WO2018214693A1

WO2018214693A1 - Video communication system detection method and apparatus, storage medium and computer device

Info

Publication number: WO2018214693A1
Application number: PCT/CN2018/084619
Authority: WO
Inventors: 关翔宇; 王艳儒; 龚琼
Original assignee: 中兴通讯股份有限公司
Priority date: 2017-05-22
Filing date: 2018-04-26
Publication date: 2018-11-29
Also published as: CN108933935B; CN108933935A

Abstract

The present disclosure relates to a video communication system detection method and apparatus, a storage medium and a computer device. The method comprises: acquiring a video to be detected generated by a video communication system according to a sample video; extracting a plurality of pictures to be detected from the video to be detected; identifying frame numbers comprised in each of the pictures to be detected; acquiring a sample picture corresponding to each of the frame numbers, wherein the sample picture is a frame picture extracted from the sample video; calculating a first similarity between each of the pictures to be detected and the corresponding sample picture; and determining, according to the first similarity between each of the pictures to be detected and the corresponding sample picture, whether the video communication system has a video processing problem.

Description

Method, device, storage medium and computer device for detecting video communication system

Technical field

The present disclosure relates to the field of multimedia technologies, and in particular, to a method, an apparatus, a storage medium, and a computer device for detecting a video communication system.

Background technique

With the development of Internet technology, video communication technology has been widely used in video telephony, interactive television, video conferencing, electronic surveillance and remote video education. In each stage of research and development, production and quality evaluation of the video communication system, the video processed by the video communication system is detected, and the image is processed according to the detected video, such as low color reproduction degree of the video image. The video communication system is perfected by freezing, image flower screen, black screen and blue screen.

However, the detection of the traditional video communication system is to observe and subjectively judge the video to be tested by the professional, and the video processing problem existing in the video communication system is obtained. This method consumes a lot of manpower and time, and is prone to missed or Problems such as nuances are not detected, resulting in low detection efficiency of video communication systems.

Summary of the invention

The following is an overview of the topics detailed in this document. This Summary is not intended to limit the scope of the claims.

Embodiments of the present disclosure provide a method, an apparatus, a storage medium, and a computer device for detecting a video processing application.

A method for detecting a video communication system, comprising:

Obtaining a video to be tested generated by the video communication system according to the sample video;

Extracting a plurality of pictures to be tested from the video to be tested;

Identifying a frame number included in each picture to be tested;

Obtaining a sample picture corresponding to each frame number, where the sample picture is a frame picture extracted from the sample video;

Calculating a first similarity between each picture to be tested and a corresponding sample picture;

Determining whether the video communication system has a video processing problem according to the first similarity between each picture to be tested and the corresponding sample picture.

A detecting device for a video communication system, comprising:

The video acquisition module to be tested is configured to acquire a video to be tested generated by the video communication system according to the sample video;

The picture extraction module to be tested is configured to extract a plurality of pictures to be tested from the video to be tested;

a frame number identification module configured to identify a frame number included in each picture to be tested;

a sample picture obtaining module, configured to acquire a sample picture corresponding to each frame serial number, where the sample picture is a frame picture extracted from the sample video;

a similarity calculation module, configured to calculate a first similarity between each picture to be tested and a corresponding sample picture;

The video processing problem determining module is configured to determine whether the video communication system has a video processing problem according to the first similarity between each picture to be tested and the corresponding sample picture.

A computer readable storage medium having stored thereon a computer program, wherein the program is implemented by a processor to implement a method of detecting the video communication system.

A computer device comprising a memory, a processor, and a computer program stored on the memory and operable on the processor, wherein the processor performs the detection method of the video communication system when the program is executed.

By using the detection method, the device, the storage medium, and the computer device of the video communication system, after extracting a plurality of pictures to be tested from the video to be tested, and identifying the frame number included in each picture to be tested, according to the picture to be tested The frame number in the frame obtains the sample picture corresponding to the picture to be tested, and the picture to be tested and the sample picture are associated by the frame number, which improves the accuracy of finding the corresponding sample picture, and saves the time for finding the picture. Determining whether there is a video processing problem in the video communication system by calculating a first similarity between each picture to be tested and a corresponding sample picture, avoiding missing the picture to be tested with quality problems, and calculating the similarity of the picture, The accuracy of the quality detection of the video image to be tested is improved, and the detection efficiency of the video communication system is improved.

Other aspects will be apparent upon reading and understanding the drawings and detailed description.

DRAWINGS

1 is an application scenario diagram of a detection method of a video communication system in an embodiment;

2 is a diagram showing the internal structure of a video communication system detecting device in an embodiment;

3 is a flow chart of a method for detecting a video communication system in an embodiment;

4 is a flow chart of a method for detecting a video communication system in another embodiment;

FIG. 5 is a flowchart of a method for detecting a video communication system in still another embodiment; FIG.

6 is a flow chart of a method for detecting a video communication system in still another embodiment;

Figure 7 is a block diagram showing the structure of a detecting apparatus of a video communication system in an embodiment;

Figure 8 is a block diagram showing the structure of a detecting apparatus of a video communication system in another embodiment.

detailed description

The present disclosure will be further described in detail below in conjunction with the accompanying drawings and embodiments. The specific embodiments described herein are merely illustrative of the disclosure and are not intended to limit the disclosure.

The detection method of the video communication system provided by the embodiment of the present disclosure can be applied to an application environment as shown in FIG. 1. As shown in FIG. 1, the video communication system detecting device 110 is connected to the video communication system 120. The video communication system 120 includes a first terminal 122 and a second terminal 124. The video communication system 120 can be a videophone, an interactive television, or a video. Video communication systems used in application scenarios such as conferences, electronic surveillance, and remote video education. The first terminal 122 and the second terminal 124 can perform data transmission via the network. In the video communication system 120, the first terminal 122 can serve as a transmitting terminal for sample video, and the second video 124 can serve as a receiving terminal for sample video. After receiving the sample video sent by the video communication system detecting device 110 for detecting the video communication system, the first terminal 122 encodes the sample video and transmits the encoded sample video to the second terminal 124. When receiving the encoded sample video, the second terminal 124 may decode and generate a corresponding video to be tested according to a corresponding decoding manner. Among them, codec standards include but are not limited to H264, H264HP, H265, and the like. The video communication system detecting device 110 can acquire the detected video and detect it. It can be understood that, in other scenarios, the first terminal 122 can also serve as the receiving terminal of the sample video, the second terminal 124 serves as the transmitting terminal of the sample video, and the second terminal 124 encodes the sample video and sends the sample video to the first terminal 122. Decoding is performed to generate a corresponding video to be tested.

In one embodiment, video communication system detection device 110 and video communication system 120 may be on the same terminal. For example, the terminal may acquire a sample piece source to generate a sample video, and through the built-in video communication application of the terminal, the sample video may be encoded, transmitted, and decoded to generate a video to be tested. For example, the videophone software to be detected can be downloaded on the terminal, and two accounts are logged in. One of the accounts is used as the first terminal 122, and the other account is used as the second terminal 124. The terminal can obtain the first terminal 122. The sample video sent and the video to be tested received by the second terminal 124 analyze the sample video and the video to be tested, thereby detecting the videophone software.

In one embodiment, as shown in FIG. 2, an internal structure diagram of a video communication system detection device in one embodiment. The communication system detecting device 110 includes a processor connected through a system bus, a nonvolatile storage medium, an internal memory, and a display screen. The processor of the video communication system detecting device is used to provide calculation and control capabilities to support the operation of the entire server. The non-volatile storage medium of the video communication system detecting device stores an operating system and computer executable instructions executable by the processor for implementing a video communication system provided by the following embodiments Detection method. The internal memory provides a cached operating environment for operating systems and computer executable instructions in a non-volatile storage medium. The network interface is configured to communicate with an external terminal to implement data transmission, such as sending sample video to the first terminal and acquiring the video to be tested from the second terminal. The display can be used to display video images.

It will be understood by those skilled in the art that the structure shown in FIG. 2 is only a block diagram of a partial structure related to the solution of the present disclosure, and does not constitute a limitation of a mobile terminal to which the present disclosure is applied, and a specific video communication system. The detection device may include more or fewer components than shown in the figures, or some components may be combined, or have different component arrangements. For example, the video communication system detecting device may further include a camera for scanning the visible area to generate a sample slice source.

In an embodiment, as shown in FIG. 3, a method for detecting a video communication system is provided. The method is applicable to the application environment shown in FIG. 1, and includes:

Step S302: Acquire a video to be tested generated by the video communication system according to the sample video.

In this embodiment, the video communication system is a communication system for transmitting video information, and through the support of multimedia technology and network communication technology, provides a face-to-face communication mode for people in different regions. The communication system may be a wireless communication system that transmits electromagnetic waves in free space, or a wired communication system that transmits information in a guiding medium. For example, the video communication system may be, but is not limited to, a video telephone system, an interactive television system, a video conference system, an electronic monitoring system, and a remote video education system. The sample video refers to the video used to detect the video communication system. For example, each frame picture of the sample video includes a frame number, and correspondingly, each frame picture of the video to be tested generated by the video communication system according to the sample video also includes a frame number. After the sample video is encoded, the transmitting end of the video communication system may transmit the sample video to one or more receiving ends by using a network transmission, and the one or more receiving ends may encode the encoded according to a corresponding decoding manner. The sample video is decoded to generate a corresponding video to be tested, and the video to be tested can be obtained for the next detection.

In one embodiment, the video communication system may be a video conference system, where the video conference system refers to individuals or groups of two or more different places, and transmits voice, video, and file data through transmission lines and multimedia devices. A system device that enables instant and interactive communication to achieve the purpose of the meeting. The conference video of the first conference scene is sent to the display screen of the second conference scene for display by the video conference system, and the next step is detected by acquiring the video displayed on the display screen of the second conference scene.

Step S304, extracting a plurality of pictures to be tested from the video to be tested.

In this embodiment, the picture to be tested is a frame picture in the video to be tested. Each frame image may be extracted from the video to be tested as a picture to be tested, or a part of the frame picture may be extracted from the video to be tested as a picture to be tested, for example, a frame picture is extracted from the video to be tested according to a preset time interval. Measure the picture. For example, the preset time interval is in the order of seconds. For example, the frame picture is extracted from the video to be tested as the picture to be tested every 1 or 2 seconds. It is also possible to preset the number of pictures to be tested to avoid missing image problems that occur in a short period of time, including but not limited to instantaneous blooming. For example, if the number of pictures to be tested obtained at intervals of 2 seconds is smaller than the number of preset pictures to be tested, the time interval can be shortened to 1 second to obtain more pictures to be tested.

In this embodiment, by extracting a frame picture from the video to be tested according to the preset time interval, the resource is saved as a picture to be tested, and the preset time interval is a second level to prevent the occurrence of the missing video, and the preset picture to be tested is preset. The number is increased to improve the accuracy of the video analysis.

Step S306, identifying a frame number included in each picture to be tested.

In this embodiment, the frame number refers to the number of the video picture used to identify the frame picture, and the frame number may be a combination of one or more of numbers, letters, and punctuation. The frame number is not repeatable, and each frame number corresponds to a unique frame picture.

For example, if the frame picture in the sample video includes the frame number, the corresponding frame picture in the video to be tested generated by the video communication system also includes the same frame number. In the case that the video communication system does not have a video processing problem, the frame picture in the sample video and the frame picture in the video to be tested have a one-to-one correspondence, and each frame number may correspond to a frame picture in the video and one to be tested. The frame picture in the video, the frame number can be used to associate the sample video with the frame picture in the video to be tested, and can identify the frame picture in the corresponding sample video by identifying the frame number included in the picture to be tested.

The frame number included in the picture to be tested can be directly identified by image recognition technology. For example, the frame number in the picture to be tested may be segmented by a threshold segmentation method, a region extraction method, a texture image segmentation method, etc., and the characters in the frame number are identified one by one. The frame number included in all the frame pictures in the sample video may be stored as a frame number library, and after the frame number included in the picture to be tested is segmented, the frame number of the divided frame is matched with the frame number in the frame number library to determine The frame number contained in the picture to be tested.

In one embodiment, the time taken to identify the frame number in the picture to be tested may be on the order of milliseconds. The frame number recognition model can also be trained through the neural network to increase the recognition accuracy rate to over 99%, thereby improving the accuracy of the detection of the video communication system and reducing the time required for the detection.

Step S308, acquiring a sample picture corresponding to each frame serial number, where the sample picture is a frame picture extracted from the sample video.

In this embodiment, the sample picture is a frame picture in the sample video, and each sample picture is converted by the video communication system to generate a corresponding picture to be tested, and the frame number included in the sample picture and the frame number included in the picture to be tested are also corresponding. A sample picture uniquely corresponding to the frame number can be queried according to the frame number of the video to be tested. For example, if the frame number in the picture to be tested is 12345, the sample picture with the frame number 12345 in the sample video is obtained.

Step S310, calculating a first similarity between each picture to be tested and a corresponding sample picture.

In this embodiment, the first similarity is the similarity between each picture to be tested and the corresponding sample picture calculated by the picture comparison algorithm. The image comparison algorithm may be to compare the feature values of each corresponding pixel of the two images, for example, RGB (Red, Green, Blue, three primary colors, by which the value of the pixel can be expressed), thereby obtaining two Image similarity algorithm. It is also possible to obtain an algorithm of two picture similarities by matching one or more combinations of contents, features, structures, relationships, textures, and gradations of two pictures. For example, a histogram improvement algorithm for two picture similarities is obtained by a gray histogram.

In an embodiment, after calculating a first similarity between each picture to be tested and a corresponding sample picture, determining whether the first similarity is lower than a first threshold. The first threshold is a similarity threshold for determining whether the picture to be tested has a quality problem, for example, 90% or 95%. If so, it is determined that there is a quality problem with the image to be tested. For example, when the first similarity between the picture to be tested and the corresponding sample picture is 89%, and the first threshold is 90%, it is determined that the picture to be tested has a quality problem.

In one embodiment, a plurality of image comparison algorithms may be preset, and a first similarity between each of the to-be-tested pictures and the sample pictures is calculated by a plurality of image comparison algorithms. For example, after the first similarity calculated by the first image comparison algorithm is lower than the first threshold, the similarity between each picture to be tested and the sample picture is calculated by the second image comparison algorithm to perform verification. If the similarity calculated by the second image comparison algorithm is still lower than the first threshold, determining that the picture to be tested has a quality problem; if the similarity calculated by the second image comparison algorithm is higher than the first threshold, determining The two pictures are identical, and there is no quality problem in the picture to be tested, and the similarity higher than the first threshold is taken as the first similarity.

Step S312, determining whether there is a video processing problem in the video communication system according to the first similarity between each picture to be tested and the corresponding sample picture.

In this embodiment, a first similarity may be calculated between each picture to be tested and a corresponding sample picture, and the first similarity between each picture to be tested and the corresponding sample picture is summarized to be analyzed and determined. Whether there is a video processing problem in the video communication system. Among them, the video processing problem includes a combination of one or more of a blue screen, a black screen, a flower screen, a color cast, and the like. For example, by analyzing a picture to be tested corresponding to the first similarity lower than the first threshold by using a preset analysis algorithm, an image problem existing in the picture to be tested may be obtained, and all image problems existing in the picture to be tested are summarized. It is determined whether the video communication system has a problem of a combination of one or more of a blue screen, a black screen, a flower screen, a color cast, and the like.

The above-mentioned detection method of the video communication system, by extracting a plurality of pictures to be tested from the video to be tested, identifying the frame number included in each picture to be tested, and acquiring the sample picture corresponding to the picture to be tested according to the frame number, and passing the frame number Correlating the to-be-tested picture and the sample picture improves the accuracy of finding the corresponding sample picture, and determining whether the video communication system has a video processing problem by calculating the first similarity between each picture to be tested and the corresponding sample picture, and avoiding The missing picture with quality problems is omitted, which saves the detection time of the video communication system and improves the detection efficiency of the video communication system.

In an embodiment, as shown in FIG. 4, before acquiring the video to be tested generated by the video communication system according to the sample video, the method further includes:

Step S402, acquiring a sample slice source for detecting a video communication system.

In this embodiment, the sample slice source is the most original video for detecting a video communication system, and the sample slice source may be an existing video, may also be a video generated by a camera scan, and may also be displayed on a desktop window. Picture. The sample slice source of the corresponding category may be selected according to the application scenario of the video communication system. For example, when the detected video communication system is a video conference system, the video with the scene state of the conference may be selected as a sample source. For another example, when the detected video communication system is an electronic surveillance video, in addition to selecting a sample source of the daytime scene, a sample source in the night scene may also be selected.

In one embodiment, the camera can be invoked to scan the viewable area, generate a video at a predetermined frame rate, and present it on the display in real time. For the original video that is presented in real time, the frame picture may be collected according to a sampling frequency less than or equal to the frame rate, and the collected frame picture set is used as the sample piece source to be processed.

Step S404, generating a sample video by adding a frame number to each frame picture of the sample piece source.

In this embodiment, the sample video refers to a video used for importing into a video communication system for detection, and the sample video can be generated by adding a frame number to each frame picture of the sample slice source. The method of adding the frame number may be to superimpose a frame number on each frame picture of the sample piece source to identify the frame picture.

Step S406, extracting a frame picture in the sample video to generate a sample picture.

In one embodiment, extracting a frame picture in the sample video and generating a sample picture includes: saving each frame picture of the sample video as a sample picture, acquiring a frame number included in each sample picture, and naming the corresponding frame number according to the frame number Sample image. Wherein, the frame number included in the sample picture can be identified by the image recognition technology, and the corresponding sample picture is named as the serial number.

In an embodiment, step S404 and step S406 can be performed simultaneously. When the frame number is added to each frame picture of the sample slice source, the frame picture is saved, and the frame picture is named as the corresponding frame number, and the frame number is omitted. The step of identifying the frame number contained in the sample picture can save time in generating the sample picture.

In this embodiment, by naming the sample picture as the corresponding frame number, the time for finding the sample picture is reduced, and the accuracy of finding the sample picture is improved.

In an embodiment, determining, according to the first similarity between each picture to be tested and the corresponding sample picture, whether the video communication system has a video processing problem, comprising: waiting according to the first similarity lower than the first threshold The number of pictures is determined to determine if there is a video processing problem in the video communication system. For example, a quantity threshold may be preset to determine whether the number of pictures to be tested corresponding to the first similarity lower than the first threshold is higher than the quantity threshold. If yes, it is determined that the video communication system has a video processing problem. The quantity threshold may be a fixed value, or a dynamic quantity threshold may be obtained by calculating a percentage of the total number of pictures to be tested.

In an embodiment of determining whether there is a video processing problem in the video communication system, as shown in FIG. 5, in step S502, determining whether the video communication system has video processing according to the number of pictures to be tested corresponding to the first similarity lower than the first threshold. After the problem, it also includes:

Step S504, when it is determined that there is a video processing problem in the video communication system, calculating a second similarity between each deviation of the to-be-tested picture and the preset deviation picture, and the deviation of the to-be-tested picture is a first similarity lower than the first threshold. Corresponding picture to be tested.

In this embodiment, the deviation picture to be tested refers to the picture to be tested corresponding to the first similarity lower than the first threshold, and the specific video processing problem existing in the video system to be tested can be determined according to the deviation picture to be tested. A deviation picture refers to a picture with quality problems, including but not limited to a blue screen picture and a black screen picture, which can be used to detect whether the deviation of the picture to be tested has the same problem, such as a blue screen or a black screen. The second similarity is the similarity between each of the deviation test images calculated by the picture comparison algorithm and the preset deviation picture. Among them, the picture comparison algorithm can be the same as the way of calculating the first similarity.

In one embodiment, the deviation picture may be multiple, and the order of calculating the deviation of the picture to be tested and each of the deviation pictures is not limited, and when the second similarity between the deviation of the picture to be tested and one of the deviation pictures is detected is higher than When the second threshold is used, the second similarity between the deviation test picture and other deviation pictures is not calculated. For example, the deviation picture is a black screen picture and a blue screen picture. If it is detected that the second similarity between the deviation picture to be tested and the black screen picture is higher than the second threshold, it is not necessary to calculate the second similarity between the deviation picture to be tested and the blue screen picture. If the second similarity between the deviation of the to-be-tested picture and the black-screen picture is lower than the second threshold, the second similarity between the deviation of the picture to be tested and the blue-screen picture is calculated.

Step S506, determining whether the second similarity is higher than the second threshold.

In this embodiment, the second threshold is a similarity threshold for determining whether the deviation of the picture to be tested has a deviation picture quality problem. When the second similarity is higher than the second threshold, step S508 is performed, and when the second similarity is lower than the second threshold, step S510 is performed.

Step S508, determining that the video processing problem existing in the video communication system includes a blue screen or a black screen.

In this embodiment, the deviation picture includes, but is not limited to, a blue screen and a black screen. When the second similarity is higher than the second threshold, it is determined that the deviation of the picture to be tested has the same quality problem as the deviation picture. Wherein, as long as the similarity between the deviation picture to be tested and the blue screen picture or the black screen picture is higher than the second threshold, it is determined that the deviation picture has a corresponding deviation picture. For example, if the second similarity between the deviation picture to be tested and the black screen picture is higher than the second threshold, it is determined that the deviation similar picture is consistent with the black screen picture, and the video processing problem includes a black screen.

In step S510, it is determined that the video processing problem existing in the video communication system includes a problem of blooming or color cast.

In this embodiment, when the second similarity is lower than the second threshold, it is determined that the deviation of the to-be-tested picture and the deviation picture are inconsistent, and the video processing problem includes, but is not limited to, a combination of one or more of a flower screen or a color cast.

In an embodiment, after determining the image quality problem of the deviation of the to-be-tested image by the foregoing method, the method further includes: classifying and storing the deviation to-be-measured image. For example, all the deviations to be tested can be classified according to categories such as black screen, blue screen, flower screen, color cast, and the like, and all the deviations to be tested are saved according to the corresponding categories.

In one embodiment, the deviation of the to-be-tested picture is classified and saved, and the method further includes: obtaining a positioning identifier of the deviation of the to-be-tested picture in the video to be tested, and naming all the deviation-to-measure pictures as the corresponding positioning identifier. The location identifier is an identifier that can locate the position of the to-be-measured picture in the video to be tested, and the location identifier includes, but is not limited to, a progress time or a percentage of progress of the deviation of the to-be-tested picture in the video to be tested. In this embodiment, by naming the deviation picture to be detected as the positioning identifier, the accuracy of finding the sample picture corresponding to the position of the sample video is improved, thereby improving the efficiency of further analyzing and confirming the problem of the deviation of the picture to be tested.

In an embodiment, after determining whether the video communication system has a video processing problem according to the first similarity between each picture to be tested and the corresponding sample picture, the method includes: determining, corresponding to the first similarity that is higher than the first threshold, corresponding to the first similarity Whether the frame number included in the picture to be tested is consistent with the frame number included in the adjacent picture to be tested, and if so, it is determined that the video processing problem existing in the video communication system includes the problem of image freezing or image jamming. In this embodiment, the image freeze refers to that the frame numbers of all the pictures to be tested in the video to be tested are consistent, and the image card is that the frame numbers of the pictures to be tested corresponding to a video in the video to be tested are consistent. The frame numbers of the pictures to be tested corresponding to the subsequent videos are inconsistent. The image to be tested corresponding to the first similarity that is higher than the first threshold does not have an image quality problem. If it is detected that the frame to be tested is consistent with the frame number of the adjacent picture to be tested, the video processing of the video communication system is determined. Problems include image freeze or image jams. It is also possible to detect whether the frame number of the picture to be tested corresponding to the first similarity lower than the first threshold is consistent with the frame number included in the adjacent picture to be tested, and if so, the video processing problem existing in the video communication system includes image quality. Problems as well as image freeze or image jams.

In an embodiment, it is possible to detect whether there are any pictures to be tested with the same frame number in all the pictures to be tested. Since the frame number of the sample picture in the sample video is a non-repeating character string, if the same picture number is detected, the picture to be tested is detected. Then, it is determined that the video processing problems existing in the video communication system include image freeze or image jamming.

In an embodiment, after identifying the frame number of each picture to be tested, all the frame numbers may be summarized in the order of extraction time. Compare whether all the frame numbers of the video to be tested are consistent with all the frame numbers of the corresponding sample videos summarized in the same manner. If not, it is determined that the video processing problems existing in the video communication system include image freeze or image jamming.

In an embodiment, acquiring the sample picture corresponding to each frame sequence includes: searching for a sample picture having the same resolution according to a resolution of the picture to be tested, and acquiring each picture to be tested in the sample picture having the same resolution. The sample picture corresponding to the frame number. Among them, the resolution is a value used to represent the image precision, including but not limited to 4K, 2K, 1080K, 720P, and the like. The resolution of a video is the number of pixels contained in a unit of an inch of a video image. The more pixels, the finer the picture. The resolution of the sample video refers to the resolution of the sample picture in the sample video, and the resolution of the video to be tested refers to the resolution of the picture to be tested in the video to be tested.

For example, the resolution of the sample video used to detect the video communication system is the same as the resolution of the video to be tested generated by the video communication system. After finding the sample picture corresponding to the same resolution according to the resolution of the picture to be tested in the video to be tested, the sample picture corresponding to the frame number of each picture to be tested is obtained in the found sample picture. In this embodiment, by searching the sample picture corresponding to the frame number of each picture to be tested in the sample picture of the corresponding resolution, the difficulty of finding the sample picture is reduced, and the efficiency of acquiring the corresponding sample picture is improved.

In one embodiment, the sample slice source may generate a plurality of corresponding sample videos to detect different video communication systems. For example, the original sample video can be converted to sample video of different resolutions by means of codec. For example, high-resolution sample video can be converted to low-resolution sample video, high-resolution sample video is used to detect video communication systems with corresponding high output resolution, and low-resolution sample video is used to detect A video communication system with a correspondingly low output resolution. Each sample video can also be converted to sample video having multiple preset resolutions to enable detection of multiple video communication systems having different output resolutions. For example, the sample pictures with the same resolution are saved as one path according to the resolution of the sample picture, and the sample pictures of different resolutions are stored in the corresponding different paths to form a sample library, and the resolution of the video to be tested can be found correspondingly. The path of the sample picture with the resolution, through which the sample picture with the corresponding resolution can be found. In this embodiment, the sample picture is stored in the corresponding path according to the resolution of the sample picture, thereby searching for the corresponding sample picture according to the resolution of the video to be tested, thereby improving the convenience of managing the sample picture and reducing the search sample. The difficulty of the photo improves the efficiency of obtaining the corresponding sample image.

In one embodiment, as shown in Figure 6, another video communication system detection method is provided. The method can be applied to an application environment as shown in FIG. 1, including:

Step S601: Acquire a sample slice source for detecting a video communication system, and generate a sample video by adding a frame sequence number to each frame picture of the sample slice source.

In this embodiment, a sample slice source of a corresponding category may be selected according to an application scenario of the video communication system. For example, when the detected video communication system is a video conference system, since the application scenario of the video conference is usually a conference room, and more face images appear, the selected sample source may be in a closed scene. , including more face images, etc. A frame number may be superimposed on the bottom edge of each frame picture, or a black border may be formed on the bottom edge of each frame picture of the sample source by editing the sample source, and the frame number may be superimposed on the black side. To reduce the interference on the frame picture itself.

Step S602, extracting a frame picture in the sample video to generate a sample picture.

In this embodiment, the frame number included in the sample picture can be identified by the image recognition technology, and the sample picture is saved and named as the corresponding serial number.

Step S603, acquiring a video to be tested generated by the video communication system according to the sample video.

In this embodiment, the transmitting end of the video communication system may transmit the sample video to one or more receiving ends after the sample video is encoded, and the one or more receiving ends may follow the corresponding decoding manner. Decoding the encoded sample video to generate a corresponding video to be tested, and acquiring the video to be tested for the next detection.

Step S604, extracting a plurality of pictures to be tested from the video to be tested.

In this embodiment, the frame image is extracted from the video to be tested as the image to be tested according to the preset time interval. For example, the frame image is extracted from the video to be tested every 1 second as the image to be tested.

In an embodiment, after extracting a plurality of pictures to be tested from the video to be tested, the method further includes determining whether the number of the extracted pictures to be tested is higher than a preset number. For example, if the number of extracted pictures to be tested is higher than the preset number, the next step of detecting is performed; if the number of extracted pictures to be tested is lower than the preset number, repeating this step to extract more pictures to be tested, such as Said to extract more pictures to be tested from the video to be tested according to a higher extraction frequency.

Step S605, identifying a frame number included in each picture to be tested.

In this embodiment, the frame number may be a string that is not repeated continuously. For example, for a video containing 1500 frame pictures, the frame number can be from 10001 to 11500 in the order of the frame picture. Alternatively, the frame number of the frame picture may not be in the order of the frame number, but an arbitrarily ordered non-repeating character string. For example, the frame number can be in the form of binary coding, and only two numbers of 0 and 1 are used to identify the frame picture, which reduces the difficulty of identifying the frame number and improves the accuracy of identifying the frame number.

Step S606: Find a sample picture having the same resolution according to the resolution of the picture to be tested, and obtain a sample picture corresponding to the frame number of each picture to be tested in the sample picture having the same resolution.

In this embodiment, the resolution of the video to be tested generated by the video communication system may be the highest output resolution of the video communication system, and correspondingly, the resolution of the sample video used for the detection video communication system is also compatible with the video communication system. The highest output resolution is the same. The sample picture having the corresponding resolution may be searched according to the resolution of the video to be tested or the resolution of the picture to be tested, and the sample picture corresponding to the frame number of the picture to be tested is searched for in the sample picture that is found.

Step S607, calculating a first similarity between each picture to be tested and a corresponding sample picture.

In this embodiment, the first similarity may be calculated by comparing each pair of corresponding pixels RGB of the to-be-measured picture and the sample picture, and determining whether the first similarity is lower than the first threshold, and if yes, the picture to be tested and the sample The image is verified by a histogram improvement algorithm. If the similarity is still lower than the first threshold by the histogram improvement algorithm, it is determined that there is a quality problem in the picture to be tested; if the similarity is higher than the first threshold by the histogram improvement algorithm, the two pictures are determined to be consistent. The picture to be tested does not have a quality problem, and the similarity higher than the first threshold is taken as the first similarity.

Step S608, determining whether there is a video processing problem in the video communication system according to the number of pictures to be tested corresponding to the first similarity lower than the first threshold.

In this embodiment, the preset number threshold is 1. If there is a picture to be tested corresponding to the first similarity lower than the first threshold, it is determined that the video communication system has a video processing problem. For example, the preset number threshold is 0.1% of the total number of pictures to be tested, and for the total number of 5000 pictures to be tested, the number of pictures to be tested corresponding to the first similarity lower than the first threshold is greater than 5. It is determined that there is a video processing problem in the video communication system. For example, when it is determined that there is a video processing problem in the video communication system, step S609 is performed, and if not, step S613 is performed.

Step S609, calculating a second similarity between each deviation of the to-be-tested picture and the preset deviation picture, where the deviation of the to-be-tested picture is a picture to be tested corresponding to the first similarity lower than the first threshold.

Step S610, determining whether the second similarity is higher than the second threshold.

In this embodiment, the second threshold is a similarity threshold for determining whether the deviation of the picture to be tested has a deviation picture quality problem. For example, when the second similarity is higher than the second threshold, step S611 is performed, and when the second similarity is lower than the second threshold, step S612 is performed.

In step S611, it is determined that the video processing problem existing in the video communication system includes a blue screen or a black screen.

In step S612, it is determined that the video processing problem existing in the video communication system includes a problem of blooming or color cast.

In step S613, it is determined whether the frame number included in the picture to be tested corresponding to the first similarity that is higher than the first threshold is consistent with the frame number included in the adjacent picture to be tested.

In this embodiment, when the frame number of the to-be-tested picture corresponding to the first similarity that is higher than the first threshold is consistent with the frame number of the adjacent picture to be tested, step S614 is performed, and if no, step S615 is performed. .

In step S614, it is determined that the video processing problem existing in the video communication system includes an image freeze or an image jam.

In step S615, it is determined that the video communication system does not have a black screen, a blue screen, a flower screen or a color cast.

In an embodiment, after step S611, step S612, step S614, and step S615, the method further includes: saving the deviation to-be-tested picture according to the corresponding category according to the determination result. Among them, categories include, but are not limited to, black screen, blue screen, flower screen, color cast, and the like. The detection report of the video communication system refers to the information of the number, category, and the like of the picture to be measured by the aggregation deviation, and is not limited thereto, and generates a report reflecting the video processing problem existing in the video communication system. The deviation test picture may also be named as the progress time of the deviation test picture in the video to be tested, and the sample picture of the corresponding progress time in the sample video may be searched according to the progress time for the next analysis and confirmation.

In this embodiment, by calculating the first similarity and determining whether the first similarity is lower than the first threshold, thereby confirming whether the image to be tested has an image quality problem, calculating the second similarity, and determining whether the second similarity is higher than the threshold. In order to confirm the specific problem of the picture to be tested, the video processing problem existing in the video communication system is gradually refined, and the accuracy of the detection of the video to be tested system is improved. By judging whether the frame number of the to-be-tested picture corresponding to the first similarity higher than the first threshold is consistent with the frame number included in the adjacent picture to be tested, image freezing or image jamming other than ignoring the image quality problem is avoided. The problem is to improve the accuracy of detecting the video to be tested, thereby improving the detection efficiency of the video communication system.

In one embodiment, as shown in FIG. 7, a detection apparatus for a video communication system is provided, including:

The to-be-tested video acquisition module 702 is configured to acquire a video to be tested generated by the video communication system according to the sample video.

The picture to be tested module 704 is configured to extract a plurality of pictures to be tested from the video to be tested.

The frame number identification module 706 is configured to identify the frame number included in each picture to be tested.

The sample picture obtaining module 708 is configured to acquire a sample picture corresponding to each frame number, and the sample picture is a frame picture extracted from the sample video.

The similarity calculation module 710 is configured to calculate a first similarity between each picture to be tested and a corresponding sample picture.

The video processing problem determining module 712 is configured to determine whether the video communication system has a video processing problem according to the first similarity between each picture to be tested and the corresponding sample picture.

In one embodiment, as shown in FIG. 8, the apparatus further includes:

The sample video generation module 714 is configured to acquire a sample slice source for detecting the video communication system, and generate a sample video by adding a frame number to each frame picture of the sample slice source.

The sample picture generating module 716 is configured to extract a frame picture in the sample video to generate a sample picture.

In one embodiment, the sample picture generating module 716 is further configured to save each frame picture of the sample video as a sample picture; acquire a frame number included in each sample picture; and name a corresponding sample picture according to the frame number.

In one embodiment, the video processing problem determining module 712 is further configured to determine whether the video communication system has a video processing problem according to the number of pictures to be tested corresponding to the first similarity lower than the first threshold.

In an embodiment, the similarity calculation module 710 is further configured to: when determining that the video communication system has a video processing problem, calculate a second similarity between each deviation of the to-be-tested picture and the preset deviation picture, and deviation the picture to be tested The video processing problem determining module 712 is further configured to: when the second similarity is higher than the second threshold, determine that the video processing problem existing in the video communication system includes a blue screen. Or a black screen problem, when the second similarity is lower than the second threshold, it is determined that the video processing problem existing in the video communication system includes a problem of blooming or color cast.

In an embodiment, the video processing problem determining module 712 is further configured to determine whether the frame number of the to-be-tested picture corresponding to the first similarity that is higher than the first threshold is consistent with the frame number included in the adjacent picture to be tested; Then, it is determined that the video processing problems existing in the video communication system include image freeze or image jamming.

In one embodiment, the sample picture obtaining module 708 is further configured to: search for a sample picture having the same resolution according to a resolution of the picture to be tested; and acquire a frame number of each picture to be tested in the sample picture having the same resolution. Corresponding sample image.

The detecting device of the video communication system, by extracting a plurality of pictures to be tested from the video to be tested, identifying the frame number included in each picture to be tested, and acquiring the sample picture corresponding to the picture to be tested according to the frame number, and passing the frame number Correlating the to-be-tested picture and the sample picture improves the accuracy of finding the corresponding sample picture, and determining whether the video communication system has a video processing problem by calculating the first similarity between each picture to be tested and the corresponding sample picture, and avoiding The missing picture with quality problems is omitted, which saves the detection time of the video communication system and improves the detection efficiency of the video communication system.

In one embodiment, a computer readable storage medium is provided having stored thereon a computer program, wherein the program, when executed by the processor, implements the steps of: acquiring a video to be tested generated by the video communication system according to the sample video; Extracting a plurality of pictures to be tested in the video to be tested; identifying a frame number included in each picture to be tested; acquiring a sample picture corresponding to each frame number, the sample picture is a frame picture extracted from the sample video; calculating each to be tested A first similarity between the picture and the corresponding sample picture; determining whether the video communication system has a video processing problem according to the first similarity between each picture to be tested and the corresponding sample picture.

In an embodiment, when the program is executed by the processor, before the step of acquiring the video to be tested generated by the video communication system according to the sample video, the following steps are further implemented: acquiring a sample slice source for detecting the video communication system; Adding a frame number to each frame picture of the sample piece source to generate a sample video; extracting a frame picture in the sample video to generate a sample picture.

In an embodiment, when the program is executed by the processor, when the step of extracting the frame picture in the sample video and generating the sample picture is performed, the following steps are implemented: saving each frame picture of the sample video as a sample picture; The frame number included in each sample picture; the corresponding sample picture is named according to the frame number.

In an embodiment, when the program is executed by the processor, when the step of determining whether the video communication system has a video processing problem according to the first similarity between each picture to be tested and the corresponding sample picture, the following is implemented. Step: Determine whether the video communication system has a video processing problem according to the number of pictures to be tested corresponding to the first similarity lower than the first threshold.

In one embodiment, when the program is executed by the processor, after the step of determining whether the video communication system has a video processing problem according to the number of pictures to be tested corresponding to the first similarity lower than the first threshold, the following is also implemented. Step: when it is determined that there is a video processing problem in the video communication system, calculating a second similarity between each deviation of the to-be-tested picture and the preset deviation picture, and the deviation of the to-be-tested picture is corresponding to the first similarity of the first threshold The picture to be tested; when the second similarity is higher than the second threshold, determining that the video processing problem existing in the video communication system includes a blue screen or a black screen; when the second similarity is lower than the second threshold, determining the video communication Video processing problems that exist in the system include problems with flower screens or color casts.

In one embodiment, when the program is executed by the processor, after implementing the step of determining whether the video communication system has a video processing problem according to the first similarity between each picture to be tested and the corresponding sample picture, the following is also implemented. Step: determining whether the frame number of the to-be-tested picture corresponding to the first similarity higher than the first threshold is consistent with the frame number included in the adjacent picture to be tested; if yes, determining that the video processing problem existing in the video communication system includes an image Freeze or image stuck.

In an embodiment, when the program is executed by the processor, when the step of acquiring the sample picture corresponding to each frame serial number is implemented, the following steps are implemented: searching for a sample picture having the same resolution according to the resolution of the picture to be tested; A sample picture corresponding to the frame number of each picture to be tested is acquired in the sample picture having the same resolution.

In one embodiment, a computer apparatus is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to: obtain the video communication system according to the following steps: a video to be tested generated by the sample video; extracting a plurality of pictures to be tested from the video to be tested; identifying a frame number included in each picture to be tested; acquiring a sample picture corresponding to each frame number, the sample picture is extracted from the sample video a frame image; calculating a first similarity between each picture to be tested and a corresponding sample picture; determining whether the video communication system has a video processing problem according to the first similarity between each picture to be tested and the corresponding sample picture .

In an embodiment, when the processor executes the program, before the step of acquiring the video to be tested generated by the video communication system according to the sample video, the following steps are further implemented: acquiring a sample slice source for detecting the video communication system; Adding a frame number to each frame picture of the sample piece source to generate a sample video; extracting a frame picture in the sample video to generate a sample picture.

In an embodiment, when the foregoing processor executes the program, when the step of extracting the frame picture in the sample video and generating the sample picture is performed, the following steps are implemented: saving each frame picture of the sample video as a sample picture; The frame number included in each sample picture; the corresponding sample picture is named according to the frame number.

In an embodiment, when the processor executes the program, when the step of determining whether the video communication system has a video processing problem according to the first similarity between each picture to be tested and the corresponding sample picture, the following is implemented. Step: Determine whether the video communication system has a video processing problem according to the number of pictures to be tested corresponding to the first similarity lower than the first threshold.

In an embodiment, when the processor executes the program, after determining the step of determining whether the video communication system has a video processing problem according to the number of pictures to be tested corresponding to the first similarity lower than the first threshold, the following is also implemented. Step: when it is determined that there is a video processing problem in the video communication system, calculating a second similarity between each deviation of the to-be-tested picture and the preset deviation picture, and the deviation of the to-be-tested picture is corresponding to the first similarity of the first threshold The picture to be tested; when the second similarity is higher than the second threshold, determining that the video processing problem existing in the video communication system includes a blue screen or a black screen; when the second similarity is lower than the second threshold, determining the video communication Video processing problems that exist in the system include problems with flower screens or color casts.

In an embodiment, when the processor executes the program, after implementing the step of determining whether the video communication system has a video processing problem according to the first similarity between each picture to be tested and the corresponding sample picture, the following is also implemented. Step: determining whether the frame number of the to-be-tested picture corresponding to the first similarity higher than the first threshold is consistent with the frame number included in the adjacent picture to be tested; if yes, determining that the video processing problem existing in the video communication system includes an image Freeze or image stuck.

In an embodiment, when the foregoing processor executes the program, when the step of acquiring the sample picture corresponding to each frame serial number is implemented, the following steps are implemented: searching for a sample picture having the same resolution according to the resolution of the picture to be tested; A sample picture corresponding to the frame number of each picture to be tested is acquired in the sample picture having the same resolution.

Those of ordinary skill in the art will appreciate that all or some of the steps, systems, and functional blocks/units of the methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. In a hardware implementation, the division between functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be composed of several physical The components work together. Some or all of the components may be implemented as software executed by a processor, such as a digital signal processor or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on a computer readable medium, which may include computer storage media (or non-transitory media) and communication media (or transitory media). As is well known to those of ordinary skill in the art, the term computer storage medium includes volatile and nonvolatile, implemented in any method or technology for storing information, such as computer readable instructions, data structures, program modules or other data. Sex, removable and non-removable media. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridge, magnetic tape, magnetic disk storage or other magnetic storage device, or may Any other medium used to store the desired information and that can be accessed by the computer. Moreover, it is well known to those skilled in the art that communication media typically includes computer readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave or other transport mechanism, and can include any information delivery media. .

The above-mentioned embodiments are merely illustrative of several embodiments of the present disclosure, and the description thereof is more specific and detailed, but is not to be construed as limiting the scope of the invention. It will be apparent to those skilled in the art that various changes and modifications may be made without departing from the scope of the present disclosure. Therefore, the scope of the invention should be determined by the appended claims.

Industrial applicability

Claims

A method for detecting a video communication system, the method comprising:

Obtaining a video to be tested generated by the video communication system according to the sample video;

Extracting a plurality of pictures to be tested from the video to be tested;

Identifying a frame number included in each picture to be tested;

Obtaining a sample picture corresponding to each frame number, where the sample picture is a frame picture extracted from the sample video;

Calculating a first similarity between each picture to be tested and a corresponding sample picture;

Determining whether the video communication system has a video processing problem according to the first similarity between each picture to be tested and the corresponding sample picture.
The method of detecting a video communication system according to claim 1, wherein before the acquiring the video to be tested generated by the video communication system according to the sample video, the method further comprises:

Obtaining a sample slice source for detecting a video communication system;

Generating a sample video by adding a frame number to each frame picture of the sample piece source;

A frame picture in the sample video is extracted to generate a sample picture.
The method for detecting a video communication system according to claim 2, wherein the extracting a frame picture in the sample video to generate a sample picture comprises:

Saving each frame picture of the sample video as a sample picture;

Obtain the frame number included in each sample picture;

Name the corresponding sample picture according to the frame number.
The method for detecting a video communication system according to claim 1, wherein the determining whether the video communication system has a video processing problem according to the first similarity between each picture to be tested and the corresponding sample picture comprises:

Determining whether there is a video processing problem in the video communication system according to the number of pictures to be tested corresponding to the first similarity lower than the first threshold.
The detecting method of the video communication system according to claim 4, wherein after determining whether the video communication system has a video processing problem according to the number of pictures to be tested corresponding to the first similarity lower than the first threshold, the method Also includes:

When it is determined that the video communication system has a video processing problem, calculating a second similarity between each of the deviation to-be-tested pictures and the preset deviation picture, the deviation of the to-be-tested picture being a first similarity lower than the first threshold The picture to be tested;

When the second similarity is higher than the second threshold, determining that the video processing problem existing in the video communication system includes a blue screen or a black screen;

When the second similarity is lower than the second threshold, it is determined that the video processing problem existing in the video communication system includes a problem of blooming or color cast.
The detecting method of the video communication system according to claim 1, wherein the method determines whether a video processing system has a video processing problem according to a first similarity between each picture to be tested and a corresponding sample picture, the method Also includes:

Determining whether the frame number of the to-be-tested picture corresponding to the first similarity that is higher than the first threshold is consistent with the frame number included in the adjacent picture to be tested;

When the frame number of the to-be-tested picture corresponding to the first similarity that is higher than the first threshold is consistent with the frame number of the adjacent picture to be tested, it is determined that the video processing problem existing in the video communication system includes image freezing or Image stuck in the problem.
The method for detecting a video communication system according to claim 1, wherein the acquiring a sample picture corresponding to each frame number comprises:

Finding sample pictures having the same resolution according to the resolution of the picture to be tested;

A sample picture corresponding to a frame number of each picture to be tested is acquired in the sample picture having the same resolution.
A detecting device for a video communication system, the device comprising:

The video acquisition module to be tested is configured to acquire a video to be tested generated by the video communication system according to the sample video;

The picture extraction module to be tested is configured to extract a plurality of pictures to be tested from the video to be tested;

a frame number identification module configured to identify a frame number included in each picture to be tested;

a sample picture obtaining module, configured to acquire a sample picture corresponding to each frame serial number, where the sample picture is a frame picture extracted from the sample video;

a similarity calculation module, configured to calculate a first similarity between each picture to be tested and a corresponding sample picture;

The video processing problem determining module is configured to determine whether the video communication system has a video processing problem according to the first similarity between each picture to be tested and the corresponding sample picture.
A computer readable storage medium having stored thereon a computer program, wherein the program is executed by a processor to perform the steps of the method of any one of claims 1 to 7.
A computer apparatus comprising a memory, a processor, and a computer program stored on the memory and operable on the processor, wherein the processor executes the program to implement the method of any one of claims 1 to 7. A step of.