CN113436065A - Image processing method, device, equipment and medium - Google Patents

Abstract

The present application discloses an image processing method, device, device and medium, belonging to the technical field of image processing. The method includes: acquiring each picture to be processed; dividing each picture to be processed according to preset dividing conditions to obtain each picture combination and picture category; respectively adopt the super-resolution processing mode set corresponding to the picture category of each picture combination, perform super-resolution processing on a picture combination, and obtain the processed super-resolution picture, which improves the hardware cost without increasing the hardware cost. Image Quality.

Description

An image processing method, apparatus, device and medium

technical field

The present application relates to the field of image technology, and in particular, to an image processing method, apparatus, device, and medium.

Background technique

With the development of computer technology, camera equipment is widely used in people's daily life and has become an indispensable part of people's life. For example, users can obtain surveillance video through surveillance equipment for security protection.

However, due to hardware reasons such as equipment aging and external environmental factors such as lighting, the quality of the obtained images is poor. However, using a high-quality video camera to perform video recording requires high hardware costs.

Therefore, how to improve the image quality without increasing the hardware cost is an urgent problem to be solved.

SUMMARY OF THE INVENTION

Embodiments of the present application provide an image processing method, apparatus, device, and medium, so as to improve image quality without increasing hardware cost.

In one aspect, an image processing method is provided, comprising:

Get each image to be processed;

According to the preset division conditions, the pictures to be processed are divided to obtain the picture combinations and the picture categories, wherein the preset division conditions are determined according to the objects identified in the pictures or the similarity between the pictures;

The super-resolution processing mode set corresponding to the picture category of each picture combination is respectively used to perform super-resolution processing on the picture combination to obtain a processed super-resolution picture.

Preferably, according to preset division conditions, each picture to be processed is divided to obtain each picture combination and picture category, including:

Perform image recognition on each picture to be processed, respectively, and determine the object identified from each picture to be processed;

According to the identified objects, the to-be-processed pictures with the same object are divided into the same group;

The picture category of the divided picture combination is set as the partial super-score processing picture.

Preferably, according to preset division conditions, each picture to be processed is divided to obtain each picture combination and picture category, including:

Determine the similarity between each two to-be-processed pictures respectively;

According to the similarity between the pictures to be processed, the pictures to be processed are divided, so that the pictures to be processed whose similarity is higher than the preset similarity threshold are divided into the same group;

Set the picture category of the divided picture combination as the overall super-scoring picture.

Preferably, the super-resolution processing mode set corresponding to the picture category of each picture combination is respectively used to perform super-resolution processing on the picture combination to obtain the processed super-resolution picture, including:

Obtaining its own device state, and determining that the obtained device state represents the idle state, respectively adopts the super-resolution processing mode set corresponding to the picture category of each picture combination, performs super-resolution processing on the picture combination, and obtains the processed super-resolution picture; or,

The super-resolution processing mode set corresponding to the picture category of each picture combination is respectively used to perform real-time super-resolution processing on the picture combination to obtain a processed super-resolution picture.

Preferably, the super-resolution processing mode set corresponding to the picture category of each picture combination is respectively used to perform super-resolution processing on the picture combination to obtain the processed super-resolution picture, including:

When the picture category of the picture combination is a local super-scoring picture, perform local super-scoring processing on the objects included in the picture combination to obtain a processed super-scoring picture;

When the picture category of the picture combination is the overall super-scoring processed picture, the overall super-scoring processing is performed on the pictures included in the picture combination to obtain the processed super-scoring picture.

In one aspect, an apparatus for image processing is provided, comprising:

an acquisition unit, used to acquire each to-be-processed picture;

A dividing unit, configured to divide each picture to be processed according to a preset dividing condition, and obtain each picture combination and picture category, wherein the preset dividing condition is determined according to the objects identified in the picture or the similarity between the pictures ;

The processing unit is applied to respectively adopt the super-resolution processing mode set corresponding to the picture category of each picture combination, perform super-resolution processing on the picture combination, and obtain the processed super-resolution picture.

Preferably, the division unit is used for:

Perform image recognition on each picture to be processed, respectively, and determine the object identified from each picture to be processed;

According to the identified objects, the to-be-processed pictures with the same object are divided into the same group;

The picture category of the divided picture combination is set as the partial super-score processing picture.

Preferably, the division unit is used for:

Determine the similarity between each two to-be-processed pictures respectively;

According to the similarity between the pictures to be processed, the pictures to be processed are divided, so that the pictures to be processed whose similarity is higher than the preset similarity threshold are divided into the same group;

Set the picture category of the divided picture combination as the overall super-scoring picture.

Preferably, the processing unit is used to:

Obtaining its own device state, and determining that the obtained device state represents the idle state, respectively adopts the super-resolution processing mode set corresponding to the picture category of each picture combination, performs super-resolution processing on the picture combination, and obtains the processed super-resolution picture; or,

The super-resolution processing mode set corresponding to the picture category of each picture combination is respectively used to perform real-time super-resolution processing on the picture combination to obtain a processed super-resolution picture.

Preferably, the processing unit is used to:

When the picture category of the picture combination is a local super-scoring picture, perform local super-scoring processing on the objects included in the picture combination to obtain a processed super-scoring picture;

When the picture category of the picture combination is the overall super-scoring processed picture, the overall super-scoring processing is performed on the pictures included in the picture combination to obtain the processed super-scoring picture.

In one aspect, a control device is provided, comprising:

at least one memory for storing program instructions;

At least one processor is configured to call the program instructions stored in the memory, and execute the steps of any one of the above image processing methods according to the obtained program instructions.

In one aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, implements the steps of any one of the above image processing methods.

In an image processing method, device, device, and medium provided by the embodiments of the present application, each picture to be processed is obtained; according to preset division conditions, each picture to be processed is divided to obtain each picture combination and picture category; The super-resolution processing mode is set corresponding to the picture category of each picture combination, and super-resolution processing is performed on a picture combination to obtain the processed super-resolution picture, which improves the image quality without increasing the hardware cost.

Other features and advantages of the present application will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the present application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description, claims, and drawings.

Description of drawings

The drawings described herein are used to provide further understanding of the present application and constitute a part of the present application. The schematic embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation of the present application. In the attached image:

FIG. 1 is an implementation flowchart of an image processing method in an embodiment of the present application;

FIG. 2 is an example diagram of a picture to be processed in an embodiment of the present application;

FIG. 3 is an example diagram of a super-resolution picture in an embodiment of the present application;

FIG. 4 is a schematic structural diagram of an image processing apparatus in an embodiment of the present application;

FIG. 5 is a schematic structural diagram of a control device in an embodiment of the present application.

Detailed ways

In order to make the objectives, technical solutions and beneficial effects of the present application clearer, the present application will be described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application.

In order to improve image quality without increasing hardware cost, embodiments of the present application provide an image processing method, apparatus, device, and medium.

The embodiments of the present application may be applied to a control device, where the control device may be a device including a camera function, or a server that receives images sent by other devices and performs image processing on the received images.

Referring to FIG. 1 , an implementation flowchart of an image processing method provided by the present application is shown. The specific implementation process of the method is as follows:

Step 100: The control device acquires the picture to be processed.

Specifically, when step 200 is executed, the control device may adopt any one or a combination of the following methods:

The first way is to control the device to obtain the pictures or videos taken by itself, and use each frame of pictures in the pictures or videos as the pictures to be processed.

In order to obtain high-quality pictures in the subsequent steps, the control device can take multiple pictures at a time when taking pictures. Further, when taking pictures, different exposure parameters and different angles can be used to obtain multiple pictures. .

Among them, exposure refers to the process of placing the photosensitive plate on the plate printing machine table, placing the negative film, and obtaining a latent or visible image through exposure. Exposure is the basic process and main feature of all photochemical imaging methods.

Exposure, the exposure mode is the mode in which the computer uses natural light sources, and is usually divided into various modes, such as manual exposure and automatic exposure. The quality of a photo is related to exposure, that is, how much light should be passed through to allow the sensor to get a clear image. The exposure amount is determined by the light-transmitting time (determined by shutter speed) and the light-transmitting area (aperture size).

Because when the scene changes dynamically, multiple similar pictures to be processed can be obtained through snapshots, and through different exposure parameters, multiple pictures to be processed of the same scene but different effects can be obtained, so that in subsequent steps, through Multiple similar images to be processed to obtain higher resolution and clearer super-resolution images.

The second way is: the control device receives pictures to be processed sent by other devices.

For example, the server receives the video sent by the monitoring device, and uses each frame of pictures extracted from the video as the pictures to be processed.

In this way, each picture to be processed can be acquired by means of shooting or by means of receiving pictures sent by other devices.

Step 101: The control device divides each picture to be processed according to preset dividing conditions, and obtains each picture combination and picture category.

Specifically, the preset division conditions are determined according to the objects identified in the pictures or the similarity between the pictures, that is, the preset division conditions may divide the pictures according to the objects contained in the pictures, or according to the similarity between the pictures The picture is divided, and the picture category is determined according to the preset dividing conditions, including local super-scoring pictures and overall super-scoring pictures.

When performing step 101, the control device can adopt the following two methods:

The first method is: performing image recognition on each picture to be processed, and dividing each picture to be processed according to the image recognition result to obtain each picture combination and picture category.

Specifically, the control device performs image recognition on each picture to be processed, respectively determines the objects recognized from each picture to be processed, and divides the pictures to be processed with the same object into the same group according to the recognized objects, And set the picture category of the divided picture combination as the partial super-score processing picture.

The object may be a person or a specified target object, such as a specific house, an animal, a landscape, etc., so that in the subsequent steps, super-resolution processing is performed on the to-be-processed picture containing the specific object.

This is because the multiple pictures may be obtained by shooting the same object in different scenes. Obviously, the pictures other than the object in each picture are different, so the pictures containing the same object can be divided into a group, In order to extract the image information of the object in each picture in the subsequent steps, and obtain the super-resolution picture of the object according to the extracted image information, so as to improve the definition of the character.

In one embodiment, the control device performs image recognition on the face image contained in each picture to be processed, sets a corresponding user ID for each identified user, and establishes a relationship between the picture to be processed and the user ID. For each user ID, the pictures to be processed corresponding to the user ID are divided into the same group.

It should be noted that the same user identified in different pictures to be processed corresponds to the same user ID. Because a picture to be processed may contain one face image or multiple face images, that is, a picture to be processed may correspond to one user ID, or may correspond to multiple user IDs, and each user ID corresponds to a Picture combination, therefore, when a picture to be processed corresponds to multiple user IDs, the multi-picture combination corresponding to the above-mentioned multiple user IDs all includes the to-be-processed picture.

For example, it is assumed that the control device contains 3 pictures, namely picture 1, picture 2 and picture 3. The control device performs face recognition on each picture, and the face recognition result is: picture 1 includes user A and user B, picture 2 includes user B, and picture 3 includes user A. Then the control device will divide each picture according to the user identified in the picture. A picture combination corresponding to user A is picture 1 and picture 3, and a picture combination corresponding to user B is picture 1 and picture 2.

For another example, the control device performs image recognition on each picture, identifies the picture containing the building "Oriental Pearl", and divides the identified pictures into a group, so that in subsequent steps, the super-resolution of the combination of pictures can be performed. rate processing to obtain a clear "Pearl of the Orient" picture.

In this way, each picture to be processed can be divided according to the objects contained in the picture to be processed, and the same group of divided pictures contains the same specific object, which can be applied to an application scenario in which the definition of a specific object is improved.

The second method is: the control device divides each to-be-processed picture according to the similarity between the to-be-processed pictures, and sets the picture category of the divided picture combination as the overall super-score processed picture.

This is because the user may take multiple pictures continuously in the same scene. Obviously, the obtained pictures are similar as a whole, and the pictures with high similarity can be divided into a group, so that in the subsequent super-score processing , extract all the image information in each picture, and synthesize high-definition super-resolution pictures.

Specifically, when the control device determines the similarity between the pictures to be processed, the following two methods can be used:

Mode 1 is: the control device determines the similarity between every two pictures to be processed, respectively.

Manner 2 is: the control device respectively determines the similarity between every two adjacent pictures to be processed.

It should be noted that the pictures to be processed are sorted according to the image time, and the image time may be the shooting time of the picture or the video progress time of each frame of pictures in the video.

Because the adjacent pictures to be processed are usually multiple shots of the same scene. In this way, only the adjacent pictures to be processed are processed, which can reduce the consumption of system resources and improve the efficiency of image processing.

That is to say, the control device divides each to-be-processed picture according to the similarity between the to-be-processed pictures, so that each to-be-processed picture whose similarity is higher than a preset similarity threshold, that is, similar to-be-processed pictures, is divided into the same group .

In one embodiment, for each picture to be processed, the control device selects the picture to be processed whose similarity with the picture to be processed is higher than the preset similarity threshold as the matching picture of the picture to be processed, and uses the picture to be processed. The to-be-processed picture and the corresponding matching picture are divided into the same group.

It should be noted that the same pictures to be processed may exist in pictures of different groups. When the similarity between one to-be-processed picture and each of the other to-be-processed pictures is not higher than the preset similarity, the to-be-processed pictures are regarded as a separate group.

In practical applications, the preset similarity threshold may be set according to actual application scenarios, for example, the preset similarity threshold may be 0.8, which is not limited herein.

For example, the preset similarity threshold is set to 0.8, and the pictures to be processed are: picture 1, picture 2...picture 5. The control device determines the similarity between each two adjacent pictures to be processed, the similarity between Figure 1 and Figure 2 is 0.9, the similarity between Figure 2 and Figure 3 is 0.95, and the similarity between Figure 3 and Figure 4 The similarity between them is 0.1, and the similarity between Figure 4 and Figure 5 is 0.85. Then, the control device divides FIG. 1 , FIG. 2 and FIG. 3 into one group, and divides FIG. 4 and FIG. 5 into one group.

In this way, similar pictures or pictures containing the same object can be divided into the same group, so that in subsequent steps, high-resolution super-score pictures can be obtained according to multiple similar pictures or pictures containing the same object.

Step 102: The control device adopts the super-resolution processing mode set corresponding to the picture category of each picture combination, performs super-resolution processing on the picture combination, and obtains the processed super-resolution picture.

Specifically, when step 102 is executed, the control device may adopt the following two methods:

The first way is: when the picture category of the picture combination is a local super-score processed picture, perform local super-score processing on the objects included in the picture combination to obtain a processed super-score picture.

The so-called local super-resolution processing means that only local super-resolution processing is performed on specific objects contained in the picture. This is because the differences between the pictures in the picture combination may be large, and each picture contains the same object. Then you can super-resolution only on the same object contained.

This is because the multiple pictures may be obtained by shooting the same object in different scenes. Obviously, the pictures other than the object in each picture are different, then the image information of the object in each picture can be extracted, and the According to the extracted image information, a super-resolution picture of the object is obtained to improve the definition of the object.

In one embodiment, the control device obtains, according to each picture to be processed included in the picture combination, the processed super-score picture is a partial picture containing only a specific object.

When the picture category of the picture combination is an overall super-scoring picture, perform overall super-scoring processing on the pictures included in the picture combination to obtain a processed super-scoring picture.

The so-called overall super-resolution processing is to directly perform overall super-resolution processing on each picture included in the picture combination. This is because the difference between the pictures in the picture combination is small, and the overall picture can be super-resolution processed. .

This is because the user may continuously take multiple pictures in the same scene. Obviously, the obtained pictures are all similar as a whole, so all the image information in each picture can be extracted during the super-resolution process, and the high-definition picture can be synthesized. Overrated pictures.

Further, when step 102 is executed, the control device may also adopt the following two methods:

The first way is as follows: the control device obtains its own device state, and when it is determined that the obtained device state represents the idle state, super-resolution processing is performed on each picture combination to obtain a processed super-resolution picture.

Since the super-resolution processing will occupy a lot of system resources, the super-resolution processing can be performed only when the control device is in an idle state, so as to avoid affecting the running speed of the control device and realize a reasonable allocation of system resources.

The second method is as follows: the control device performs real-time super-resolution processing on each picture combination respectively, and obtains a processed super-resolution picture.

For example, an object captures multiple pictures at a time through a mobile phone, and uses the captured pictures as a group to perform super-resolution processing in real time to obtain high-resolution super-resolution pictures.

In one embodiment, super-resolution processing is performed on each picture combination respectively, and when obtaining the processed super-resolution picture, the control device may adopt the following steps:

S1021: Obtain the image time of each to-be-processed picture in each picture combination respectively.

S1022: Divide each picture combination into each picture set according to the image time and set duration of the picture to be processed.

In one embodiment, for each picture combination, the following steps are performed:

According to the set duration, the time between the earliest image time and the latest image time in the picture combination is divided into multiple time intervals, and the images to be processed whose image times are in the same time interval are divided into the same picture set middle.

The start time of each time interval is the image time, and the duration of the time interval is not greater than the set duration.

For example, if the set duration is 3s, the picture combination includes picture 1, picture 2, picture 3 and picture 4, and the corresponding image times are: 1s, 2s, 5s and 6s. Then the first time interval is [1, 3], the second time interval [5, 7], picture 1 and picture 2 are divided into the same picture set, and picture 3 and picture 4 are divided into the same picture set.

For another example, if the set duration is 5s, and the pictures are combined into successive frames of pictures extracted from the video, the control device will sequentially change the image time of each frame of pictures to every 5s (such as 1-5s, 6-10s...) The pictures inside are divided into the same picture set.

In this way, for pictures to be processed with discrete image time, the initial time of the time interval can be set according to the image time of each to-be-processed picture, and for pictures to be processed with continuous image time, the set time interval can be used.

In this way, each picture to be processed with a short interval time can be divided into the same picture set.

S1023: Perform super-resolution processing on each picture included in each picture set to obtain a corresponding super-resolution picture.

Specifically, according to the picture category of each picture combination, the picture category corresponding to the corresponding picture set is determined, and according to the super-resolution processing mode set corresponding to the picture category of each picture set, a preset super-resolution algorithm is used, respectively for each picture set. Each picture included in the picture set is subjected to super-resolution processing to obtain a corresponding super-resolution picture.

Among them, the super-resolution algorithm is used to obtain a high-resolution image from a series of low-resolution images. The core idea is to exchange temporal bandwidth (obtaining multiple frames of image sequences of the same scene) for spatial resolution, so as to realize the conversion from temporal resolution to spatial resolution.

Further, after obtaining the processed super-score picture, the control device may also store the obtained over-score picture and delete each to-be-processed picture, thereby reducing the consumption of storage resources.

In this way, a plurality of pictures to be processed of the same scene or containing the same object can be divided according to the similarity or the image recognition result, and a high-resolution super-score picture can be obtained according to the divided pictures to be processed.

Referring to FIG. 2, it is an example diagram of a picture to be processed, and FIG. 2 includes diagrams (a) and (b). Referring to FIG. 3, it is an example diagram of a super-score picture. The control device adopts a super-resolution algorithm, and performs super-resolution processing on both pictures (a) and (b) with a resolution of 160×240, and obtains a super-resolution picture with a resolution of 320×480 as shown in Figure 3.

In the embodiment of the present application, the pictures to be processed are firstly divided into multiple picture combinations according to the objects identified in the pictures, or the similarity between pictures, and the picture categories of the picture combinations are set, and then, according to the image time, divide each picture combination into multiple picture sets respectively, and finally, according to the super-score processing mode set corresponding to the picture category of each picture combination, for each low-resolution to-be-processed picture in each picture set, Get high-resolution superscoring images. In this way, for different image categories, different super-resolution processing modes are used to reconstruct low-resolution images to obtain high-quality super-resolution images. The problem of poor image quality caused by factors such as rain. Further, high-quality pictures can be obtained without updating the hardware device of the camera and without increasing the hardware cost.

Based on the same inventive concept, an image processing apparatus is also provided in the embodiments of the present application. Since the above-mentioned apparatus and equipment solve problems in principle similar to an image processing method, the implementation of the above-mentioned apparatus can refer to the implementation of the method. The repetition will not be repeated.

As shown in FIG. 4 , which is a schematic structural diagram of an image processing apparatus provided by an embodiment of the present application, including:

an obtaining unit 401, configured to obtain each picture to be processed;

The dividing unit 402 is configured to divide each picture to be processed according to preset dividing conditions, and obtain each picture combination and picture category;

The processing unit 403 is applied to respectively adopt the super-resolution processing mode set corresponding to the picture category of each picture combination, perform super-resolution processing on the picture combination, and obtain the processed super-resolution picture.

Preferably, the dividing unit 402 is used for:

Perform image recognition on each picture to be processed, respectively, and determine the object identified from each picture to be processed;

According to the identified objects, the to-be-processed pictures with the same object are divided into the same group;

The picture category of the divided picture combination is set as the partial super-score processing picture.

Preferably, the dividing unit 402 is used for:

Determine the similarity between each two to-be-processed pictures respectively;

According to the similarity between the pictures to be processed, the pictures to be processed are divided, so that the pictures to be processed whose similarity is higher than the preset similarity threshold are divided into the same group;

Set the picture category of the divided picture combination as the overall super-scoring picture.

Preferably, the processing unit 403 is used for:

Obtaining its own device state, and determining that the obtained device state represents the idle state, respectively adopts the super-resolution processing mode set corresponding to the picture category of each picture combination, performs super-resolution processing on the picture combination, and obtains the processed super-resolution picture; or,

The super-resolution processing mode set corresponding to the picture category of each picture combination is respectively used to perform real-time super-resolution processing on the picture combination to obtain a processed super-resolution picture.

Preferably, the processing unit 403 is used for:

When the picture category of the picture combination is a local super-scoring picture, perform local super-scoring processing on the objects included in the picture combination to obtain a processed super-scoring picture;

When the picture category of the picture combination is the overall super-scoring processed picture, the overall super-scoring processing is performed on the pictures included in the picture combination to obtain the processed super-scoring picture.

In an image processing method, device, device, and medium provided by the embodiments of the present application, each picture to be processed is obtained; according to preset division conditions, each picture to be processed is divided to obtain each picture combination and picture category; The super-resolution processing mode is set corresponding to the picture category of each picture combination, and super-resolution processing is performed on a picture combination to obtain the processed super-resolution picture, which improves the image quality without increasing the hardware cost.

For the convenience of description, the above parts are divided into modules (or units) according to their functions and described respectively. Of course, the functions of each module (or unit) may be implemented in one or more software or hardware when implementing the present application.

Based on the above embodiment, referring to FIG. 5 , a schematic structural diagram of a control device in an embodiment of the present application.

The embodiment of the present application provides a control device, the control device may include a processor 510 (Center Processing Unit, CPU), a memory 520, an input device 530, an output device 540, etc., and the input device 530 may include a keyboard, a mouse, a A touch screen, etc., the output device 540 may include a display device, such as a liquid crystal display (Liquid Crystal Display, LCD), a cathode ray tube (Cathode Ray Tube, CRT), and the like.

Memory 520 may include read only memory (ROM) and random access memory (RAM) and provide processor 510 with program instructions and data stored in memory 520 . In the embodiment of the present application, the memory 520 may be used to store the image processing program in the embodiment of the present application.

The processor 510 invokes the program instructions stored in the memory 520, and the processor 510 is configured to execute an image processing method provided by the embodiment shown in FIG. 1 .

In the embodiment of the present application, a computer-readable storage medium is also provided, on which a computer program is stored, and when the computer program is executed by a processor, the image processing method in any of the foregoing method embodiments is implemented.

As will be appreciated by those skilled in the art, the embodiments of the present application may be provided as a method, a system, or a computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It will be understood that each flow and/or block in the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means for implementing the functions specified in a flow or flow of a flowchart and/or a block or blocks of a block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions The apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the flowcharts and/or the block or blocks of the block diagrams.

While the preferred embodiments of the present application have been described, additional changes and modifications to these embodiments may occur to those skilled in the art once the basic inventive concepts are known. Therefore, the appended claims are intended to be construed to include the preferred embodiment and all changes and modifications that fall within the scope of this application.

Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims (10)

1. a method for image processing, is characterized in that, comprises: Get each image to be processed; Divide each picture to be processed according to a preset dividing condition, and obtain each picture combination and picture category, wherein the preset dividing condition is determined according to the objects identified in the picture or the similarity between the pictures; The super-resolution processing mode set corresponding to the picture category of each picture combination is respectively used to perform super-resolution processing on the picture combination to obtain a processed super-resolution picture. 2. The method according to claim 1, wherein, according to preset division conditions, each picture to be processed is divided to obtain each picture combination and picture category, comprising: Perform image recognition on each picture to be processed, respectively, and determine the object identified from each picture to be processed; According to the identified objects, the to-be-processed pictures with the same object are divided into the same group; The picture category of the divided picture combination is set as the partial super-score processing picture. 3. The method according to claim 1, wherein, according to preset dividing conditions, each picture to be processed is divided, and each picture combination and picture category are obtained, comprising: Determine the similarity between each two to-be-processed pictures respectively; According to the similarity between the pictures to be processed, the pictures to be processed are divided, so that the pictures to be processed whose similarity is higher than the preset similarity threshold are divided into the same group; Set the picture category of the divided picture combination as the overall super-scoring picture. 4. The method according to claim 1, wherein the super-resolution processing mode corresponding to the picture category of each picture combination is adopted respectively, and the super-resolution processing is performed on the picture combination to obtain the processed super-resolution picture. ,include: Obtain its own device status, and when it is determined that the acquired device status represents the idle state, use the super-resolution processing mode set corresponding to the picture category of each picture combination, perform super-resolution processing on the picture combination, and obtain the processed super-score. pictures; or, The super-resolution processing mode set corresponding to the picture category of each picture combination is respectively adopted to perform real-time super-resolution processing on the picture combination to obtain a processed super-resolution picture. 5. The method according to any one of claims 1-4, characterized in that, a super-resolution processing mode corresponding to a picture category of each picture combination is adopted to perform super-resolution processing on the picture combination, and obtain processing After the super-scoring pictures, including: When the picture category of the picture combination is a local super-scoring picture, perform local super-scoring processing on the objects included in the picture combination to obtain a processed super-scoring picture; When the picture category of the picture combination is an overall super-scoring picture, perform overall super-scoring processing on the pictures included in the picture combination to obtain a processed super-scoring picture. 6. A device for image processing, comprising: an acquisition unit, used to acquire each to-be-processed picture; A dividing unit, configured to divide each picture to be processed according to a preset dividing condition, and obtain each picture combination and picture category, wherein the preset dividing condition is based on the objects identified in the picture or the similarity between the pictures definite; The processing unit is applied to respectively adopt the super-resolution processing mode set corresponding to the picture category of each picture combination, perform super-resolution processing on the picture combination, and obtain the processed super-resolution picture. 7. The apparatus of claim 6, wherein the dividing unit is used for: Perform image recognition on each picture to be processed, respectively, and determine the object identified from each picture to be processed; According to the identified objects, the to-be-processed pictures with the same object are divided into the same group; The picture category of the divided picture combination is set as the partial super-score processing picture. 8. The apparatus of claim 6, wherein the dividing unit is used for: Determine the similarity between each two to-be-processed pictures respectively; According to the similarity between the pictures to be processed, the pictures to be processed are divided, so that the pictures to be processed whose similarity is higher than the preset similarity threshold are divided into the same group; Set the picture category of the divided picture combination as the overall super-scoring picture. 9. A control device, characterized in that, comprising: at least one memory for storing program instructions; At least one processor is configured to call the program instructions stored in the memory, and execute the steps of the method according to any one of the preceding claims 1-5 according to the obtained program instructions. 10. A computer-readable storage medium on which a computer program is stored, characterized in that, when the computer program is executed by a processor, the steps of any one of the methods of claims 1-5 are implemented.

Images