes in step S2119), the reference index refIdxLXCo1 in the time merge candidate LX is assigned a value identical to the value of the reference index refIdxLX [xB] [yV] in the LX of the prediction block B (step S2120). Here, xB and yB are indices indicating the position of the upper left pixel in the prediction block B within the frame.

In the case where the predFlagLX flag [xB] [yB], indicating whether or not to conduct the LX prediction of the prediction block B, is 0 (No in step S2119), the reference index refIdxLXCo1 in the time merge candidate LX is assigned a value of the default is 0 (step S2121).

The processes from step S2119 to step S2121 are performed for L0 and L1, respectively (step S2118 to step S2122), and the reference index derivation process is completed.

The second sample option

Next, in the following, an explanation will be given of a second exemplary embodiment of the present invention. In FIG. 22 shows adjoining blocks that are referenced in the derivation process of the reference indices of the time merge candidates in accordance with a second exemplary embodiment of the present embodiment. In the second exemplary embodiment of the present embodiment, in accordance with the partition mode (PartMode) of the prediction block and the partition index PartIdx of the prediction block, one switches to which of the prediction blocks is used: a prediction block adjacent to the left side of the prediction block being the output object, or a block predictions adjacent to its upper side. They are addressed by a prediction block adjacent to the coding block from the outside. In the case where the partition mode (PartMode) is a 2Nx2N partition (PART_2Nx2N), as shown in FIG. 22 (a), a reference is made to the prediction block A0 adjacent to the left of the prediction block being the output object and the reference index in LX of the time merge candidate is assigned the value of the reference index in LX of the prediction block A0.

In the case where the separation mode (PartMode) is 2NxN separation (PART_2Nx2N), 2NxnU separation (PART_2NxnU) or 2NxnD separation (PART_2NxnD), when the encoding unit that is the processing object is divided into two prediction blocks arranged vertically, as shown in FIG. 22 (b), FIG. 22 (c) and FIG. 22 (d), reference is made to the prediction blocks adjacent to the left sides of the corresponding prediction blocks that are the output objects, and the corresponding reference indices in the LX time merge candidates are assigned the values of the reference indices in the LX prediction blocks adjacent to the left side of the corresponding prediction blocks being output objects. In the case of the prediction block being the output object whose partition index PartIdx is 0, a prediction block A0 adjacent to the left is accessed and the reference index in LX of the time merge candidate is assigned the value of the reference index in LX of the prediction block A0. In the case of the prediction block that is the output object, whose partition index PartIdx is 1, the prediction block A1 is adjoined to the left and the reference index in LX of the time merge candidate is assigned the value of the reference index in LX of the prediction block A1. Since both the prediction blocks A0 and A1 that are being accessed are located on the outside of the encoding block, the reference indices of the candidates for time merging of the two prediction blocks, the partition index of which PartIdx is 0 and 1, respectively, can be respectively output in parallel.

In the case where the partition mode (PartMode) is an Nx2N partition (PART_Nx2N), nLx2N partition (PART_nLx2N) or nRx2N partition (PART_nRx2N), when the encoding unit that is the processing object is divided into two prediction blocks arranged horizontally, as shown in FIG. 22 (e), FIG. 22 (f) and FIG. 22 (g), reference is made to the prediction block A0 adjacent to the left of that prediction block that is the output object whose partition index PartIdx is 0, and the reference index in the LX of the merge candidate is assigned the value of the reference index in the LX of the prediction block A0. In the case of the prediction block that is the output object, whose partition index PartIdx is 1, the prediction block B1 adjacent to the top is referred to and the reference index in LX of the time merge candidate is assigned the value of the reference index in LX of the prediction block B1. Since both the prediction blocks A0 and B1 that are being accessed are located on the outside of the encoding block, the reference indices of the candidates for the time merger of the two prediction blocks, the partition index PartIdx, which are 0 and 1, respectively, can be respectively output in parallel.

However, in the case where adjoining prediction blocks A and B do not perform LX prediction, the reference index in LX of the time merge candidate is assigned a default value of 0. The reason why the default value of the reference index in LX of the time merge candidate is set to 0 in the case where adjoining prediction blocks A and B do not perform LX prediction, it is that a reference frame corresponding to a reference index value of 0 is most likely to be selected in inter-frame prediction. However, the scope of the present invention is not limited to this example. The default value of the reference index may be assigned a value other than 0 (for example, 1, 2, etc.), or a syntax element may be generated in the bitstream at the sequence level, at the frame level or at the layer level The default is a reference index, so this syntax element can be passed and selected during encoding.

In FIG. 23 is a flowchart illustrating a procedure for outputting reference indices of time merge candidates in step S202 of FIG. 18, in accordance with a second exemplary embodiment of the present embodiment. First, in the case where the partition mode (PartMode) is not an Nx2N partition (PART_Nx2N), nLx2N partition (PART_nLx2N) or nRx2N partition (PART_nRx2N) and the partition index PartIdx is not 1 (No in step S2101), (i.e., in the case when it is a 2Nx2N partition (PART_2Nx2N), 2NxN partition (PART_2NxN), 2NxnU partition (PART_2NxnU), 2NxnD partition (PART_2NxnD), or is an Nx2N partition (PART_Nx2N), nLxNN -partition (PART nRx2N) and partition index PartIdx of which is 0) from the memory for storing encoding information 115 or 210, information for encoding the block is predicted And I, adjacent to the left of the prediction block that is an object O (step S2111).

The subsequent processes from step S2113 to step S2115 are performed for L0 and L1, respectively (step S2112 - step S2116). If the reference index is output in L0 of the candidate for a time merger, LX is specified as L0, and in the case of the reference index in L1 is a candidate for time merge, LX is specified as L1. However, in the case where the slice_type layer type is a P layer, the inter prediction mode contains only L0 prediction (Pred_L0) and contains neither L1 prediction (Pred_L1) nor bi-prediction (Pred_BI). Therefore, the process related to L1 may be omitted.

In the case where the predFlagLX [xA] [yA] flag indicating whether or not to conduct LX prediction of prediction block A is 0 (Yes in step S2113), the reference index refIdxLXCo1 in the time merge candidate LX is assigned a value, identical to the value of the reference index refIdxLX [xA] [yA] in the LX of the prediction block A (step S2114). Here, xA and yA are indices indicating the position of the upper left pixel in prediction block A within the frame.

According to the present embodiment, in the prediction block N (N = A, B) in the case where the prediction block N is on the outside of the layer being encoded or decoded, and cannot be used in the case when the prediction block N was not encoded, since the prediction block N is subsequent to the prediction block being the object of encoding or decoding, in the order of encoding or decoding, so that the prediction block N cannot be used, or in the case when PredMode prediction is intra-frame prediction (MODE_INTRA), both flags, predFlagL0 [xN] [yN], indicating whether to use or not to use L0 prediction, and predFlagL1 [xN] [yN], indicating whether to use or not to use L1 prediction are 0. Here, xN and yN are indices indicating the position of the upper left pixel in the prediction block N inside the frame. In the case where the prediction mode PredMode of the prediction block N is inter prediction (MODE_INTER) and the inter prediction mode of the prediction block N is L0 prediction (Pred_L0), the predFlagL0 [xN] [yN] flag indicating whether to use or not to use L0 the prediction of the prediction block N is 1, and the flag predFlagL1 [xN] [yN] indicating whether to use or not use the L1 prediction of the prediction block N is 0. In the case where the inter-frame prediction mode of the prediction block N is L1 prediction (Pred_L1), flag predFlagL0 [xN] [yN], y indicating whether to use or not use the L0 prediction of the prediction block N is 0, and the flag predFlagL1 [xN] [yN] indicating whether to use or not use the L1 prediction of the prediction block N is 1. In the case where the inter prediction mode of the prediction block N is bi-prediction (Pred_BI), the flag predFlagL0 [xN] [yN] indicating whether to use or not use the L0 prediction of the prediction block N, and the flag predFlagL1 [xN] [yN] indicating then, use or not use L1 prediction of the prediction block N, both are one.

In the case where the predFlagLX [xA] [yA] flag indicating whether or not to conduct the LX prediction of prediction block A is 0 (No in step S2113), the reference index refIdxLXCo1 in the time merge candidate LX is assigned a value the default is 0 (step S2115).

The processes from step S2113 to step S2115 are performed for L0 and L1, respectively (step S2112 to step S2116), and the reference index derivation process is completed.

On the other hand, in the case where the partition mode (PartMode) is an Nx2N partition (PART_Nx2N), nLx2N partition (PART_nLx2N) or nRx2N partition (PART_nRx2N) and the partition index PartIdx is 1 (Yes in step S2102), then from the memory for storing encoding information 115 or 210, information is output for encoding the prediction block B adjacent to the prediction block being the output object from above (step S2117).

The subsequent processes from step S2119 to step S2121 are performed for L0 and L1, respectively (step S2118 - step S2122). If the reference index is output in L0 of the candidate for a time merger, LX is specified as L0, and in the case of the reference index in L1 is a candidate for time merge, LX is specified as L1. However, in the case where the slice_type layer type is a P layer, the inter prediction mode contains only L0 prediction (Pred_L0) and contains neither L1 prediction (Pred_L1) nor bi-prediction (Pred_BI). Therefore, the process related to L1 may be omitted.

In the case where the predFlagLX flag [xB] [yB] indicating whether or not to conduct the LX prediction of prediction block B is not 0 (Yes in step S2119), the reference index refIdxLXCo1 in the time merge candidate LX is assigned a value identical to the value of the reference index refIdxLX [xB] [yV] in the LX of the prediction block B (step S2120). Here, xB and yB are indices indicating the position of the upper left pixel in the prediction block B within the frame.

In the case where the predFlagLX [xB] [yB] flag indicating whether to conduct or not to conduct LX prediction of prediction block B is 0 (No in step S2119), the reference index refIdxLXCo1 in the LX of the merge candidate in time is assigned a value of the default is 0 (step S2121).

The processes from step S2119 to step S2121 are performed for L0 and L1, respectively (step S2118 to step S2122), and the reference index derivation process is completed.

Third exemplary option

Next, in the following, an explanation will be given of a third exemplary embodiment of the present embodiment. In FIG. 24 illustrates adjoining blocks that are referenced in the derivation process of the reference indices of the time merge candidates in accordance with a third exemplary embodiment of the present embodiment. In a third exemplary embodiment of the present embodiment, in accordance with a prediction block partition mode (PartMode) and a prediction block partition index PartIdx, a switch is made to which of the prediction blocks is used: a prediction block adjacent to the left side of the prediction block being the output object, or prediction unit adjacent to its upper side. In the case of a prediction block being an output object whose partition index PartIdx is 0, a prediction block adjacent to the long side, which has a higher correlation, is referred to. In the case of the prediction block that is the output object, whose partition index PartIdx is 1, an appeal is made to the prediction block, which is adjacent to the prediction block from its outer side. In the case where the partition mode (PartMode) is a 2Nx2N partition (PART_2Nx2N), as shown in FIG. 24 (a), a reference is made to the prediction block A0 adjacent to the left of the prediction block being the output object and the reference index in LX of the time merge candidate is assigned the value of the reference index in LX of the prediction block A0.

In the case where the partition mode (PartMode) is 2NxN partition (PART_2NxN), 2NxnU partition (PART_2NxnU) or 2NxnD partition (PART_2NxnD), when the encoding unit that is the processing object is divided into two prediction blocks arranged vertically, as shown in FIG. 24 (b), FIG. 24 (c) and FIG. 24 (d), a reference is made to the prediction block B0 adjacent to the upper side, which is the long side, of the prediction block that is the output object, the partition index of which PartIdx is 0, the reference index in LX of the merge candidate in time is assigned a reference index value in LX prediction block B0. In the case of the prediction block that is the output object, whose partition index PartIdx is 1, the prediction block A1 is adjoined to the left side and is located on the outside of the encoding block, and the reference index in LX of the time merge candidate is assigned the value of the reference index in LX prediction block A1. Since both the prediction blocks B0 and A1 that are being accessed are located on the outside of the encoding block, the reference indices of the candidates for the time merger of the two prediction blocks, the partition index of which PartIdx is 0 and 1, respectively, can be respectively output in parallel.

In the case where the partition mode (PartMode) is an Nx2N partition (PART_Nx2N), nLx2N partition (PART_nLx2N) or nRx2N partition (PART_nRx2N), when the encoding unit that is the processing object is divided into two prediction blocks arranged horizontally, as shown in FIG. 24 (e), FIG. 24 (f) and FIG. 24 (g), a prediction block A0 adjacent to the left side, which is the long side, is referenced of that prediction block that is the output object, whose partition index PartIdx is 0, the reference index in LX of the time merge candidate is assigned a reference index value in LX prediction block A0. In the case of the prediction block that is the output object, whose partition index PartIdx is 1, the prediction block B1 adjacent to the upper side and located on the outside of the coding block is accessed, and the reference index in LX of the time merge candidate is assigned the reference index value in LX prediction block B1. Since both the prediction blocks A0 and B1 that are being accessed are located on the outside of the encoding block, the reference indices of the candidates for the time merger of the two prediction blocks, whose partition indexes PartIdx are 0 and 1, respectively, can be displayed in parallel, respectively.

However, in the case where adjoining prediction blocks A and B do not perform LX prediction, the reference index in the LX of the time merge candidate is assigned a default value of 0. The reason why the default value of the reference index in the LX of the time merge candidate is assigned a value equal to 0 in the case when adjoining prediction blocks A and B do not perform LX prediction, it is that the reference frame corresponding to the value of the reference index equal to 0 has the highest probability of being selected in the inter-frame prediction Azanias. However, the scope of the present invention is not limited to this example. The default value of the reference index may be assigned a value other than 0 (for example, 1, 2, etc.), or a syntax element may be generated in the bitstream at the sequence level, at the frame level or at the layer level The default is a reference index, so this syntax element can be passed and selected during encoding.

In FIG. 25 is a flowchart illustrating a process for outputting reference indices of time merge candidates in step S202 of FIG. 18, in accordance with a third exemplary embodiment of the present embodiment. First, in the case where the partition mode (PartMode) is 2NxN partition (PART_2NxN), 2NxnU partition (PART_2NxnU), 2NxnD partition (PART_2NxnD) and the PartIdx partition index is not 0, or in the case where the partition mode is Nx2N partition (PART_Nx2N), nLx2N partition (PART_nLx2N) or nRx2N partition (PART_nRx2N) and PartIdx partition index is not 1 (No in step S2103), in other words, in the case where the partition mode is 2Nx2N partition (PART_2Nx2N), in the case when the partition mode is 2NxN partition (PART_2NxN), 2NxnU partition (PART_2NxnU) or 2NxnD partition (PART_2NxnD) and partition index PartIdx is 0, or when the split mode is Nx2N partition (PART_Nx2N), nLx2N partition (PART_nLx2N) or nRx2N partition (PART_nRx2N) and PartIdx partition index is 0, information is stored from the encoding information storage 115 or 210 for encoding a prediction block A adjacent to the left of the prediction block that is the output object (step S2111).

The subsequent processes from step S2113 to step S2115 are performed for L0 and L1, respectively (step S2112 - step S2116). If the reference index is output in L0 of the candidate for a time merger, LX is specified as L0, and in the case of the reference index in L1 is a candidate for time merge, LX is specified as L1. However, in the case where the slice_type layer type is a P layer, the inter prediction mode contains only L0 prediction (Pred_L0) and contains neither L1 prediction (Pred_L1) nor bi-prediction (Pred_BI). Therefore, the process related to L1 may be omitted.

In the case where the predFlagLX [xA] [yA] flag indicating whether or not to conduct the LX prediction of prediction block A is not 0 (Yes in step S2113), the reference index refIdxLXCo1 in the time merge candidate LX is assigned a value identical to the value of the reference index refIdxLX [xA] [yA] in the LX of the prediction block A (step S2114). Here, xA and yA are indices indicating the position of the upper left pixel in prediction block A within the frame.

According to the present embodiment, in the prediction block N (N = A, B) in the case where the prediction block N is on the outside of the layer being encoded or decoded, and cannot be used in the case when the prediction block N was not encoded, since the prediction block N is subsequent to the prediction block being the object of encoding or decoding, in the order of encoding or decoding, so that the prediction block N cannot be used, or in the case when m prediction PredMode is an intra prediction (MODE_INTRA), both flags, predFlagL0 [xN] [yN], indicating whether to use or not using L0 prediction, prediction block N and predFlagL1 [xN] [yN], indicating whether to use or not use L1 prediction, the prediction block N is 0. Here, xN and yN are indices indicating the position of the upper left pixel in the prediction block N inside the frame. In the case where the prediction mode PredMode of the prediction block N is inter prediction (MODE_INTER) and the inter prediction mode is L0 prediction (Pred_L0), the predFlagL0 flag [xN] [yN] indicating whether to use or not use the L0 prediction of the prediction block N is 1, and the predFlagL1 [xN] [yN] flag indicating whether to use or not use the L1 prediction of the prediction block N is 0. In the case where the inter-frame prediction mode of the prediction block N is L1 prediction (Pred_L1), flag predFlagL0 [xN] [yN] indicating Use or not use the L0 prediction of the prediction block N, is 0, and the flag predFlagL1 [xN] [yN], indicating whether to use or not use the L1 prediction of the prediction block N, is 1. In the case when the block prediction mode is Prediction N is bi-prediction (Pred_BI), a flag predFlagL0 [xN] [yN] indicating whether to use or not use the L0 prediction of the prediction block N, and a flag predFlagL1 [xN] [yN] indicating whether to use do not use L1 prediction of the prediction block N, both are 1.

In the case where the predFlagLX [xA] [yA] flag indicating whether to conduct or not to conduct LX prediction of prediction block A is 0 (No in step S2113), the reference index refIdxLXCo1 in the time merge candidate LX is assigned a value of the default is 0 (step S2115).

The processes from step S2113 to step S2115 are performed for L0 and L1, respectively (step S2112 to step S2116), and the reference index derivation process is completed.

On the other hand, in the case where the partition mode (PartMode) is an Nx2N partition (PART_Nx2N), nLx2N partition (PART_nLx2N) or nRx2N partition (PART_nRx2N) and the partition index PartIdx is 1 (Yes in step S2102), then from the memory for storing encoding information 115 or 210, information is output for encoding the prediction block B adjacent to the prediction block being the output object from above (step S2117).

The subsequent processes from step S2119 to step S2121 are performed for L0 and L1, respectively (step S2118 - S2122). If the reference index is output in L0 of candidates for a time merger, LX is specified as L0, and in the case of a reference index in L1 is candidates for a time merger, LX is specified as L1. However, in the case where the slice_type layer type is a P layer, the inter prediction mode contains only the L0 prediction (Pred_L0) and contains neither the L1 prediction (Pred_L1) nor the bi prediction (Pred_BI). Therefore, the process related to L1 may be omitted.

In the case where the predFlagLX [xB] [yB] flag indicating whether or not to conduct the LX prediction of prediction block B is not 0 (Yes in step S2119), the reference index refIdxLXCo1 in the time merge candidate LX is assigned a value identical to the value of the reference index refIdxLX [xB] [yB] in the LX of the prediction block B (step S2120). Here, xB and yB are indices indicating the position of the upper left pixel in the prediction block B within the frame.

In the case where the predFlagLX [xB] [yB] flag indicating whether to conduct or not to conduct LX prediction of prediction block B is 0 (No in step S2119), the reference index refIdxLXCo1 in the LX of the merge candidate in time is assigned a value of the default is 0 (step S2121).

The processes from step S2119 to step S2121 are performed for L0 and L1, respectively (step S2118 to step S2122), and the reference index derivation process is completed.

Fourth Example

Next, in the following, an explanation will be given of a fourth exemplary embodiment of the present invention. In FIG. 26 shows adjoining blocks that are referenced in the derivation process of the reference indices of the time merge candidates in accordance with a fourth exemplary embodiment of the present embodiment. In the fourth exemplary embodiment of the present embodiment, in accordance with the partitioning mode (PartMode) of the encoding unit and the partitioning index PartIdx of the prediction unit, switching is made whether or not to address the prediction unit adjacent to the left side of the prediction unit that is the output object. In the case when the prediction block adjacent to the left side is located on the outside of the encoding block, the prediction block is accessed, and in the case when the prediction block adjacent to the left side is inside the encoding block, the prediction block is not called and the reference index is set to the default value. In the case where the partition mode (PartMode) is a 2Nx2N partition (PART_2Nx2N), as shown in FIG. 26 (a), a reference is made to the prediction block A0 adjacent to the left of the prediction block being the output object and the reference index in LX of the time merge candidate is assigned the value of the reference index in LX of the prediction block A0.

In the case where the partition mode (PartMode) is 2NxN partition (PART_2NxN), 2NxnU partition (PART_2NxnU) or 2NxnD partition (PART_2NxnD), when the encoding unit that is the processing object is divided into two prediction blocks arranged vertically, as shown in FIG. 26 (b), FIG. 26 (c) and FIG. 26 (d), a reference is made to the prediction block A0 adjacent to the left of that prediction block that is the output object whose partition index PartIdx is 0, and the reference index in the LX of the merge candidate is assigned the value of the reference index in the LX of the prediction block A0. In the case of the prediction block that is the output object, whose partition index PartIdx is 1, the prediction block A1 is adjoined to the left and the reference index in LX of the time merge candidate is assigned the value of the reference index in LX of the prediction block A1. Since both the prediction blocks A0 and A1 that are being accessed are located on the outside of the coding block, the reference indices of the candidates for the time merger of the two prediction blocks, whose partition index PartIdx is 0 and 1, respectively, can be respectively output in parallel.

In the case where the partition mode (PartMode) is an Nx2N partition (PART_Nx2N), nLx2N partition (PART_nLx2N) or nRx2N partition (PART_nRx2N), when the encoding unit that is the processing object is divided into two prediction blocks arranged horizontally, as shown in FIG. 26 (e), FIG. 26 (f) and FIG. 26 (g), reference is made to the prediction block A0 adjacent to the left of that prediction block that is the output object whose partition index PartIdx is 0, and the reference index in the LX of the merge candidate is assigned the value of the reference index in the LX of the prediction block A0. In the case of the prediction block that is the output object, whose partition index PartIdx is 1, no reference is made to the adjoining prediction block, and the reference index in the LX of the merge candidate is assigned a default value of 0. Because the prediction block A0 to be referenced is located on the outside of the coding block, then the reference indices of the candidates for time merging of two prediction blocks, the partition index of which PartIdx is respectively 0 and 1, can correspond to but withdrawn in parallel.

However, in the case where adjoining prediction block A does not perform LX prediction, the reference index in LX of the time merge candidate is assigned a default value of 0. The reason why the default value of the reference index in LX of the time merge candidate is set to 0 in the case when adjoining prediction blocks A and B do not perform LX prediction, it is that a reference frame corresponding to a reference index value of 0 has the highest probability of being selected in the inter-frame predicted ui. However, the scope of the present invention is not limited to this example. The default value of the reference index may be assigned a value other than 0 (for example, 1, 2, etc.), or a syntax element may be generated in the bitstream at the sequence level, at the frame level or at the layer level The default is a reference index, so this syntax element can be passed and selected during encoding.

In FIG. 27 is a flowchart illustrating a process of outputting reference indices of time merge candidates in step S202 of FIG. 18, in accordance with a fourth exemplary embodiment of the present embodiment. First, in the case where the partitioning mode (PartMode) is not an Nx2N partition (PART_Nx2N), nLx2N partition (PART_nLx2N) or nRx2N partition (PART_nRx2N) and the partition index PartIdx is not 1 (No in step S2102), (i.e., in case of 2Nx2N partition (PART_2Nx2N), 2NxN partition (PART_2NxN), 2NxnU partition (PART_2NxnU), 2NxnD partition (PART_2NxnD) or nRx2N partition (PART_nRx2N) and the storage partition index PartIdx is 0), or 210, information is output for encoding the prediction block A adjacent to the left of the prediction block being the output object (step S2111) .

The subsequent processes from step S2113 to step S2115 are performed for L0 and L1, respectively (step S2112 - step S2116). If the reference index is output in L0 of the candidate for a time merger, LX is specified as L0, and in the case of the reference index in L1 is a candidate for time merge, LX is specified as L1. However, in the case where the slice_type layer type is a P layer, the inter prediction mode contains only the L0 prediction (Pred_L0) and contains neither the L1 prediction (Pred_L1) nor the bi prediction (Pred_BI). Therefore, the process related to L1 may be omitted.

In the case where the predFlagLX [xA] [yA] flag indicating whether or not to conduct the LX prediction of prediction block A is not 0 (Yes in step S2113), the reference index refIdxLXCo1 in the time merge candidate LX is assigned a value identical to the value of the reference index refIdxLX [xA] [yA] in the LX of the prediction block A (step S2114). Here, xA and yA are indices indicating the position of the upper left pixel in prediction block A within the frame.

According to the present embodiment, in the prediction block N (N = A, B) in the case where the prediction block N is on the outside of the layer being encoded or decoded, and cannot be used in the case when the prediction block N was not encoded, since the prediction block N is subsequent to the prediction block being the object of encoding or decoding, in the order of encoding or decoding, so that the prediction block N cannot be used, or in the case when m prediction PredMode is an intra-frame prediction (MODE_INTRA), both flags, predFlagL0 [xN] [yN], indicating whether to use or not using L0 prediction, and predFlagL1 [xN] [yN], indicating whether to use or not using L1 prediction are 0. Here, xN and yN are indices indicating the position of the upper left pixel in the prediction block N inside the frame. In the case where the prediction mode PredMode of the prediction block N is inter prediction (MODE_INTER) and the inter prediction mode is L0 prediction (Pred_L0), the predFlagL0 flag [xN] [yN] indicating whether to use or not use the L0 prediction of the prediction block N is 1, and the predFlagL1 [xN] [yN] flag indicating whether to use or not use the L1 prediction of the prediction block N is 0. In the case where the inter-frame prediction mode of the prediction block N is L1 prediction (Pred_L1) , flag predFlagL0 [xN] [yN] indicating to use or not to use the L0 prediction of the prediction block N is 0, and the flag predFlagL1 [xN] [yN] indicating whether to use or not to use the L1 prediction of the prediction block N is 1. In the case where the block prediction mode is Prediction N is bi-prediction (Pred_BI), a flag predFlagL0 [xN] [yN] indicating whether to use or not use the L0 prediction of the prediction block N, and a flag predFlagL1 [xN] [yN] indicating whether to use do not use L1 prediction of the prediction block N, both are 1.

In the case where the predFlagLX [xA] [yA] flag indicating whether to conduct or not to conduct LX prediction of prediction block A is 0 (No in step S2113), the reference index refIdxLXCo1 in the time merge candidate LX is assigned a value of the default is 0 (step S2115).

The processes from step S2113 to step S2115 are performed for L0 and L1, respectively (step S2112 to step S2116), and the reference index derivation process is completed.

On the other hand, in the case where the partition mode (PartMode) is Nx2N partition (PART_Nx2N), nLx2N partition (PART_nLx2N) or nRx2N partition (PART_nRx2N) and PartIdx partition index is 1 (Yes in step S2102), the subsequent process of step S2102) S2121 is performed for each L0 and L1 (step S2118 - S2122). In the case of outputting the reference index in L0 of the candidate for time merger, LX is specified as L0, and in the case of the output of the reference index in L1 of the candidate for time merge, LX is set as L1. However, in the case where the slice_type layer type is a P layer, the inter prediction mode contains only L0 prediction (Pred_L0) and contains neither L1 prediction (Pred_L1) nor bi-prediction (Pred_BI). Therefore, the process related to L1 may be omitted.

The reference index refIdxLXCo1 in LX of the time merge candidate is assigned a default value of 0 (step S2121).

The processes from step S2119 to step S2121 are performed for L0 and L1, respectively (step S2118 to step S2122), and the reference index derivation process is completed.

Fifth Example

Next, in the following, an explanation will be given of a fifth exemplary embodiment of the present invention. In FIG. 28 shows adjoining blocks that are referenced in the derivation process of reference indices of merge candidates in time in accordance with a fifth exemplary embodiment of the present embodiment. In the fifth exemplary embodiment of the present embodiment, in accordance with the partition mode (PartMode), a switch is made whether or not to access the prediction block adjacent to the left side of the prediction block that is the output object. An appeal is made to the prediction block adjacent to the outside of the coding block. In the case when the prediction unit adjacent to the left side is located on the outside of the encoding unit, the encoding unit refers to the prediction unit, and in the case when the prediction unit adjacent to the left side is located inside the encoding unit, the encoding unit does not access to the prediction block, and the reference index is assigned a default value. In the case where the partition mode (PartMode) is a 2Nx2N partition (PART_2Nx2N), as shown in FIG. 28 (a), a reference is made to the prediction block A0 adjacent to the left of the prediction block being the output object and the reference index in LX of the time merge candidate is assigned the value of the reference index in LX of the prediction block A0.

In the case where the partition mode (PartMode) is 2NxN partition (PART_2NxN), 2NxnU partition (PART_2NxnU) and 2NxnD partition (PART_2NxnD), when the encoding unit that is the processing object is divided into two prediction blocks arranged vertically, as shown in FIG. 28 (b), FIG. 28 (c) and FIG. 28 (d), a reference is made to the prediction block A0 adjacent to the left of that prediction block that is the output object whose partition index PartIdx is 0, and the reference index in the LX of the merge candidate is assigned the value of the reference index in the LX of the prediction block A0. In the case of the prediction block that is the output object, whose partition index PartIdx is 1, the prediction block A1 is adjoined to the left and the reference index in LX of the time merge candidate is assigned the value of the reference index in LX of the prediction block A1. Since both the prediction blocks A0 and A1 that are being accessed are located on the outside of the encoding block, the reference indices of the candidates for time merging of the two prediction blocks, the partition index of which PartIdx is 0 and 1, respectively, can be respectively output in parallel.

In the case when the partition mode (PartMode) is an Nx2N partition (PART_Nx2N), nLx2N partition (PART_nLx2N) or nRx2N partition (PART_nRx2N), when the encoding unit that is the processing object is divided into two prediction blocks located horizontally in both In cases of a prediction block whose PartIdx partition index is 0 or 1, the adjoining prediction block is not referenced, and the reference index in the LX candidate for the time merge candidate is assigned a default value of 0. Since no prediction block is referenced If the adjacent to the prediction block, which is the object of processing, does not refer to the prediction block in the coding block, then the reference indices of candidates for the time merger of two prediction blocks, the partition index of which PartIdx is 0 and 1, respectively, can be respectively output in parallel.

However, in the case where adjoining prediction block A does not perform LX prediction, the reference index in LX of the time merge candidate is assigned a default value of 0. The reason why the default value of the reference index in LX of the time merge candidate is set to 0 in the case when the adjoining prediction block A does not conduct LX prediction, or in the case when the partition mode (PartMode) of the encoding block containing the prediction block that is the output object is Nx2N partition (PART_Nx2N), nLx2N-p Thousands separator (PART_nLx2N) or nRx2N-division (PART_nRx2N), it is that the reference frame corresponding to the reference index value equal to 0 has the highest probability of being selected in the interframe prediction. However, the scope of the present invention is not limited to this example. The default value of the reference index can be set to a value other than 0 (for example, 1, 2, etc.), or in the bitstream at the sequence level, at the frame level, or at the layer level, a syntax element can be formed indicating the value The default is a reference index, so this syntax element can be passed and selected during encoding.

In FIG. 29 is a flowchart illustrating a process for outputting reference indices of time merge candidates in step S202 of FIG. 18, in accordance with a fifth exemplary embodiment of the present embodiment. First, in the case where the partition mode (PartMode) is not an Nx2N partition (PART_Nx2N), nLx2N partition (PART_nLx2N) or nRx2N partition (PART_nRx2N) (No in step S2101), that is, in the case of a 2Nx2N partition (PART_2Nx2N) , 2NxN partitions (PART_2NxN), 2NxnU partitions (PART_2NxnU), 2NxnD partitions (PART_2NxnD), information for encoding the prediction block A adjacent to the left of the prediction block that is the output object is output from the encoding information storage 115 or 210 (step S2111) .

The subsequent processes from step S2113 to step S2115 are performed for L0 and L1, respectively (step S2112 - step S2116). If the reference index is output in L0 of the candidate for a time merger, LX is specified as L0, and in the case of the reference index in L1 is a candidate for time merge, LX is specified as L1. However, in the case where the slice_type layer type is a P layer, the inter prediction mode contains only L0 prediction (Pred_L0) and contains neither L1 prediction (Pred_L1) nor bi-prediction (Pred_BI). Therefore, the process related to L1 may be omitted.

In the case where the predFlagLX [xA] [yA] flag indicating whether or not to conduct the LX prediction of prediction block A is not 0 (Yes in step S2113), the reference index refIdxLXCo1 in the time merge candidate LX is assigned a value identical to the value of the reference index refIdxLX [xA] [yA] in the LX of the prediction block A (step S2114). Here, xA and yA are indices indicating the position of the upper left pixel in prediction block A within the frame.

According to the present embodiment, in the prediction block N (N = A, B) in the case where the prediction block N is on the outside of the layer being encoded or decoded, and cannot be used in the case when the prediction block N was not encoded, since the prediction block N is subsequent to the prediction block being the object of encoding or decoding, in the order of encoding or decoding, so that the prediction block N cannot be used, or in the case when m prediction PredMode is an intra-frame prediction (MODE_INTRA), both flags, predFlagL0 [xN] [yN], indicating whether to use or not using L0 prediction, and predFlagL1 [xN] [yN], indicating whether to use or not using L1 prediction are 0. Here, xN and yN are indices indicating the position of the upper left pixel in the prediction block N inside the frame. In the case where the prediction mode PredMode of the prediction block N is inter prediction (MODE_INTER) and the inter prediction mode is L0 prediction (Pred_L0), the flag predFlagL0 [xN] [yN] indicating whether to use or not use the L0 prediction of the prediction block N is 1, and the predFlagL1 [xN] [yN] flag indicating whether to use or not use the L1 prediction of the prediction block N is 0. In the case where the inter-frame prediction mode of the prediction block N is L1 prediction (Pred_L1), flag predFlagL0 [xN] [yN] indicating Use or not use the L0 prediction of the prediction block N, is 0, and the flag predFlagL1 [xN] [yN], indicating whether to use or not use the L1 prediction of the prediction block N, is 1. In the case when the block prediction mode is Prediction N is bi-prediction (Pred_BI), a flag predFlagL0 [xN] [yN] indicating whether to use or not use the L0 prediction of the prediction block N, and a flag predFlagL1 [xN] [yN] indicating whether to use or do not use L1 prediction of the prediction block N, both are 1.

In the case where the predFlagLX [xA] [yA] flag indicating whether to conduct or not to conduct LX prediction of prediction block A is 0 (No in step S2113), the reference index refIdxLXCo1 in the time merge candidate LX is assigned a value of the default is 0 (step S2115).

The processes from step S2113 to step S2115 are performed for L0 and L1, respectively (step S2112 to step S2116), and the reference index derivation process is completed.

On the other hand, in the case where the partition mode (PartMode) is Nx2N partition (PART_Nx2N), nLx2N partition (PART_nLx2N) or nRx2N partition (PART_nRx2N) (Yes in step S2101), the subsequent process of step S2121 is performed for each L0 and L1 (step S2118 - step S2122). In the case of outputting the reference index in L0 of the candidate for time merge, LX is specified as L0, and in the case of the output of the reference index in L1 of the candidate for time merger, LX is set as L1. However, in the case where the slice_type layer type is a P layer, the inter prediction mode contains only L0 prediction (Pred_L0) and contains neither L1 prediction (Pred_L1) nor bi-prediction (Pred_BI). Therefore, the process related to L1 may be omitted.

The reference index refIdxLXCo1 in LX of the time merge candidate is assigned a default value of 0 (step S2121).

The processes from step S2119 to step S2121 are performed for L0 and L1, respectively (step S2118 to step S2122), and the reference index derivation process is completed.

Sixth Example

Next, in the following, an explanation will be given of a sixth exemplary embodiment of the present invention. According to a sixth exemplary embodiment of the present embodiment, regardless of the partition mode (PartMode) of the encoding unit that contains the prediction mode being the output object (the encoding unit that is the processing object) and the value of the partition index of the PartIdx mode of the output object, referring to adjoining prediction blocks are not performed, and the reference index in LX of the time merger candidate is assigned a default value of 0. Since no prediction blocks are accessed, Adjacent to the prediction block being the object of processing, the prediction blocks inside the coding block are not accessed, therefore, candidates for time merging of two prediction blocks that are contained in the same coding block, the partition index PartIdx which is respectively 0 and 1, can be respectively output in parallel.

The reason why the default reference index value in LX of the time merge candidate is set to 0 is that the reference frame corresponding to the reference index value of 0 is most likely to be selected in inter-frame prediction. However, the scope of the present invention is not limited to this example. The default value of the reference index can be set to a value other than 0 (for example, 1, 2, etc.), or in the bitstream at the sequence level, at the frame level, or at the layer level, a syntax element can be formed indicating the value The default is a reference index, so this syntax element can be passed and selected during encoding.

In addition, in accordance with a sixth exemplary embodiment, the reference index refIdxLXCo1 in LX of the time merge candidate is assigned a default value of 0, without reference to an adjoining block. Therefore, the derivation process can be simplified compared to the first, second, third, fourth, fifth and seventh (described later) implementation examples.

In FIG. 30 is a flowchart illustrating a process for deriving reference indices of time merge candidates in step S202 of FIG. 18, in accordance with a sixth exemplary embodiment of the present embodiment.

The process of step S2115 is performed for L0 and L1, respectively (step S2112 - S2116). If the reference index in L0 of the candidate for a time merge is output, LX is specified as L0, and in the case of the reference index of the list in L1 of the candidate for time merge, LX is set as L1. However, in the case where the slice_type layer type is a P layer, the inter prediction mode contains only L0 prediction (Pred_L0) and contains neither L1 prediction (Pred_L1) nor bi-prediction (Pred_BI). Therefore, the process related to L1 may be omitted.

The reference index refIdxLXCo1 in LX of the time merge candidate is assigned a default value of 0 (step S2115).

The process of step S2115 is performed for L0 and L1, respectively (step S2112 to step S2116), and the reference index derivation process is completed.

Seventh Example

Next, in the following, an explanation of the seventh exemplary embodiment of the present embodiment will be provided. In FIG. 31 illustrates adjoining blocks that are referenced in the derivation process of reference indices of merge candidates in time, in accordance with a seventh exemplary embodiment of the present embodiment. According to a seventh exemplary embodiment of the present embodiment, regardless of the partition mode (PartMode) of the encoding unit that contains the prediction mode that is the output object (the encoding unit that is the processing object) and the partition index value of the PartIdx mode of the output object, access is made to the prediction block A adjacent to the left to the encoding block that is the processing object, as shown in FIG. 31 (a) - FIG. 31 (g), and the reference index value in the LX of the time merge candidate is assigned the value of the reference index in the LX of the prediction block A. Since the prediction block A being accessed is located on the outside of the encoding block, the reference indices of the merge candidates are time of two prediction blocks, the partition index of which PartIdx is 0 and 1, respectively, can be respectively output in parallel.

However, in the case where adjoining prediction block A does not perform LX prediction, the reference index in LX of the time merge candidate is assigned a default value of 0. The reason why the default value of the reference index in LX of the time merge candidate is set to 0 in the case where adjoining prediction block A does not produce LX prediction, it is that a reference frame corresponding to a reference index value of 0 is most likely to be selected in inter-frame prediction. However, the scope of the present invention is not limited to this example. The default value of the reference index can be set to a value other than 0 (for example, 1, 2, etc.), or in the bitstream at the sequence level, at the frame level, or at the layer level, a syntax element can be formed indicating the value The default is a reference index, so this syntax element can be passed and selected during encoding.

According to a seventh exemplary embodiment, the values of the reference indices of the time merge candidates of the respective prediction blocks within the coding block are set as common values. Therefore, it is not necessary to derive a reference index of a time merge candidate for each prediction block, so that the output process can be simplified.

In FIG. 32 is a flowchart illustrating a process for outputting reference indices of time merge candidates in step S202 of FIG. 18, in accordance with a seventh exemplary embodiment of the present embodiment. First, information for encoding the prediction block A adjacent to the left of the encoding block that is the processing object is output from the encoding information storage 115 or 210 (step S2131).

The subsequent processes from step S2133 to step S2135 are performed for L0 and L1, respectively (step S2132 - step S2136). If the reference index is output in L0 of the candidate for a time merger, LX is specified as L0, and in the case of the reference index in L1 is a candidate for time merge, LX is specified as L1. However, in the case where the slice_type layer type is a P layer, the inter prediction mode contains only L0 prediction (Pred_L0) and contains neither L1 prediction (Pred_L1) nor bi-prediction (Pred_BI). Therefore, the process related to L1 may be omitted.

In the case where the predFlagLX [xA] [уА] flag indicating whether or not to conduct LX prediction of prediction block A, which is adjacent to the left of the encoding block that is the object of processing, is not 0 (Yes in step S2133), the reference the index refIdxLXCo1 in LX of the time merge candidate is assigned a value identical to the value of the reference index refIdxLX [xA] [yA] in the LX of prediction block A (step S2134). Here, xA and yA are indices indicating the position of the upper left pixel in prediction block A, which is adjacent to the left of the encoding block that is the processing object, inside the frame.

According to the present embodiment, in the prediction block N (N = A, B) in the case where the prediction block N is on the outside of the layer being encoded or decoded, and cannot be used in the case when the prediction block N was not encoded, since the prediction block N is subsequent to the prediction block being the object of encoding or decoding, in the order of encoding or decoding, so that the prediction block N cannot be used, or in the case when m prediction PredMode is an intra-frame prediction (MODE_INTRA), both flags, predFlagL0 [xN] [yN], indicating whether to use or not using L0 prediction, and predFlagL1 [xN] [yN], indicating whether to use or not using L1 prediction are 0. Here, xN and yN are indices indicating the position of the upper left pixel in the prediction block N inside the frame. In the case where the prediction mode PredMode of the prediction block N is inter prediction (MODE_INTER) and the inter prediction mode is L0 prediction (Pred_L0), the flag predFlagL0 [xN] [yN] indicating whether to use or not to use L0 prediction the prediction block N is 1, and the predFlagL1 [xN] [yN] flag indicating whether to use or not use the L1 prediction of the prediction block N is 0. In the case where the inter-frame prediction mode of the prediction block N is L1 prediction (Pred_L1 ), the predFlagL0 [xN] [yN] flag, indicating Use or not use the L0 prediction of the prediction block N, is 0, and the flag predFlagL1 [xN] [yN], indicating whether to use or not use the L1 prediction of the prediction block N, is 1. In the case when the block prediction mode is Prediction N is bi-prediction (Pred_BI), a flag predFlagL0 [xN] [yN] indicating whether to use or not use the L0 prediction of the prediction block N, and a flag predFlagL1 [xN] [yN] indicating whether to use do not use L1 prediction of the prediction block N, both are 1.

In the case where the predFlagLX [xA] [yA] flag indicating whether or not to conduct LX prediction of prediction block A is 0 (No in step S2133), the reference index refIdxLXCo1 in the time merge candidate LX is assigned a value of the default is 0 (step S2135).

The processes from step S2133 to step S2135 are performed for L0 and L1, respectively (step S2132 to step S2136), and the reference index derivation process is completed.

Although, in accordance with the seventh exemplary embodiment, the switching occurs whether or not to apply to the prediction block adjacent to the left side of the encoding block containing the prediction block being the output object, instead of the prediction block adjacent to the left side, switching of , contact or not contact the prediction block adjacent to the upper side.

Eighth Example

Next, an explanation will be provided on the eighth exemplary embodiment of the present invention. In FIG. 43, adjoining blocks are shown that are referenced in the derivation process of reference indices of time merge candidates in accordance with an eighth exemplary embodiment of the present embodiment. According to an eighth exemplary embodiment of the present embodiment, regardless of the partition mode (PartMode) of the encoding unit, and in accordance with the partition index PartIdx of the prediction unit, switching is made to whether or not to apply to the prediction unit adjacent to the left side of the prediction unit that is the object output. In the case when the partition index PartIdx of the prediction block is 0, a prediction block adjacent to the left side is accessed, and in the case where the PartIdx partition index is a value other than 0, the adjacent prediction block is not referenced and the partition index value set by default. In the case where the partition index PartIdx of the prediction block is 0, the prediction block adjacent to the left side is always located on the outside of the encoding block in any split mode (PartMode). However, in the case where the PartIdx partition index takes a value other than 0, the prediction block adjacent to the left side may be inside the encoding block, which depends on the partition mode (PartMode). As shown in FIG. 43 (a), a reference is made to the prediction block A0 adjacent to the left of the prediction block being the output object and the reference index value in LX of the time merge candidate is assigned the reference index value in LX of the prediction block A0.

In the case where the partition mode (PartMode) is 2NxN partition (PART_2Nx2N), 2NxnU partition (PART_2NxnU) and 2NxnD partition (PART_2NxnD), when the encoding unit being the object of processing is divided into two prediction blocks located vertically or in in the case where the partition mode (PartMode) is Nx2N partition (PART_Nx2N), nLx2N partition (PART_nLx2N) or nRx2R partition (PART_nRx2N), as shown in FIG. 43 (b), 43 (c), 43 (d), 43 (e), 43 (f) and 43 (g), a prediction block A0 is accessed adjacent to the left of the prediction block that is the output object, the partition index PartIdx which is 0, and the reference index in LX of the time merge candidate is assigned the value of the reference index in LX of prediction block A0. In the case of the prediction block that is the output object, whose partition index PartIdx is 1, no reference is made to the adjoining prediction block, and the reference index in the LX of the merge candidate is assigned a default value of 0. Because the prediction block A0 to be referenced is located on the outside of the coding block, then the values of the reference indices of the candidates for time merging of two prediction blocks, the partition index of which PartIdx is 0 and 1, respectively, can be responsibly derived in parallel.

However, in the case where adjoining prediction block A does not perform LX prediction, the reference index in LX of the time merge candidate is assigned a default value of 0. The reason why the default value of the reference index in LX of the time merge candidate is set to 0 in the case when the adjoining prediction block A does not conduct LX prediction, or in the case when the partition index PartIdx of the prediction block being the output object is 1, then the reference frame corresponding to the reference value full-time index is equal to 0, it has the highest probability of being selected in the inter-frame prediction. However, the scope of the present invention is not limited to this example. The default value of the reference index can be set to a value other than 0 (for example, 1, 2, etc.), or in the bitstream at the sequence level, at the frame level, or at the layer level, a syntax element can be formed indicating the value The default is a reference index, so this syntax element can be passed and selected during encoding.

In FIG. 44 is a flowchart illustrating a process for outputting reference indices of time merge candidates in step S202 of FIG. 18, in accordance with an eighth exemplary embodiment of the present embodiment. First, in the case where the partition index PartIdx is 0 (Yes in step S2104), information for encoding the prediction block A adjacent to the left of the encoding block that is the processing object is output from the encoding information storage 115 or 210 (step S2111).

The subsequent processes from step S2113 to step S2115 are performed for L0 and L1, respectively (step S2112 - step S2116). If the reference index is output in L0 of the candidate for a time merger, LX is specified as L0, and in the case of the reference index in L1 is a candidate for time merge, LX is specified as L1. However, in the case where the slice_type layer type is a P layer, the inter prediction mode contains only L0 prediction (Pred_L0) and contains neither L1 prediction (Pred_L1) nor bi-prediction (Pred_BI). Therefore, the process related to L1 may be omitted.

In the case where the predFlagLX [xA] [yA] flag indicating whether or not to conduct the LX prediction of prediction block A is not 0 (Yes in step S2113), the reference index refIdxLXCo1 in the time merge candidate LX is assigned a value identical to the value of the reference index refIdxLX [xA] [yA] in the LX of the prediction block A (step S2114). Here, xA and yA are indices indicating the position of the upper left pixel in prediction block A within the frame.

According to the present embodiment, in the prediction block N (N = A or B) in the case where the prediction block N is on the outside of the layer being encoded or decoded, and cannot be used in the case when the prediction block N was not encoded, since the prediction block N is subsequent to the prediction block being the object of encoding or decoding, in the order of encoding or decoding, so that the prediction block N cannot be used, or in the case when p PredMode prediction mode is intra-frame prediction (MODE_INTRA), both flags predFlagL0 [xN] [yN] indicating whether to use or not use L0 prediction and predFlagL1 [xN] [yN] indicating whether to use or not use L1 prediction are 0. Here, xN and yN are indices indicating the position of the upper left pixel in the prediction block N inside the frame. In the case where the prediction mode PredMode of the prediction block N is inter prediction (MODE_INTER) and the inter prediction mode is L0 prediction (Pred_L0), the flag predFlagL0 [xN] [yN] indicating whether to use or not use the L0 prediction of the prediction block N is 1, and the predFlagL1 [xN] [yN] flag indicating whether to use or not use the L1 prediction of the prediction block N is 0. In the case where the inter-frame prediction mode of the prediction block N is L1 prediction (Pred_L1), flag predFlagL0 [xN] [yN] indicating Use or not use the L0 prediction of the prediction block N, is 0, and the flag predFlagL1 [xN] [yN], indicating whether to use or not use the L1 prediction of the prediction block N, is 1. In the case when the block prediction mode is Prediction N is bi-prediction (Pred_BI), a flag predFlagL0 [xN] [yN] indicating whether to use or not use the L0 prediction of the prediction block N, and a flag predFlagL1 [xN] [yN] indicating whether to use or do not use L1 prediction of the prediction block N, both are 1.

In the case where the predFlagLX [xA] [yA] flag indicating whether to conduct or not to conduct LX prediction of prediction block A is 0 (No in step S2113), the reference index refIdxLXCo1 in the time merge candidate LX is assigned a value of the default is 0 (step S2115).

The processes from step S2113 to step S2115 are performed for L0 and L1, respectively (step S2112 to step S2116), and the reference index derivation process is completed.

On the other hand, in the case where the partition index PartIdx is not 0 (No in step S2104), the subsequent process of step S2121 is performed for each L0 and L1 (step S2118 - step S2122). If the reference index is output in L0 of the candidate for a time merger, LX is specified as L0, and in the case of the reference index in L1 is a candidate for time merge, LX is specified as L1. However, in the case where the slice_type layer type is a P layer, the inter prediction mode contains only L0 prediction (Pred_L0) and contains neither L1 prediction (Pred_L1) nor bi-prediction (Pred_BI). Therefore, the process related to L1 may be omitted.

The reference index refIdxLXCo1 in LX of the time merge candidate is assigned a default value of 0 (step S2121).

The processes of step S2121 are performed for L0 and L1, respectively (step S2118 to step S2122), and the reference index derivation process is completed.

Although, in accordance with the eighth exemplary embodiment, the switching is performed whether or not to apply to the prediction block adjacent to the left side of the encoding block containing the prediction block being the output object, instead of the prediction block adjacent to the left side, switching , contact or not contact the prediction block adjacent to the upper side.

Although, in accordance with the present embodiment, it is assumed that the NxN partition (PART_NxN) is not defined as the partition mode (PartMode) of the encoding unit, it is also possible to determine the NxN partition (PART_NxN. In the case where the partition mode (PartMode) is NxN -partition (PART_NxN), also when deriving the reference index of the time merge candidate of the prediction block contained in the coding block that is the object of processing, by outputting the reference index without reference to the adjoining prediction block that is contained within the block identical to the encoding block included in the prediction block being the object of processing, the reference indices of the time merge candidates of the four prediction blocks, whose partition index PartIdx is 0, 1, 2, and 3, respectively, can be respectively output in parallel.

For example, in the case of the NxN separation (Part_NxN), the adjoining prediction block is not referenced and the reference index in the LX candidate for the time merger is assigned a default value of 0. Since no prediction block adjacent to the prediction block that is the object is referenced output, reference indices of candidates for the time merger of four prediction blocks, the partition index of which PartIdx is 0, 1, 2, and 3, respectively, can be respectively output in parallel.

Alternatively, the reference index of the time merge candidate may also be displayed by referring to the reference index of an adjoining block. In FIG. 33 illustrates adjoining blocks that are referenced in the process of deriving reference indices of candidates for time merging of an NxN-division division coding block (PART_NxN).

As shown in FIG. 33 (a), in the case of a prediction block being an output object whose partition index PartIdx is 0, a prediction block A0 adjacent to the left is accessed and the reference index in LX of the merge candidate is assigned the value of the reference index in LX of the prediction block A0 . In the case of the prediction block that is the output object, whose partition index PartIdx is 1, the prediction block B1 adjacent to the top is referred to and the reference index in LX of the time merge candidate is assigned the value of the reference index in LX of the prediction block B1. In the case of the prediction block being the output object whose partition index PartIdx is 2, the prediction block A2 is adjoined to the left and the reference index in LX of the time merge candidate is assigned the value of the reference index in LX of A2 prediction block. In the case of a prediction block being an output object whose partition index PartIdx is 3, no reference to the adjacent prediction block is made, and the reference index in LX of the merge candidate is assigned a default value of 0. Since the prediction blocks A0 and A2 are adjacent to the left to the prediction block, which is the object of processing, and B1, adjacent to it from above, all are located on the outside of the coding block, reference indices of candidates for time merging of four prediction blocks, index s separation PartIdx which are 0, 1, 2 and 3, respectively, may suitably be derived in parallel.

Alternatively, as shown in FIG. 33 (b), in the case of a prediction block being an output object whose partition index PartIdx is 0, a prediction block A0 adjacent to the left is accessed and the reference index in LX of the merge candidate is assigned the value of the reference index in LX of prediction block A0 . In the case of the prediction block being the output object whose partition index PartIdx is 2, the prediction block A2 is adjoined to the left and the reference index in LX of the time merge candidate is assigned the value of the reference index in LX of A2 prediction block. In the case of a prediction block being an output object whose partition index PartIdx is 1 or 3, no reference to the adjacent prediction block is made, and the reference index in LX of the merge candidate is assigned a default value of 0. Since both prediction blocks A0 and A2 , adjacent to the left of the prediction block that is the processing object, are located on the outside of the coding block, then the reference indices of candidates for the time merger of the four prediction blocks, the partition index PartIdx of which rykh is respectively 0, 1, 2 and 3, can be respectively deduced in parallel.

Alternatively, as shown in FIG. 33 (c), a reference is made to prediction block A, adjacent to the left of the encoding block being the object of processing, and the reference index in LX of the time merge candidate is assigned the value of the reference index in LX of prediction block A. Since prediction block A is adjacent to the left to block encoding, which is the object of processing, is located on the outside of the encoding block, then the values of the reference indices of candidates for the merger in time of four prediction blocks, the partition index of which PartIdx is Namely 0, 1, 2, and 3, can be respectively output in parallel.

Alternatively, as shown in FIG. 33 (d), in the case of a prediction block being an output object whose partition index PartIdx is 0, a prediction block A0 adjacent to the left is accessed and the reference index in LX of the merge candidate is assigned the value of the reference index in LX of the prediction block A0 . In the case of a prediction block that is an output object whose partition index PartIdx is other than 0 (PartIdx is 1, 2, or 3), the adjoining block is not accessed, and the reference index in the LX of the merge candidate is assigned a default value of 0. Since the prediction block A0, adjacent to the left of the prediction block that is the object of processing, is located on the outside of the coding block, the reference indices of the time merge candidates of the four prediction blocks, the partition index of which PartIdx is 0, 1, 2, and 3, respectively, can be respectively output in parallel.

Next, a detailed explanation will be given of a method for deriving a merge candidate using inter-frame prediction information of a frame of another time point of step S203 in FIG. 18. In FIG. 34 is a flowchart illustrating a procedure of a time merge candidate withdrawal process of step S203 in FIG. eighteen.

First, a colPic frame of another point in time is output using the slice_type layer type and the collocated_from_flag flag described above (step S3101).

In FIG. 35 is a flowchart illustrating a process for outputting a colPic frame of another point in time of step S3101 in FIG. 34. In the case where the slice_type layer type is B-layer and the collocated_from_10_flag flag described above is 0 (Yes in step S3201 and Yes in step S3202), RefPicList1 [0] (that is, the frame, by the reference index in the reference list Whose L1 is 0) is defined as a colPic frame of another point in time (step S3203). Otherwise, that is, in the case where the slice_type layer type is B-layer and the collocated_from_10_flag flag described above is 1 (Yes in step S3201 and No in step S3202), or in the case when the slice_type layer type is P- a layer (No in step S3201 and Yes in step S3204), RefPicList0 [0] (that is, a frame whose reference index in the reference list L0 is 0) is defined as a colPic frame of another point in time (step S3205).

Then, returning to the flowchart of FIG. 34, a colPU prediction block of another point in time is output, and encoding information is output (step S3102).

In FIG. 36 is a flowchart illustrating a process of outputting a colPU prediction block of a colPic frame of another point in time of step S3102 in FIG. 34.

First, in the colPic frame of another point in time, a prediction block located at the bottom right (from the outside) at a position identical to the position of the prediction block being the object of processing is used as the colPU prediction block of another point in time (step S3301). This prediction block corresponds to the prediction block T0 in FIG. 9.

Then, coding information of the colPU prediction unit of another point in time is output (step S3302). In the case where the PredMode of the colPU prediction unit of another time cannot be used, or in the case where the PredMode prediction of the colPU prediction unit of another time is intra-frame prediction (MODE_INTRA) (Yes in step S3303 and Yes in step S3304), the prediction block inside the colPic frame of another point in time, located at the top left in the middle of the position identical to the position of the prediction block being the object of processing, is used as the prediction block colPU of another point in time (step S3305). This prediction block corresponds to the prediction block T1 in FIG. 9.

Then, returning to the flowchart of FIG. 34, the prediction of the motion vector mvL1Co1 in L0 is output from the prediction block in another frame at a position identical to the position of the prediction block being the object of encoding or decoding, the availableFlagL0Co1 flag is displayed indicating the validity or inadmissibility of the Co1 time merge candidate (step S3103), and the prediction of the motion vector mvL1Co1 in L1 and the flag availableFlagL1Co1 are displayed, indicating the admissibility or inadmissibility of the candidate for time merger Co1. In addition, in the case when the flag availableFlagL0Co1 or the flag availableFlagL1Co1 is 1, the flag availableFlagCo1, indicating whether the candidate for the merger in time Co1 is valid or not, is set to 1.

In FIG. 37 is a flowchart illustrating a process for outputting inter-prediction information of a time merge candidate in step S3103 and step S3104 in FIG. 34. For L0 or L1, a list of objects for outputting candidates for a time merge is defined as LX, and a prediction using the LX list is referred to as an LX prediction, and is then used in this sense unless otherwise indicated. In the case of calling step S3103, which is the process of outputting the time merge candidate in L0, LX is set to L0, and in the case of calling step S3104, which is the process of outputting the candidate for merging time in L1, LX is set to L1.

In the case when the PredMode prediction mode of the colPU prediction block of another time is intra-frame prediction (MODE_INTRA) or the colPU prediction block cannot be used, (No in step S3402, No in step S3401), both flags, the flag availableFlagLXCo1 and the flag predFlagLXCo1, are set equal to 0 (step S3403), the motion vector mvLXCo1 is set to (0,0) (step S3404), the process of outputting the interframe prediction information of the time merge candidate is completed.

In the case where the prediction unit co1PU can be used in the case where the prediction mode PredNode is not an intra prediction mode (MODE_INRTA) (Yes in step S3401, Yes in step S3402), mvCo1, refIdxCo1 and availableFlagCo1 are outputted by the following procedure.

In the case where the flag PredFlagL0 [xPCo1] [yPCo1], which indicates whether or not the L0 prediction of the colPU prediction block is 0 (Yes in step S3405), the prediction mode of the colPU prediction block is Pred_L1, therefore, the motion vector mvCo1 is set to a value identical to the value of MvL1 [xPCo1] [yPCo1], which is a motion vector in L1 of the colPU prediction unit (step S3406), the reference index refIdxCo1 is set to a value identical to the value of the reference index RefIdxL1 [xPCo1] [yPCo1] in L1 (step S3407) and the list ListCo1 is set as L1 (step S3408). Here, xPCo1 and yPCo1 are indices indicating the position of the upper left pixel of the co1PU prediction block inside the co1Pic frame of another point in time.

On the other hand, in the case where the PredFlagL0 [xPCo1] [yPCLo1] L0 prediction flag of the co1PU prediction block is not 0 (No in step S3405 in FIG. 37), it is determined whether or not the PredFlagL1 [xPCo1] [yPCLo1 flag is ] L1 prediction of the prediction block co1PU equal to 0. In the case where the flag PredFlagL1 [xPCo1] [yPCLo1] L1 prediction of the prediction block co1PU is 0 (Yes in step S3409), the motion vector mvCo1 is set to the value identical to the value MvL0 [xPCo1] [ yPCo1], which is a motion vector in L0 of the prediction block co1PU (step S3410), the reference index refIdxCo1 is set to be identical in value to of the reference index RefIdxL0 [xPCo1] [yPCLo1] in L0 (step S3411), and the list ListCo1 is set to L0 (step S3412).

On the other hand, in the case where the PredFlagL0 [xPCo1] [yPCLo1] flag of the L0 prediction of the co1PU prediction block and the PredFlagL1 [xPCo1] [yPCLo1] flag of the L1 prediction of the co1PU block are not 0 at the same time (No in step S3405 and No in step S3409 ), the inter prediction mode of the co1PU prediction block is bi-prediction (Pred_BI), and therefore, one is selected from the motion vectors in two L0 and L1 (step S3413).

In FIG. 38 is a flowchart illustrating a process for outputting time merge candidate inter prediction information when the inter prediction mode of the co1PU prediction unit is bi-prediction (Pred_BI).

First, it is determined whether or not the POCs of all frames registered in all reference lists are less than the POCs of the frame that is the subject of the current encoding or decoding (step S3501). In the case where the POC of all frames registered in L0 or L1, where L0 and L1 are the reference lists of the co1PU prediction block, will be smaller than the POC of the frame being the object of the current encoding or decoding (Yes in step S3501), and LX is L0, that is, the candidate for the motion vector prediction vector in L0 of the frame to be encoded or decoded is output (Yes in step S3502), the inter prediction information in L0 of the prediction block co1PU is selected, and in the case where LX is L1, that is, it is output prediction vector candidate a motion vector in frame L1, which is the object of encoding or decoding (No at step S3502), selects the interframe prediction information in L1 co1PU prediction block. On the other hand, in the case where at least one of the POCs of the frames registered in any of the reference lists L0 and L1 of the co1PU prediction unit is larger than the POCs of the frame being the object of the current encoding or decoding (No in step S3501), and while the collocated_from_10_flag flag is 0 (Yes in step S3503), then the inter prediction information in L0 of the prediction block co1PU is selected, and in the case where the collocated_from_10_flag flag is 1, (No in step S3503), the inter prediction information in L1 of the block is selected predictions co1PU.

In the case of selecting inter-frame prediction information in L0 of the co1PU prediction block (Yes in step and Yes in step S3503), the motion vector mvCo1 is set to the same value as MvL0 [xPCo1] [yPCo1] (step S3504), the reference index refIdxCo1 is set to the same value as RefIdxL0 [xPC01] [yPCo1] (step S3505), and the list ListCo1 is set to L0 (step S3506).

In the case of selecting the inter prediction information in L1 of the co1PU prediction block (No in step S2502 and No in step S3503), the motion vector mvCo1 is set to the value identical to the value MvL1 [xPCo1] [yPCo1] (step S3507), the reference index refIdxCo1 is set to the same value the value of RefIdxL1 [xPC01] [yPCo1] (step S3508), and the ListCo1 list is set to L1 (step S3509).

Referring again to FIG. 37, if the inter prediction information can be derived from the prediction unit co1PU, then the flag availableFlagLXCo1 and the flag predFlagLXCo1 are both set to 1 (step S3414).

After that, the motion vector mcCo1 is scaled and determined as the motion vector mvLXCo1 in LX of the time merge candidate (step S3415). With reference to FIG. 39 and FIG. 40, an explanation will be given of a procedure for calculating a motion vector scale.

In FIG. 39 is a flowchart showing a process of calculating a scale of a motion vector of step S3105 in FIG. 34.

Subtracting the POC of the reference frame corresponding to the reference index refIdxCo1, which is referenced in the list ListCo1 of the prediction block co1PU, from the POC of the frame co1Pic of another time, the distance td between the frames is output (step S3601). Further, in the case where the POC of the reference frame being referenced in the list ListCo1 of the prediction unit co1PU is preceding the frame co1Pic of another point in time in the playback order, the distance td between the frames is positive, and in the case where the POC of the reference frame, which is accessed in the list ListCo1 of the prediction block co1PU, is next relative to the frame co1Pic of another point in time in the playback order, then the distance td between the frames has a negative value.

td = POC of the prediction block co1PU of another point in time - POC of the reference frame, which is accessed in the list ListCo1 of the prediction block co1PU.

Subtracting the POC of the reference frame corresponding to the reference index in LX of the time merge candidate output in step S202 of FIG. 18, the distance between the frames is derived from the POC of the frame that is the subject of the current encoding or decoding (step S3602). In the case where the reference frame that is being accessed in the LX list of the frame that is the object of the current encoding or decoding is the previous in the playback order relative to the frame that is the object of the current encoding or decoding, the distance between the frames takes a positive value, and in the case when the reference frame that is being accessed in the LX list of the frame that is the object of the current encoding or decoding is the next in the playback order relative to the frame, i representing object of this coding or decoding, the distance between frames takes a negative value.

tb = POC of the frame that is the object of the current encoding or decoding - POC of the reference frame corresponding to the reference index in LX of the candidate for time merger.

After that, the distances td between frames and tb between frames are compared (step S3603). In the case where the distances td and tb are identical to each other (Yes in step S3603), the motion vector mvLXCo1 in LX of the time merge candidate is set to be identical in value to the value of the motion vector mvCo1 (step S3604), and the scaling process is completed.

mvLXCo1 = mvCo1

On the other hand, in the case where the distances td and tb are not identical to each other (No in step S3603), a scale calculation process is performed by multiplying mvCo1 by tb or td in accordance with the following equation (step S3605), and the scaled motion vector mvCo1 in LX candidate for a time merger.

mvLXCo1 = tb or td * mvCo1

In FIG. 40 shows an example in the case where the calculation of the scale in step S3605 is performed to the nearest integer. The processes of step S3606 to step S3608 of FIG. 40 correspond to step S3605 in FIG. 40.

First, in the same manner as in the block diagram shown in FIG. 39, the distance td between the frames and the distance tb between the frames is output (step S3601 and S3602).

After that, the distances td between frames and tb between frames are compared (step S3603). In the case where the distances td and tb are identical (Yes in step S3603), the motion vector mvLXCo1 in LX of the time merge candidate is set to be identical in value to the value of the motion vector mvCo1 (step S3604), in the same way as in the block diagram on FIG. 39, and the scale calculation process is completed.

mvLXCo1 = mvCo1

On the other hand, in the case where the distances td and tb are not identical (No in step S3603), the variable tx is output in accordance with the following equation (step S3606).

tx = (16384 + Abs (td or 2)) or td

Next, the DistScaleFactor scaling factor is output in accordance with the following equation (step S3607).

DistScaleFactor = (tb * tx + 32) >> 6

After that, the scaled motion vector mvLXCo1 in LX of the time merge candidate is determined in accordance with the following equation (step S3608).

mvLXCo1 = ClipMv (Sign (DistScaleFactor * mvCo1) *

((Abs (DistScaleFactor * mvCo1) +127) >> 8))

Next, a detailed explanation will be given of the method of step S204 in FIG. 18 registering the merger candidate in the list of merger candidates and constructing a list of merger candidates. In FIG. 41 is a flowchart showing a processing procedure for constructing a list of merge candidates. In accordance with this method, setting priorities and registering merge candidates with a higher priority in the mergeCandList merge candidate list, the merge index code merge_idx [x0] [y0] is reduced. By inserting a higher priority element at the top of the list of merge candidates, the code value is reduced. For example, when there are five elements in the mergeCandList merge candidate list, index 0 of the merge candidate list is set to “0”, its index 1 is set to “10”, its index 2 is set to “110”, its index 3 is set as "1110" and its index 4 is set as "11110", thereby the value of the code representing index 0 becomes 1 bit. By registering with an index of 1 elements for which it is assumed that they will occur with a high frequency, the code value is reduced.

The merge candidate list mergeCandList is configured as a list structure that contains merge indices indicating the position in the merge candidate list and a memory area in which merge candidates corresponding to their indices are stored as elements. The merge index number starts at 0, and the merge candidates are stored in the memory area of the mergeCandList merge candidate list. In the subsequent process, the prediction block that becomes the merge candidate with the merge index i registered in the mergeCandList merge candidate list is represented as mergeCandList [i], thereby differs from the merge candidate list mergeCandList in matrix form.

First, in the case where availableFlagA is 1 (Yes in step S4101), merge candidate A is registered at the beginning of the mergeCandList merge candidate list (step S4102).

After that, in the case where availableFlagB is 1 (Yes in step S4103), merge candidate B is registered at the end of the mergeCandList merge candidate list (step S4104).

After that, in the case where availableFlagC is 1 (Yes in step S4105), the merge candidate C is registered at the end of the mergeCandList merge candidate list (step S4106).

After that, in the case where availableFlagD is 1 (Yes in step S4107), the merge candidate D is registered at the end of the mergeCandList merge candidate list (step S4108).

After that, in the case where availableFlagE is 1 (Yes in step S4109), the merge candidate E is registered at the end of the mergeCandList merge candidate list (step S4110).

After that, in the case where availableFlagCo1 is 1 (Yes in step S4109), the Co1 merge candidate is registered at the end of the mergeCandList merge candidate list (step S4110).

Further, in the merge mode, the prediction block A, which is adjacent to the left, and the prediction block B, which is adjacent to the top, are often located so that they become one with the prediction block that is the object of encoding or decoding, therefore, in the case where interframe information can be output predictions of prediction blocks A and B, candidates for merging A and B are registered in the list of candidates priority, ahead of other candidates for merging C, D, E and Co1.

In FIG. 13, in the encoding information selection unit 136 of the inter prediction information output unit 104 of the moving picture encoding device, a merge candidate is selected from among the merge candidates registered in the merge candidate list, and the merge indices and the interframe prediction information of the merge candidates corresponding to the merge indices are provided to the motion compensation prediction unit 105.

When selecting a merge candidate, a method similar to the method in the prediction method determination unit 107 may be used. For each merge candidate, encoding information and coding distortion between the code value of the coding information and the residual signal, and coding distortion between the signal of the prediction frame and frame signal. A merge candidate is determined that has the smallest generated code and the least coding distortion. For each merge candidate, entropy encoding of the syntax element merge_idx, which is information for encoding the merge mode, is performed, and the code value of the encoding information is calculated. Next, for each merge candidate, the code value of the encoded prediction residual signal is calculated in a manner similar to the method in the motion compensation prediction unit 105. The prediction residual signal is the residual signal between the signal of the prediction frame on which motion compensation is carried out in accordance with the information of the inter prediction of each candidate on merging, and a frame signal, which is the object of encoding and which is provided from the frame memory 101. It is calculated and received I, as the evaluation value, the total value of the generated code, to which is added the code value of the information for coding (that is, the merge index) and the code value of the residual prediction signal.

Further, after encoding the residual prediction signal thus obtained, decoding is performed to estimate the amount of distortion, and the encoding distortion is calculated as a coefficient representing the signal error of the original frame resulting from the encoding. By comparing the total value of the generated code and coding distortions for each merge candidate, coding information is determined at which the value of the generated code and coding distortions become the smallest. The merge index corresponding to the encoding information determined in this case is encoded as the merg_idx flag represented by the second syntax structure of the prediction block. Preferably, the value of the generated code calculated here is a value obtained by simulating coding processes, however, approximations can also be applied to simplify calculations or to make rough estimates.

On the other hand, in FIG. 14, in the encoding information selection block 236 of the inter prediction information output unit 205 of the moving picture encoding device from the merge candidates registered in the merge candidate list, a merge candidate that matches the obtained merge index is selected, and the merge candidate inter-frame prediction information is provided to the block motion compensation predictions 206, and is stored in encoding information storage memory 210.

The moving image bitstream outputted from the moving image encoding apparatus according to the embodiments described above has a specific data format so that the data stream can be decoded in accordance with the encoding method used in these embodiments. A moving image decoding apparatus corresponding to a moving image encoding apparatus may decode a bitstream in this specific format.

In the case where a wired or wireless network is used to exchange bit streams between the moving image encoding device and the moving image decoding device, the bit stream can be converted into a data format suitable for a transmission method over a communication channel. In this case, a moving image transmission device and a moving image receiving device are used. The moving image transmission device converts the bitstream output from the moving image encoding device into encoded data in a data format suitable for the transmission method through the communication channel, and transmits the encoded data to the network. The moving image receiving device receives encoded data from the network, reconstructs the bitstream, and provides this bitstream to the moving image decoding device.

The moving image transmission device comprises a memory that buffers a bitstream output from the moving image encoding device, a packet processing unit that packetizes the bitstream, a transmission unit that transmits the packetized bitstream through the network. A moving image receiving device comprises a receiving unit that receives a packetized bitstream through a network, a memory that buffers the received bitstream, and a packet processing unit that processes encoded data packets, generates a bitstream, and provides this bitstream to a moving image decoding device.

It should be noted that the processes related to encoding and decoding described above can undoubtedly be implemented as transmitting, storing and receiving devices using hardware. The processes can also be implemented by embedded programs stored in read-only memory (ROM), flash memory or computer programs or others. An embedded program or program implemented in software may be stored on and provided by the computer, read from a computer, may be received from a server via a wired or wireless network, or may be provided by means of data broadcasting, such as terrestrial broadcasting or digital satellite broadcasting.

The above is an explanation based on exemplary embodiments. It is believed that these exemplary embodiments are illustrative only and it will be apparent to those skilled in the art that various modifications to the constituent elements and processes can be developed and that such modifications are also within the scope of the present invention.

Item 1. A moving image coding device that divides a first block obtained by dividing each frame into one or more second blocks, and encodes a moving image using inter-frame prediction, comprising:

an output unit of the first prediction information that outputs the candidate for the first inter prediction information from the inter prediction information of the third block adjacent to the second block that is the object of encoding, inside the frame that is the object of encoding;

an output unit of the second prediction information that outputs the candidate for the second inter prediction information from the inter prediction information of the fourth block, which is in a position identical to the position of the second block that is the encoding object, or in its vicinity, inside a frame different from the frame that is the encoding object ;

a candidate list construction unit that generates a list of candidates for prediction information containing candidates for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this output candidate for the first inter-frame prediction information is added, and in the case when the candidate is displayed to the second inter prediction information, respectively, this inferred candidate for the second inter prediction information is added;

a selection unit that selects a candidate for inter prediction information used for inter prediction of the second block to be encoded from one or more prediction information candidates in the prediction information candidate list, and determines an index that indicates inter prediction information;

an encoding unit that encodes an index indicating inter-prediction information used for inter-prediction of a second block being an encoding; wherein

the output unit of the first prediction information does not use, as a candidate for the first inter prediction information, encoding information of a fifth block contained in a block identical to the first block containing the second block that is the encoding object.

Clause 2. A moving image encoding device according to Clause 1, characterized in that the output unit of the second prediction information outputs the candidate to the second inter prediction information without reference to the encoding information of the fifth block.

Clause 3. A moving image encoding device, in accordance with paragraphs 1 or 2, characterized in that in the separation mode, where the first block is divided into the upper sixth block and the lower seventh block, arranged vertically, in the case when the second block being the object of encoding is a seventh block, the output block of the first prediction information does not use encoding information of the sixth block adjacent to the upper side of the seventh block as a candidate for the first inter prediction information, and

in the division mode, where the first block is divided into the left eighth block and the right ninth block arranged horizontally, in the case where the second block being the encoding is the ninth block, the output unit of the first prediction information does not use encoding information of the eighth block adjacent to the left side of the ninth block, as a candidate for the first inter-frame prediction information.

Clause 4. A moving image encoding device in accordance with Clause 3, characterized in that in the merge mode in which the inter prediction of the second block being the encoding is performed, based on the inter prediction information containing the candidate for the second inter prediction information, for any the second block, which is the object of encoding, and regardless of the split mode, the output block of the second prediction information assigns reference index information to the specification the reference frame in the candidate for the second inter-frame prediction information, the default value and outputs the candidate for the second inter-frame prediction information based on the reference index information to which the default value is assigned.

Clause 5. The moving image coding apparatus according to Clause 4, characterized in that the default value assigned to the reference index information of the candidate for the second inter-frame prediction information is 0.

Item 6. A moving image encoding device that divides an encoding block into one or more prediction blocks in accordance with a separation mode, and conducts motion compensation prediction, comprising:

a reference index output unit, which is in a merge mode, where the inter prediction information determined as a time merge candidate is derived from the inter prediction information of the prediction unit that is in a position identical to or in the vicinity of the prediction unit that is the encoding object, inside the encoded frame, different in time from the prediction block that is the encoding object, and based on the output information of the inter-frame prediction, inter-frames are performed e prediction prediction block which is the object of coding, displays the information on the reference index merging candidate time as the reference index information that specifies a reference frame used in the prediction block, which is the object of encoding; and

a time merge candidate generation unit that outputs interframe prediction information of a time merge candidate based on the derived information of the reference index, wherein

in the case where the separation mode is a mode where the coding unit is divided by a horizontal border into the prediction units arranged vertically, the reference index output unit assigns the reference time index information of the time merge candidate to the reference index information of the encoded prediction unit adjacent to the left side of the prediction unit, which is the object of encoding, and provides this reference index information, and

in the case where the separation mode is a mode where the coding unit is divided by a vertical boundary into the prediction units horizontally, the reference index output unit assigns the reference time index information of the candidate for fusion to the reference index information of the encoded prediction unit adjacent to the upper side of the prediction unit, being the object of encoding, and provides this reference index information.

Clause 7. A method of encoding a moving image that divides the first block obtained by dividing each frame into one or more second blocks, and encodes the moving image using inter-frame prediction, comprising:

the stage at which the candidate for the first inter-frame prediction information is derived from the inter-frame prediction information of the third block adjacent to the second block that is the encoding object, inside the frame that is the encoding object;

the stage at which the candidate for the second inter-prediction information is derived from the inter-prediction information of the fourth block, which is in a position identical to the position of the second block that is the encoding object, or in its vicinity, inside a frame different from the frame that is the encoding object;

the stage at which a list of candidates for prediction information is constructed containing candidates for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this derived candidate for the first inter-frame prediction information is added, and in the case when a candidate for the second inter prediction information, respectively, this derived candidate for the second inter prediction information is added;

a step in which a candidate for inter-prediction information used for inter-prediction of the second block to be encoded is selected from one or more prediction information candidates in the prediction information candidate list, and an index that indicates inter-prediction information is determined;

a step of encoding an index indicating inter-prediction information used for inter-prediction of a second block to be encoded; wherein

the stage at which the candidate for the first inter-frame prediction information is output does not use the encoding information of the fifth block contained in a block identical to the first block containing the second block that is the encoding object as a candidate for the first inter-frame prediction information.

Clause 8. A method of encoding a moving image in accordance with clause 7, characterized in that at the stage in which the second prediction information is output, the candidate for the second inter-prediction information is displayed without reference to the encoding information of the fifth block.

Clause 9. A method for encoding a moving image, in accordance with clauses 7 or 8, characterized in that

in the split mode, where the first block is divided into the upper sixth block and the lower seventh block arranged vertically, in the case where the second block to be encoded is the seventh block, the stage in which the first prediction information is output does not use the encoding information of the sixth block adjacent to the upper side of the seventh block as a candidate for the first inter-frame prediction information, and

in the split mode, where the first block is divided into a left eighth block and a right ninth block arranged horizontally, in the case where the second block being an encoding is a ninth block, the stage in which the first prediction information is output does not use the encoding information of the eighth block adjacent to the left side of the ninth block, as a candidate for the first inter-frame prediction information.

Clause 10. A method for encoding a moving image in accordance with Clause 9, characterized in that in the merge mode, where the inter prediction of the second block being the decoding is performed, based on the inter prediction information containing the candidate for the second inter prediction information, for any second block, which is the object of encoding, and regardless of the separation mode, the step of outputting the second prediction information assigns reference index information for specification Porn frame candidate for a second inter prediction information, the default value and displays the information of the candidate for the second inter-prediction based on the information the reference index, which is set by default.

Clause 11. A method for encoding a moving image in accordance with Clause 10, characterized in that the default value assigned to the reference index information of the candidate for the second inter-frame prediction information is 0.

Clause 12. A moving image coding program recorded on a recording medium and read by a computer, which divides the first block obtained by dividing each frame into one or more second blocks, and encodes the moving image using inter-frame prediction, comprising:

an output unit of the first prediction information that outputs the candidate for the first inter prediction information from the inter prediction information of the third block adjacent to the second block that is the object of encoding, inside the frame that is the object of encoding;

an output unit of the second prediction information that outputs the candidate for the second inter prediction information from the inter prediction information of the fourth block, which is in a position identical to the position of the second block that is the encoding object, or in its vicinity, inside a frame other than the frame that is the encoding object ;

a candidate list building module that generates a list of candidates for prediction information containing candidates for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this output candidate for the first inter-frame prediction information is added, and in the case when the candidate is displayed to the second inter prediction information, respectively, this inferred candidate for the second inter prediction information is added;

a selection module that selects a candidate for inter prediction information used for inter prediction of the second block to be encoded from one or more prediction information candidates in the prediction information candidate list and determines an index that indicates inter prediction information;

an encoding module that encodes an index indicative of inter prediction information used for inter prediction of a second block being an encoding, wherein

the output module of the first prediction information does not use, as a candidate for the first inter prediction information, the encoding information of the fifth block contained in a block identical to the first block containing the second block that is the encoding object.

Clause 13. A coding program for a moving image in accordance with Clause 12, characterized in that

in the division mode, where the first block is divided into the upper sixth block and the lower seventh block arranged vertically, in the case where the second block being the encoding is the seventh block, the first prediction information output unit does not use encoding information of the sixth block adjacent to the upper side of the seventh block, as a candidate for the first inter-frame prediction information, and

in the division mode, where the first block is divided into the left eighth block and the right ninth block arranged horizontally, in the case where the second block being the encoding object is the ninth block, the first prediction information output unit does not use encoding information of the eighth block adjacent to the left side of the ninth block, as a candidate for the first inter-frame prediction information, and

in the merge mode, where the inter prediction of the second block being the coding is performed, based on the information of the inter prediction containing the candidate for the second inter prediction information, for any second block that is the coding, and regardless of the separation mode, the output module of the second prediction information assigns information reference index for specifying the reference frame in the candidate for the second inter-frame prediction information, the default value and in leads the candidate for the second inter-prediction information based on the information the reference index, which is set by default.

Clause 14. A moving image decoding apparatus that decodes a bitstream, where the first block, which is obtained by dividing each frame, is divided into one or more second blocks, and the moving image is encoded using inter-frame prediction, comprising:

an output unit of the first prediction information that outputs the candidate for the first inter prediction information from the inter prediction information of the third block adjacent to the second block that is the decoding object within the frame that is the decoding object;

an output unit of the second prediction information, which outputs the candidate for the second inter prediction information from the inter prediction information of the fourth block, which is in a position identical to the position of the second block that is the decoding object, or in its vicinity, inside a frame different from the frame that is the decoding object ;

a decoding unit that decodes an index indicating inter-prediction information used for inter-prediction of a second block to be decoded;

a candidate list construction unit that generates a list of candidates for prediction information containing candidates for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this output candidate for the first inter-frame prediction information is added, and in the case when the candidate is displayed to the second inter prediction information, respectively, this inferred candidate for the second inter prediction information is added; and

a selection unit that selects a candidate for inter prediction information used for inter prediction of a second block that is the decoding object indicated by the index from one or more prediction information candidates in the prediction information candidate list, wherein

the output unit of the first prediction information does not use, as a candidate for the first inter prediction information, encoding information of a fifth block contained in a block identical to the first block containing the second block that is the decoding object.

Clause 15. A moving image decoding apparatus according to Clause 14, characterized in that the output unit of the second prediction information outputs the candidate to the second inter-frame prediction information without reference to the encoding information of the fifth block.

Clause 16. A moving image decoding device, in accordance with clauses 14 or 15, characterized in that

in the split mode, where the first block is divided into the upper sixth block and the lower seventh block arranged vertically, in the case where the second block being the decoding object is the seventh block, the first prediction information output unit does not use encoding information of the sixth block adjacent to the upper the side of the seventh block, as a candidate for the first inter-frame prediction information, and

in the split mode, where the first block is divided into the left eighth block and the right ninth block arranged horizontally, in the case where the second block being the decoding object is the ninth block, the output unit of the first prediction information does not use encoding information of the eighth block adjacent to the left side of the ninth block, as a candidate for the first inter-frame prediction information.

Clause 17. A moving image decoding apparatus according to clause 16, characterized in that in the merge mode, where the inter prediction of the second block that is the decoding object is carried out, based on the inter prediction information containing the candidate for the second inter prediction information, for any second block, which is the object of encoding, and regardless of the separation mode, the output block of the second prediction information assigns reference index information to the spec Bani reference frame candidate information for the second inter-frame prediction is the default and displays the information of the candidate for the second inter-prediction based on the information the reference index, which is set by default.

Clause 18. A method for decoding a moving image in accordance with Clause 17, wherein the default value assigned as the reference index information of the candidate for the second inter-frame prediction information is 0.

Clause 19. A moving image decoding apparatus that divides a decoding unit into one or more prediction blocks in accordance with a separation mode, and conducts motion compensation prediction, comprising:

a reference index output unit, which is in a merge mode, where the inter prediction information determined as a time merge candidate is derived from the inter prediction information of the prediction unit that is in a position identical to or in the vicinity of the prediction unit that is the decoding object, inside the decoded frame, which is different in time from the prediction block that is the object of decoding, and from the output inter prediction information, an inter frame a new prediction of the prediction unit being the decoding object outputs information of the reference index of the time merge candidate as information of the reference index that specifies a reference frame used in the prediction unit being the decoding object; and

a time merge candidate generation unit that outputs interframe prediction information of a time merge candidate based on the derived information of the reference index, wherein

in the case where the separation mode is a mode where the decoding unit is divided by a horizontal boundary into the prediction units arranged vertically, the reference index output unit assigns the reference time index information of the candidate for fusion to the reference index information of the decoded prediction unit adjacent to the left side of the prediction unit, which is the object of decoding, and provides this information of the reference index, and

in the case where the separation mode is a mode where the decoding unit is divided by a vertical border into the prediction units horizontally, the reference index output unit assigns the reference time index information of the candidate for fusion to the reference information of the decoded prediction unit adjacent to the upper side of the prediction unit, being the decoding object, and provides this reference index information.

Item 20. A method for decoding a moving image that decodes an encoded bitstream, where the first block, which is obtained by dividing each frame, is divided into one or more second blocks, and the moving image is encoded using inter-frame prediction, comprising:

the stage at which the candidate for the first inter-frame prediction information is derived from the inter-frame prediction information of the third block adjacent to the second block that is the decoding object within the frame that is the decoding object;

the stage at which the candidate for the second inter prediction information is derived from the inter prediction information of the fourth block, which is in a position identical to the position of the second block that is the decoding object, or in its vicinity, inside a frame different from the frame that is the decoding object;

a step of decoding an index indicating inter-prediction information used for inter-prediction of the second block to be decoded;

the stage at which a list of candidates for prediction information is constructed containing candidates for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this derived candidate for the first inter-frame prediction information is added, and in the case when a candidate for the second inter prediction information, respectively, this derived candidate for the second inter prediction information is added; and

the step of selecting a candidate for inter prediction information used for inter prediction of the second block that is the decoding object indicated by the index from one or more prediction information candidates in the list of candidates for prediction information, wherein

the stage at which the candidate for the first inter-prediction information is displayed does not use the encoding information of the fifth block contained in a block identical to the first block containing the second block that is the decoding object as a candidate for the first inter-prediction information.

Clause 21. A method for decoding a moving image in accordance with clause 20, characterized in that in the step in which the second prediction information is output, the candidate for the second inter-frame prediction information is output without reference to the encoding information of the fifth block.

Paragraph 22. A method for decoding a moving image, in accordance with paragraphs 20 or 21, characterized in that

in the division mode, where the first block is divided into the upper sixth block and the lower seventh block arranged vertically, in the case where the second block being the decoding object is the seventh block, the stage in which the first prediction information is output does not use the encoding information of the sixth block adjacent to the upper side of the seventh block as a candidate for the first inter-frame prediction information, and

in the split mode, where the first block is divided into a left eighth block and a right ninth block arranged horizontally, in the case where the second block being the decoding object is the ninth block, the stage in which the first prediction information is output does not use the encoding information of the eighth block adjacent to the left side of the ninth block, as a candidate for the first inter-frame prediction information.

Clause 23. The method of decoding a moving image in accordance with clause 22, characterized in that in the merge mode, where the inter prediction of the second block being the decoding is performed, based on the inter prediction information containing the candidate for the second inter prediction information, for any second block, which is the object of decoding, regardless of the separation mode, the stage at which the second information is displayed prediction assigns information of the reference index for specifying the reference frame in the candidate for the second inter-frame prediction information, the default value, and outputs the candidate for the second inter-frame prediction information based on the reference index information to which the default value is assigned.

Clause 24. A method for decoding a moving image in accordance with clause 23, wherein the default value assigned to the reference index information of the candidate for the second inter-frame prediction information is 0.

Paragraph 25. A moving image decoding program recorded on a recording medium and read by a computer, decoding an encoded bitstream, where the first block, which is obtained by dividing each frame, is divided into one or more second blocks, and the moving image is encoded using inter-frame prediction, comprising:

a candidate output module for first prediction information that outputs a candidate for first inter prediction information from inter prediction information of a third block adjacent to a second block that is a decoding object within a frame that is a decoding object;

an output unit of the second prediction information that outputs the candidate for the second inter prediction information from the inter prediction information of the fourth block, which is in a position identical to the position of the second block that is the decoding object, or in its vicinity, inside a frame other than the frame that is the decoding object ;

a decoding module that decodes an index indicating inter-prediction information used for inter-prediction of a second block to be decoded;

a candidate list building module that generates a list of candidates for prediction information containing candidates for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this output candidate for the first inter-frame prediction information is added, and in the case when the candidate is displayed to the second inter prediction information, respectively, this inferred candidate for the second inter prediction information is added; and

a selection module that selects a candidate for inter prediction information used for inter prediction of a second block that is the decoding object indicated by the index from one or more prediction information candidates in the prediction information candidate list;

the output module of the first prediction information does not use, as a candidate for the first inter prediction information, encoding information of a fifth block contained in a block identical to the first block containing the second block that is the decoding object.

Paragraph 26. The program for decoding a moving image in accordance with paragraph 25, characterized in that

in the division mode, where the first block is divided into the upper sixth block and the lower seventh block arranged vertically, in the case where the second block being the decoding object is the seventh block, the first prediction information output unit does not use encoding information of the sixth block adjacent to the upper side of the seventh block, as a candidate for the first inter-frame prediction information, and

in the split mode, where the first block is divided into the left eighth block and the right ninth block arranged horizontally, in the case where the second block being the decoding object is the ninth block, the first prediction information output unit does not use encoding information of the eighth block adjacent to the left side of the ninth block, as a candidate for the first inter-frame prediction information, and

in the merge mode, where the inter prediction of the second block being the decoding object is performed, based on the inter prediction information containing the candidate for the second inter prediction information, for any second block being the decoding, regardless of the split mode, the output module of the second prediction information assigns information of the reference an index for specifying a reference frame in a candidate for the second inter prediction information default value, and outputs the candidate for the second inter prediction information based on the reference index information to which the default value is assigned.

A moving image coding apparatus that divides a first block obtained by dividing each frame into one or more second blocks, and encodes a moving image using inter-frame prediction comprising:

an output unit of the first prediction information that conducts the process of outputting one or more candidates for the first inter prediction information from the inter prediction information of one or more third blocks adjacent to the second block that is the encoding object, inside the frame that is the encoding object;

an output unit of the second prediction information, which conducts the process of outputting the candidate for the second inter prediction information from the inter prediction information of the fourth block, which is in a position identical to the position of the second block being the encoding, or in its vicinity, inside a frame other than the frame being object of coding;

a candidate list construction unit that generates a list of candidates for prediction information containing candidates for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this output candidate for the first inter-frame prediction information is added, and in the case when the candidate is displayed to the second inter prediction information, respectively, this inferred candidate for the second inter prediction information is added;

a selection unit that selects a candidate for inter prediction information used for inter prediction of the second block to be encoded from one or more prediction information candidates in the prediction information candidate list, and determines an index that indicates inter prediction information; and

an encoding unit that encodes an index indicating inter-prediction information used for inter-prediction of a second block being an encoding, wherein

the output unit of the first prediction information carries out the process of outputting the candidate to the first inter-frame prediction information without accessing the encoding information of the fifth block contained in a block identical to the first block containing the second block that is the object of encoding, and

in the split mode, where the first block is divided into the upper block and the lower block arranged vertically with a 1: 3 ratio, the second prediction information output unit carries out the process of outputting the candidate to the second inter-frame prediction information based on the reference index by assigning a default value to the reference index value, without reference to the encoding information of the fifth block contained in the block identical to the first block containing the second block that is the object of encoding.

A moving image decoding apparatus that decodes a bitstream, where the first block obtained by dividing each frame is divided into one or more second blocks, and the moving image is encoded using inter-frame prediction, comprising:

an output unit of the first prediction information that conducts the process of outputting one or more candidates for the first inter prediction information from the inter prediction information of one or more third blocks adjacent to the second block that is the decoding object within the frame that is the decoding object;

an output unit of the second prediction information that conducts the process of outputting the candidate for the second inter prediction information from the inter prediction information of the fourth block, which is in a position identical to the position of the second block being the decoding object, or in its vicinity, inside a frame other than the frame being decoding object;

a decoding unit that decodes an index indicating inter-prediction information used for inter-prediction of a second block to be decoded;

a candidate list construction unit that generates a list of candidates for prediction information containing candidates for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this output candidate for the first inter-frame prediction information is added, and in the case when the candidate is displayed to the second inter prediction information, respectively, this inferred candidate for the second inter prediction information is added; and

a selection unit that selects a candidate for inter prediction information used for inter prediction of a second block that is the decoding object indicated by the index from one or more prediction information candidates in the prediction information candidate list, wherein

the output unit of the first prediction information conducts the process of outputting the candidate to the first inter-frame prediction information without accessing the encoding information of the fifth block contained in a block identical to the first block containing the second block that is the object of decoding, and

in the split mode, where the first block is divided into the upper block and the lower block arranged vertically with a 1: 3 ratio, the second prediction information output unit carries out the process of outputting the candidate to the second inter-frame prediction information based on the reference index by assigning a default value to the reference index value, without reference to the encoding information of the fifth block contained in the block identical to the first block containing the second block that is the object of decoding.

A moving image decoding method that decodes an encoded bitstream, where the first block obtained by dividing each frame is divided into one or more second blocks, and the moving image is encoded using inter-frame prediction, comprising:

a step in which the process of deriving one or more candidates for the first inter-frame prediction information from the inter-frame prediction information of one or more third blocks adjacent to the second block that is the decoding object within the frame that is the decoding object is carried out;

a step in which the process of deriving a candidate for the second inter prediction information from the inter prediction information of the fourth block, which is in a position identical to the position of the second block being the object of decoding, or in its vicinity, inside the frame other than the frame being the object of decoding;

a step of decoding an index indicating inter-prediction information used for inter-prediction of the second block to be decoded;

the stage at which a list of candidates for prediction information is constructed containing candidates for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this derived candidate for the first inter-frame prediction information is added, and in the case when a candidate for the second inter prediction information, respectively, this derived candidate for the second inter prediction information is added; and

the step of selecting a candidate for inter prediction information used for inter prediction of the second block that is the decoding object indicated by the index from one or more prediction information candidates in the list of candidates for prediction information,

the stage at which the process of outputting one or more candidates for the first inter-frame prediction information is carried out, the process of outputting the candidate for the first inter-frame prediction information without resorting to encoding information of the fifth block contained in the block identical to the first block containing the second block that is the decoding object, and wherein

in the separation mode, where the first block is divided into the upper block and the lower block arranged vertically with a ratio of 1: 3, the stage in which the process of outputting the second prediction information is carried out, conducts the process of outputting the candidate to the second inter-frame prediction information based on the reference index by assigning the value reference index default value, without reference to the encoding information of the fifth block contained in the block identical to the first block containing the second block that is the decoding object.

A transmission device comprising:

a packet processing unit that packetizes a bitstream encoded by a moving image coding method that divides a first block obtained by dividing each frame into one or more second blocks, and a moving image is encoded using inter-frame prediction to obtain encoded data; and

a transmission unit that transmits a packetized bitstream, wherein the moving picture coding method comprises:

a step in which the process of deriving one or more candidates for the first inter-frame prediction information from the inter-frame prediction information of one or more third blocks adjacent to the second block that is the object of encoding, inside the frame that is the object of encoding;

a step in which the process of deriving a candidate for the second inter prediction information from the inter prediction information of the fourth block, which is in a position identical to the position of the second block that is the encoding object, or in its vicinity, inside the frame other than the frame that is the encoding object;

the stage at which a list of candidates for prediction information is constructed containing candidates for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this derived candidate for the first inter-frame prediction information is added, and in the case when a candidate for the second inter prediction information, respectively, this derived candidate for the second inter prediction information is added;

a step in which a candidate for inter-prediction information used for inter-prediction of the second block that is the coding indicated by the index is selected from one or more prediction information candidates in the prediction information candidate list, and an index indicating inter-prediction information is determined; and

a step at which an index is encoded indicating inter-prediction information used for inter-prediction of the second block to be encoded, wherein

the stage in which the process of outputting one or more candidates for the first inter-frame prediction information is carried out, conducts the process of outputting the candidate for the first inter-frame prediction information without accessing encoding information of the fifth block contained in a block identical to the first block containing the second block that is the encoding object, and wherein

in the split mode, where the first block is divided into the upper block and the lower block vertically, with a ratio of 1: 3, the stage at which the second prediction information is output conducts the process of outputting the candidate to the second inter-frame prediction information based on the reference index by assigning the value of the reference index the default value, without reference to the encoding information of the fifth block contained in the block identical to the first block containing the second block that is the encoding object.

A transmission method comprising:

a packet processing step of packetizing a bitstream encoded by a moving picture coding method that divides the first block obtained by dividing each frame into one or more second blocks, and the moving picture is encoded using inter-frame prediction to obtain encoded data; and

the step of transmitting the packetized bitstream, wherein the moving picture encoding method comprises:

a step in which the process of deriving one or more candidates for the first inter-frame prediction information from the inter-frame prediction information of one or more third blocks adjacent to the second block that is the object of encoding, inside the frame that is the object of encoding;

a step in which the process of deriving a candidate for the second inter prediction information from the inter prediction information of the fourth block, which is in a position identical to the position of the second block that is the encoding object, or in its vicinity, inside the frame other than the frame that is the encoding object;

the stage at which a list of candidates for prediction information is constructed containing candidates for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this derived candidate for the first inter-frame prediction information is added, and in the case when a candidate for the second inter prediction information, respectively, this derived candidate for the second inter prediction information is added;

the step of selecting a candidate for inter prediction information used for inter prediction of a second block that is an encoding object indicated by an index from one or more prediction information candidates in the prediction information candidate list, and

a step at which an index is encoded indicating inter-prediction information used for inter-prediction of the second block to be encoded, wherein

the stage in which the process of outputting one or more candidates for the first inter-frame prediction information is carried out, conducts the process of outputting the candidate for the first inter-frame prediction information without accessing encoding information of the fifth block contained in a block identical to the first block containing the second block that is the encoding object, and wherein

in the split mode, where the first block is divided into the upper block and the lower block vertically, with a ratio of 1: 3, the stage at which the second prediction information is output conducts the process of outputting the candidate to the second inter-frame prediction information based on the reference index by assigning the value of the reference index the default value, without reference to the encoding information of the fifth block contained in the block identical to the first block containing the second block that is the decoding object.

A receiving device comprising:

a receiving unit that receives encoded data that is a packetized bitstream, where the first block obtained by dividing each frame is divided into one or more second blocks, and the moving image is encoded using inter-frame prediction;

a packet processing unit that processes packets of received encoded data and generates a bitstream;

an output unit of the first prediction information that conducts the process of outputting one or more candidates for the first inter-frame prediction information from the inter-frame prediction information of one or more third blocks adjacent to the second block that is the decoding object within the frame that is the decoding object in the bitstream;

an output unit of the second prediction information that conducts the process of outputting the candidate for the second inter prediction information from the inter prediction information of the fourth block, which is in a position identical to the position of the second block being the decoding object, or in its vicinity, inside a frame other than the frame being decoding object;

a decoding unit that decodes an index indicating inter-prediction information used for inter-prediction of a second block to be decoded;

a candidate list construction unit that generates a list of candidates for prediction information containing candidates for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this output candidate for the first inter-frame prediction information is added, and in the case when the candidate is displayed to the second inter prediction information, respectively, this inferred candidate for the second inter prediction information is added; and

a selection unit that selects a candidate for inter prediction information used for inter prediction of a second block that is the decoding object indicated by the index from one or more prediction information candidates in the prediction information candidate list, wherein

the output unit of the first prediction information conducts the process of outputting the candidate to the first inter-frame prediction information without accessing the encoding information of the fifth block contained in a block identical to the first block containing the second block that is the object of decoding, and

in the split mode, where the first block is divided into the upper block and the lower block arranged vertically with a 1: 3 ratio, the second prediction information output unit carries out the process of outputting the candidate to the second inter-frame prediction information based on the reference index by assigning a default value to the reference index value, without reference to the encoding information of the fifth block contained in the block identical to the first block containing the second block that is the object of decoding.

A moving image decoding apparatus that decodes a bitstream, where the first block obtained by dividing each frame is divided into one or more second blocks, and the moving image is encoded using inter-frame prediction, comprising:

an output unit of the first prediction information that performs the process of deriving one or more candidates for the first inter prediction information from the inter prediction information of one or more third blocks in the vicinity of the second block to be decoded within the frame that is being decoded;

an output unit of the second prediction information that performs the process of deriving a candidate for the second inter prediction information from the inter prediction information of the fourth block, which is in a position identical to the position of the second block being the decoding object, or in its vicinity, inside a frame other than the frame being decoding object;

a decoding unit that decodes an index indicating inter-prediction information used for inter-prediction of a second block to be decoded;

a candidate list construction unit that generates a list of candidates for prediction information containing candidates for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this output candidate for the first inter-frame prediction information is added, and in the case when the candidate is displayed to the second inter prediction information, respectively, this inferred candidate for the second inter prediction information is added; and

a selection unit that selects a candidate for inter prediction information used for inter prediction of a second block that is the decoding object indicated by the index from one or more prediction information candidates in the prediction information candidate list, wherein

in the separation mode, where the first block is divided into the upper block and the lower block, located vertically, with a ratio of 1: 1, 1: 3 or 3: 1, in the case when the second block, which is the object of decoding, is the lower block, the output unit of the first information prediction performs the process of outputting the candidate to the first information inter-frame prediction without accessing the encoding information of the fifth block adjacent to the upper side of the second block, and

in the split mode, where the first block is divided into the upper block and the lower block arranged vertically with a ratio of 1: 1, 1: 3 or 3: 1, the block for outputting the second prediction information performs the process of outputting the candidate to the second inter-frame prediction information based on the reference index the candidate for the second inter prediction information by assigning a default value to the reference index value without reference to the encoding information of the fifth block contained in a block identical to the first block containing the second block, yayuschiysya object coding.

A moving image decoding method that provides decoding of a bitstream, where the first block obtained by dividing each frame is divided into one or more second blocks, and the moving image is encoded using inter-frame prediction, comprising:

a step in which the process of outputting one or more candidates for the first inter-frame prediction information from the inter-frame prediction information of one or more third blocks in the vicinity of the second block that is the decoding object, inside the frame that is the decoding object;

a step in which the process of deriving a candidate for the second inter prediction information from the inter prediction information of the fourth block, which is in a position identical to the position of the second block that is the decoding object, or in its vicinity, inside the frame other than the frame that is the decoding object;

a step of decoding an index indicating inter-prediction information used for inter-prediction of the second block to be decoded;

a stage at which a list of candidates for prediction information is constructed containing a candidate for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this derived candidate for the first inter-frame prediction information is added, and in the case when a candidate for the second inter prediction information, respectively, this derived candidate for the second inter prediction information is added; and

the step of selecting a candidate for inter prediction information used for inter prediction of the second block that is the decoding object indicated by the index from one or more prediction information candidates in the list of candidates for prediction information,

in the split mode, where the first block is divided into the upper block and the lower block, located vertically, with a ratio of 1: 1, 1: 3 or 3: 1, in the case when the second block, which is the object of decoding, is the lower block, in step which the process of outputting one or more candidates to the first inter-frame prediction information is performed, the process of outputting the candidate to the first inter-frame prediction information is performed without reference to encoding information of the fifth block adjacent to the upper side of the second block, and

in the separation mode, where the first block is divided into the upper block and the lower block arranged vertically with a ratio of 1: 1, 1: 3 or 3: 1, at the stage where the process of outputting the second prediction information is performed, the process of outputting the candidate to the second information inter prediction is performed based on the reference index of the candidate for the second inter prediction information by assigning a default value to the reference index without accessing the encoding information of the fifth block contained in a block identical to th unit comprising a second unit being the object of decoding.

A long-term computer-readable recording medium onto which an image decoding program is recorded decoding a bitstream, where the first block obtained by dividing each frame is divided into one or more second blocks, and the moving image is encoded using inter-frame prediction, comprising:

a module for outputting the first prediction information, which enables the process of outputting one or more candidates for the first inter-frame prediction information from the inter-frame prediction information of one or more third blocks in the vicinity of the second block that is the decoding object, inside the frame that is the decoding object;

an output module of the second prediction information, which provides the process of outputting the candidate for the second inter prediction information from the inter prediction information of the fourth block, which is in a position identical to the position of the second block that is the object of decoding, or in its vicinity, inside a frame other than the frame, decoding subject;

a decoding module that provides decoding of an index indicative of inter prediction information used for inter prediction of a second block to be decoded;

a candidate list building module that provides a candidate list for prediction information containing a candidate for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this derived candidate for the first inter-frame prediction information is added, and in the case when a candidate for the second inter-frame prediction information, respectively, this derived candidate for the second inter-frame prediction information is added; and

a selection module that provides a candidate selection for inter prediction information used for inter prediction of the second block that is the decoding object indicated by the index from one or more prediction information candidates in the prediction information candidate list, wherein

in the separation mode, where the first block is divided into the upper block and the lower block, located vertically, with a ratio of 1: 1, 1: 3 or 3: 1, in the case when the second block, which is the object of decoding, is the lower block, the output unit of the first information prediction performs the process of outputting the candidate to the first information inter-frame prediction without accessing the encoding information of the fifth block adjacent to the upper side of the second block, and

in the split mode, where the first block is divided into the upper block and the lower block arranged vertically with a ratio of 1: 1, 1: 3 or 3: 1, the block for outputting the second prediction information performs the process of outputting the candidate to the second inter-frame prediction information based on the reference index the candidate for the second inter prediction information by assigning a default value to the reference index value without reference to the encoding information of the fifth block contained in a block identical to the first block containing the second block, yayuschiysya object coding.

A moving image decoding apparatus that decodes a bitstream, where the first block obtained by dividing each frame is divided into one or more second blocks, and the moving image is encoded using inter-frame prediction, comprising:

an output unit of the first prediction information that performs the process of deriving one or more candidates for the first inter prediction information from the inter prediction information of one or more third blocks in the vicinity of the second block to be decoded within the frame that is being decoded;

an output unit of the second prediction information that performs the process of deriving a candidate for the second inter prediction information from the inter prediction information of the fourth block, which is in a position identical to the position of the second block being the decoding object, or in its vicinity, inside a frame other than the frame being decoding object;

a decoding unit that decodes an index indicating inter-prediction information used for inter-prediction of a second block to be decoded;

a candidate list construction unit that generates a list of candidates for prediction information containing candidates for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this output candidate for the first inter-frame prediction information is added, and in the case when the candidate is displayed to the second inter prediction information, respectively, this inferred candidate for the second inter prediction information is added; and

a selection unit that selects a candidate for inter prediction information used for inter prediction of a second block that is the decoding object indicated by the index from one or more prediction information candidates in the prediction information candidate list, wherein

in the separation mode, where the first block is divided into the left block and the right block, located horizontally, with a ratio of 1: 1, 1: 3 or 3: 1, in the case when the second block, which is the object of decoding, is the right block, the output unit of the first information prediction performs the process of outputting the candidate to the first information inter-frame prediction without accessing the encoding information of the fifth block adjacent to the left side of the second block, and

in the split mode, where the first block is divided into a left block and a right block located horizontally with a ratio of 1: 1, 1: 3 or 3: 1, the block for outputting the second prediction information performs the process of outputting the candidate to the second inter-frame prediction information based on the reference index the candidate for the second inter prediction information by assigning a default value to the reference index value without reference to the encoding information of the fifth block contained in a block identical to the first block containing the second block, yayuschiysya object coding.

A moving image decoding method that provides decoding of a bitstream, where the first block obtained by dividing each frame is divided into one or more second blocks, and the moving image is encoded using inter-frame prediction, comprising:

a step in which the process of outputting one or more candidates for the first inter-frame prediction information from the inter-frame prediction information of one or more third blocks in the vicinity of the second block that is the decoding object, inside the frame that is the decoding object;

a step in which the process of deriving a candidate for the second inter prediction information from the inter prediction information of the fourth block, which is in a position identical to the position of the second block that is the decoding object, or in its vicinity, inside the frame other than the frame that is the decoding object;

a step of decoding an index indicating inter-prediction information used for inter-prediction of the second block to be decoded;

a stage at which a list of candidates for prediction information is constructed containing a candidate for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this derived candidate for the first inter-frame prediction information is added, and in the case when a candidate for the second inter prediction information, respectively, this derived candidate for the second inter prediction information is added; and

the step of selecting a candidate for inter prediction information used for inter prediction of the second block that is the decoding object indicated by the index from one or more prediction information candidates in the list of candidates for prediction information,

in the split mode, where the first block is divided into the left block and the right block, located horizontally, with a ratio of 1: 1, 1: 3 or 3: 1, in the case when the second block, which is the object of decoding, is the right block, at the stage, which the process of outputting one or more candidates to the first inter-frame prediction information is performed, the process of outputting the candidate to the first inter-frame prediction information is performed without reference to encoding information of the fifth block adjacent to the left side of the second block, and

in the separation mode, where the first block is divided into the left block and the right block, located horizontally, with a ratio of 1: 1, 1: 3 or 3: 1, at the stage where the process of outputting the second prediction information is performed, the process of outputting the candidate to the second information inter prediction is performed based on the reference index of the candidate for the second inter prediction information by assigning a default value to the reference index without accessing the encoding information of the fifth block contained in a block identical to th unit comprising a second unit being the object of decoding.

A long-term computer-readable recording medium onto which an image decoding program is recorded decoding a bitstream, where the first block obtained by dividing each frame is divided into one or more second blocks, and the moving image is encoded using inter-frame prediction, comprising:

a module for outputting the first prediction information, which enables the process of outputting one or more candidates for the first inter-frame prediction information from the inter-frame prediction information of one or more third blocks in the vicinity of the second block that is the decoding object, inside the frame that is the decoding object;

an output module of the second prediction information, which provides the process of outputting the candidate for the second inter prediction information from the inter prediction information of the fourth block, which is in a position identical to the position of the second block that is the object of decoding, or in its vicinity, inside a frame other than the frame, decoding subject;

a decoding module that provides decoding of an index indicative of inter prediction information used for inter prediction of a second block to be decoded;

a candidate list building module that provides a candidate list for prediction information containing a candidate for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this derived candidate for the first inter-frame prediction information is added, and in the case when a candidate for the second inter-frame prediction information, respectively, this derived candidate for the second inter-frame prediction information is added; and

a selection module that provides a candidate selection for inter prediction information used for inter prediction of the second block that is the decoding object indicated by the index from one or more prediction information candidates in the prediction information candidate list, wherein

in the separation mode, where the first block is divided into the left block and the right block, located horizontally, with a ratio of 1: 1, 1: 3 or 3: 1, in the case when the second block, which is the object of decoding, is the right block, the output unit of the first information prediction performs the process of outputting the candidate to the first information inter-frame prediction without accessing the encoding information of the fifth block adjacent to the left side of the second block, and

in the split mode, where the first block is divided into a left block and a right block located horizontally with a ratio of 1: 1, 1: 3 or 3: 1, the block for outputting the second prediction information performs the process of outputting the candidate to the second inter-frame prediction information based on the reference index the candidate for the second inter prediction information by assigning a default value to the reference index value without reference to the encoding information of the fifth block contained in a block identical to the first block containing the second block, yayuschiysya object coding.

A moving image coding apparatus that divides a first block obtained by dividing each frame into one or more second blocks, and encodes a moving image using inter-frame prediction, comprising:

an output unit of the first prediction information that performs the process of outputting one or more candidates for the first inter prediction information from the inter prediction information of one or more third blocks adjacent to the second encoding object block within the encoding object frame;

an output unit of the second prediction information, which performs the process of outputting the candidate for the second inter prediction information from the inter prediction information of the fourth block, which is in a position identical to the position of the second block being the encoding, or in its vicinity, inside a frame other than the frame being object of coding;

block for constructing a list of candidates that generates a list of candidates for prediction information containing a candidate for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this derived candidate for the first inter-frame prediction information is added, and in the case when the candidate is displayed to the second inter prediction information, respectively, this inferred candidate for the second inter prediction information is added;

a selection unit that selects a candidate for inter prediction information used for inter prediction of the second block to be encoded from one or more prediction information candidates in the prediction information candidate list, and determines an index that indicates inter prediction information; and

an encoding unit that encodes an index indicating inter-prediction information used for inter-prediction of a second block being an encoding, wherein

in the separation mode, in which the first block is divided into the upper block and the lower block, located vertically, in a ratio of 1: 1, 1: 3 or 3: 1, in the case when the second block, which is the object of encoding, is the lower block, the output block of the first the prediction information, the candidate outputting process on the first inter prediction information is performed without reference to the encoding information of the fifth block adjacent to the upper side of the second block, and

in the separation mode, in which the first block is divided into the upper block and the lower block vertically in the ratio 1: 1, 1: 3 or 3: 1, the block for outputting the second prediction information performs the process of outputting the candidate to the second inter-frame prediction information based on the reference the index of the candidate for the second inter prediction information by assigning the value of the reference index to the default value without accessing the encoding information of the fifth block contained in a block identical to the first block including Ora block being an object of coding.

A moving image coding method that divides a first block obtained by dividing each frame into one or more second blocks, and encodes a moving image using inter-frame prediction, comprising:

a step in which the process of deriving one or more candidates for the first inter-frame prediction information from the inter-frame prediction information of one or more third blocks adjacent to the second block that is the object of encoding, inside the frame that is the object of encoding;

a step in which the process of deriving the candidate for the second inter-prediction information from the inter-prediction information of the fourth block, which is in a position identical to the position of the second block that is the encoding object, or in its vicinity, inside the frame different from the frame that is the encoding object;

the step of constructing a list of candidates for prediction information containing a candidate for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this output candidate for the first inter-frame prediction information is added, and in the case when the candidate for second inter prediction information, respectively, this inferred candidate for the second inter prediction information is added;

a step in which a candidate for inter-prediction information used for inter-prediction of the second block to be encoded is selected from one or more prediction information candidates in the prediction information candidate list, and an index indicating inter-prediction information is determined; and

a step at which an index is encoded indicating inter-prediction information used for inter-prediction of the second block to be encoded, wherein

in separation mode, in which the first block is divided into the upper block and the lower block vertically in the ratio 1: 1, 1: 3 or 3: 1, in the case when the second block, which is the object of encoding, is the lower block, at the execution stage a process for deriving one or more candidates for the first inter-frame prediction information, a process for outputting a candidate for the first inter-frame prediction information without accessing encoding information of a fifth block adjacent to the upper side of the second block, and

in the separation mode, in which the first block is divided into the upper block and the lower block located vertically in the ratio 1: 1, 1: 3 or 3: 1, at the stage of the process of outputting the candidate to the second inter-frame prediction information, the process of outputting the candidate to the second inter prediction information based on a reference index of a candidate for the second inter prediction information by assigning a default value to the reference index value without reference to encoding information of the fifth block contained in a block identical to the first block including a second block that is an encoding object.

A long-term computer-readable recording medium on which a moving image encoding program is recorded, executed by a computer, which divides the first block obtained by dividing each frame into one or more second blocks, and encodes the moving image using inter-frame prediction, where this program contains:

an output unit of the first prediction information that performs the process of outputting one or more candidates for the first inter prediction information from the inter prediction information of one or more third blocks adjacent to the second block that is the encoding object, inside the frame that is the encoding object;

an output unit of the second prediction information that performs the process of deriving a candidate for the second inter prediction information from the inter prediction information of the fourth block, which is in a position identical to the position of the second block being the encoding, or in its vicinity, inside a frame other than the frame being object of coding;

a candidate list building module that generates a list of candidates for prediction information containing a candidate for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this output candidate for the first inter-frame prediction information is added, and in the case when the candidate is displayed to the second inter prediction information, respectively, this inferred candidate for the second inter prediction information is added;

a selection module that selects a candidate for inter prediction information used for inter prediction of the second block to be encoded from one or more prediction information candidates in the prediction information candidate list and determines an index that indicates inter prediction information; and

an encoding module that encodes an index indicative of inter prediction information used for inter prediction of a second block being an encoding, wherein

in the split mode, in which the first block is divided into the upper block and the lower block, located vertically, in the ratio 1: 1, 1: 3 or 3: 1, in the case when the second block, which is the object of encoding, is the lower block, the output module of the first the prediction information, the candidate outputting process on the first inter prediction information is performed without reference to the encoding information of the fifth block adjacent to the upper side of the second block, and

in the separation mode, in which the first block is divided into the upper block and the lower block arranged vertically in the ratio 1: 1, 1: 3 or 3: 1, the output module of the second prediction information performs the process of outputting the candidate to the second inter-frame prediction information based on the reference the index of the candidate for the second inter prediction information by assigning the value of the reference index to the default value without accessing the encoding information of the fifth block contained in a block identical to the first block including the second block, which is the object of encoding.

DESCRIPTION OF REFERENCE NUMBERS

101 — frame memory, 102 — motion vector calculation unit, 103 — motion vector difference calculation unit, 104 — inter prediction information output unit, 105 — motion compensation prediction unit, 106 — intraframe prediction unit, 107 — prediction method determination unit, 108 — residual signal generating unit, 109 — orthogonal transform / quantization unit, 110 — first bit stream generating unit, 111 — second bit stream generating unit, 112 — multiplexing unit, 130 — candidate generation unit spatial merge, 131 - time merge candidate indexes output unit, 132 - time merge candidate generation unit, 133 - merge candidate registration unit, 134 - merge candidate equality determination unit, 135 - merge candidate replenishment unit, 136 - encoding information selection unit, 201 - separation unit, 202 - decoding unit of the first bit stream, 203 - decoding unit of the second bit stream, 204 - motion vector calculation unit, 205 - inter prediction information output unit, 206 - pre motion compensation indications, 207 — intraframe prediction block, 208 — dequantization / inverse orthogonal transform block, 209 — convolution unit of decoded frame signals, 210 — encoding information storage memory, 211 — decoded frame memory, 230 — spatial merge candidate generation unit, 231 - a unit for outputting reference indices of candidates for a merger in time, 232 - a unit for generating candidates for a merger in time, 233 - a unit for registering candidates for a merger, 234 - a unit for determining the equality of candidates for a merger s 235 - refill unit candidates for merger, and 236 - a selection unit encoding information.

INDUSTRIAL APPLICABILITY

The present invention is applicable to motion picture coding technology using motion compensation prediction.

Claims (24)

1. A moving image coding apparatus that divides a first block obtained by dividing each frame into one or more second blocks and encodes a moving image using inter-frame prediction, comprising: an output unit of the first prediction information that performs the process of outputting one or more candidates for the first inter prediction information from the inter prediction information of one or more third blocks adjacent to the second encoding object block within the encoding object frame; an output unit of the second prediction information, which performs the process of outputting the candidate for the second inter prediction information from the inter prediction information of the fourth block, which is in a position identical to the position of the second block being the encoding, or in its vicinity, inside a frame other than the frame being object of coding; block for constructing a list of candidates that generates a list of candidates for prediction information containing a candidate for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this derived candidate for the first inter-frame prediction information is added, and in the case when a candidate is displayed to the second inter prediction information, respectively, this inferred candidate for the second inter prediction information is added; a selection unit that selects a candidate for inter prediction information used for inter prediction of a second block to be encoded from one or more prediction information candidates in the prediction information candidate list and determines an index that indicates inter prediction information; and an encoding unit that encodes an index indicating inter-prediction information used for inter-prediction of a second block being an encoding, wherein in the separation mode, in which the first block is divided into the upper block and the lower block, located vertically, in a ratio of 1: 1, 1: 3 or 3: 1, in the case when the second block, which is the object of encoding, is the lower block, the output block of the first the prediction information, the candidate outputting process on the first inter prediction information is performed without reference to the encoding information of the fifth block adjacent to the upper side of the second block, and in the separation mode, in which the first block is divided into the upper block and the lower block vertically in the ratio 1: 1, 1: 3 or 3: 1, the block for outputting the second prediction information performs the process of outputting the candidate to the second inter-frame prediction information based on the reference the index of the candidate for the second inter prediction information by assigning the value of the reference index to the default value without accessing the encoding information of the fifth block contained in a block identical to the first block including Ora block being an object of coding. 2. A method for encoding a moving image that divides the first block obtained by dividing each frame into one or more second blocks and encodes the moving image using inter-frame prediction, comprising: a step in which the process of deriving one or more candidates for the first inter-frame prediction information from the inter-frame prediction information of one or more third blocks adjacent to the second block that is the object of encoding, inside the frame that is the object of encoding; a step in which the process of deriving the candidate for the second inter-prediction information from the inter-prediction information of the fourth block, which is in a position identical to the position of the second block that is the encoding object, or in its vicinity, inside the frame different from the frame that is the encoding object; the step of constructing a list of candidates for prediction information containing a candidate for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this derived candidate for the first inter-frame prediction information is added, and in the case when the candidate for second inter prediction information, respectively, this inferred candidate for the second inter prediction information is added; a step in which a candidate for inter-prediction information used for inter-prediction of the second block to be encoded is selected from one or more prediction information candidates in the prediction information candidate list, and an index indicating inter-prediction information is determined; and a step at which an index is encoded indicating inter-prediction information used for inter-prediction of the second block to be encoded, wherein in separation mode, in which the first block is divided into the upper block and the lower block vertically in the ratio 1: 1, 1: 3 or 3: 1, in the case when the second block, which is the object of encoding, is the lower block, at the execution stage a process for deriving one or more candidates for the first inter-frame prediction information, a process for outputting a candidate for the first inter-frame prediction information without accessing encoding information of a fifth block adjacent to the upper side of the second block, and in the separation mode, in which the first block is divided into the upper block and the lower block located vertically in the ratio 1: 1, 1: 3 or 3: 1, at the stage of the process of outputting the candidate to the second inter-frame prediction information, the process of outputting the candidate to the second inter prediction information based on a reference index of a candidate for the second inter prediction information by assigning a default value to the reference index value without reference to encoding information of the fifth block contained in a block identical to the first block including a second block that is an encoding object. 3. A long-term computer-readable recording medium on which a moving image coding program is recorded, executed by a computer, which divides the first block obtained by dividing each frame into one or more second blocks and encodes the moving image using inter-frame prediction, where this program contains: an output unit of the first prediction information that performs the process of outputting one or more candidates for the first inter prediction information from the inter prediction information of one or more third blocks adjacent to the second block that is the encoding object, inside the frame that is the encoding object; an output unit of the second prediction information that performs the process of deriving a candidate for the second inter prediction information from the inter prediction information of the fourth block, which is in a position identical to the position of the second block being the encoding, or in its vicinity, inside a frame other than the frame being object of coding; a candidate list building module that generates a list of candidates for prediction information containing a candidate for prediction information, to which, when a candidate for the first inter-frame prediction information is output, this output candidate for the first inter-frame prediction information is added, and in the case when the candidate is displayed to the second inter prediction information, respectively, this inferred candidate for the second inter prediction information is added; a selection module that selects a candidate for inter prediction information used for inter prediction of the second block to be encoded from one or more prediction information candidates in the prediction information candidate list and determines an index that indicates inter prediction information; and an encoding module that encodes an index indicative of inter prediction information used for inter prediction of a second block being an encoding, wherein in the split mode, in which the first block is divided into the upper block and the lower block, located vertically, in the ratio 1: 1, 1: 3 or 3: 1, in the case when the second block, which is the object of encoding, is the lower block, the output module of the first the prediction information, the candidate outputting process on the first inter prediction information is performed without reference to the encoding information of the fifth block adjacent to the upper side of the second block, and in the separation mode, in which the first block is divided into the upper block and the lower block arranged vertically in the ratio 1: 1, 1: 3 or 3: 1, the output module of the second prediction information performs the process of outputting the candidate to the second inter-frame prediction information based on the reference the index of the candidate for the second inter prediction information by assigning the value of the reference index to the default value without accessing the encoding information of the fifth block contained in a block identical to the first block including the second block, which is the object of encoding.

Images