Video quality evaluation method, device and computer readable storage medium

Abstract

The application discloses a video quality evaluation method and device and a computer readable storage medium. The method comprises the following steps: obtaining a video to be evaluated, performing frame splitting on the video to be evaluated, and obtaining a plurality of video frames to be evaluated, wherein each video frame to be evaluated comprises a number code; identifying the number code in each video frame to be evaluated to obtain number information of each video frame to be evaluated; determining a target reference video frame corresponding to each number information from a reference video frame based on the number information, wherein the reference video frame is a video frame obtained by adding a number code to an original video frame; performing image quality comparison on the video frame to be evaluated corresponding to each number information and the target reference video frame corresponding to each number information to obtain an image quality evaluation result corresponding to each number information; and determining a video quality evaluation result of the video to be evaluated based on the image quality evaluation result corresponding to each number information. The method can effectively improve the accuracy of video quality evaluation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of video processing, in particular to a video quality evaluation method and device and a computer readable storage medium. BACKGROUND

[0002] With the continuous development of Internet technology, daily life has become inseparable from the Internet. In the Internet era, with the continuous development of intelligent terminal technology and the continuous reduction of traffic cost, the form of information transmission is also undergoing great changes. Information transmission has gradually developed from traditional text transmission to a combination of text, pictures and video transmission. Among them, video has become the primary transmission method of current information transmission due to its large information transmission volume, rich content and diverse presentation.

[0003] Due to different video or live application encoding methods, the original video processed by the video application or live application will cause different degrees of quality loss. The industry often uses video quality evaluation methods to evaluate the quality of the video processed by the video application or live application to evaluate the video processing capability of the video application or live application and locate the quality problem. However, the current video quality evaluation method generally uses the comparison and evaluation based on the characteristics of the video frame image itself, which often causes difficulty in ensuring frame alignment due to the high similarity between the frame split images, and thus cannot guarantee accurate quality evaluation of the video. SUMMARY

[0004] The embodiments of the present application provide a video quality evaluation method, device and computer readable storage medium, which can effectively improve the accuracy of video quality evaluation.

[0005] The first aspect of the present application provides a video quality evaluation method, the method comprising:

[0006] Obtaining a video to be evaluated, and frame splitting the video to be evaluated to obtain a plurality of video frames to be evaluated, wherein each video frame to be evaluated contains a number barcode;

[0007] Identifying the number barcode in each video frame to be evaluated to obtain the number information of each video frame to be evaluated;

[0008] Determining the target reference video frame corresponding to each number information from the reference video frame based on the number information, wherein the reference video frame is a video frame obtained by adding a number barcode to an original video frame;

[0009] Comparing the image quality of each number information corresponding video frame to be evaluated and the corresponding target reference video frame to obtain the image quality evaluation result corresponding to each number information;

[0010] determine a video quality evaluation result of the video to be evaluated based on the image quality evaluation result corresponding to each numbering information.

[0011] Correspondingly, the second aspect of the present application provides a video quality evaluation device, the device comprising:

[0012] an acquisition unit configured to acquire a video to be evaluated and split frames of the video to be evaluated to obtain a plurality of video frames to be evaluated, wherein each of the video frames to be evaluated comprises a numbering barcode;

[0013] an identification unit configured to identify the numbering barcode in each of the video frames to be evaluated to obtain numbering information of each of the video frames to be evaluated;

[0014] a first determination unit configured to determine a target reference video frame corresponding to each numbering information from reference video frames based on the numbering information, wherein the reference video frames are video frames obtained by adding numbering barcodes to original video frames;

[0015] a comparison unit configured to compare the video frame to be evaluated corresponding to each numbering information with the target reference video frame corresponding thereto in terms of image quality to obtain an image quality evaluation result corresponding to each numbering information;

[0016] a second determination unit configured to determine a video quality evaluation result of the video to be evaluated based on the image quality evaluation result corresponding to each numbering information.

[0017] In some embodiments, the video quality evaluation device provided by the present application further comprises:

[0018] a first acquisition subunit configured to acquire an original video and split frames of the original video to obtain a plurality of original video frames;

[0019] an adding subunit configured to add a numbering barcode to each of the original video frames based on an order of each of the original video frames in the original video to obtain a reference video frame corresponding to each of the original video frames;

[0020] a generating subunit configured to generate a reference video according to the reference video frame corresponding to each of the original video frames and input the reference video into a video processing application to obtain an output video to be evaluated.

[0021] In some embodiments, the adding subunit comprises:

[0022] a numbering module configured to number the plurality of original video frames in order to obtain numbering information of each of the original video frames;

[0023] a generating module configured to generate a numbering barcode of each of the original video frames based on the numbering information of each of the original video frames;

[0024] an adding module, configured to add the number barcode of each original video frame into the corresponding original video frame to obtain a reference video frame corresponding to each original video frame.

[0025] In some embodiments, the generating module comprises:

[0026] a creating sub-module, configured to create a quick response matrix code object;

[0027] an adding sub-module, configured to add data to the quick response matrix code object according to the number information of each original video frame to obtain a target quick response matrix code object corresponding to each original video frame;

[0028] a generating sub-module, configured to generate the number barcode corresponding to each original video frame based on the target quick response matrix code object corresponding to each original video frame.

[0029] In some embodiments, the identifying unit comprises:

[0030] a clipping sub-unit, configured to clip the number barcode in each video frame to be evaluated to obtain a first number barcode image of each video frame to be evaluated;

[0031] a processing sub-unit, configured to perform pixel enhancement processing on the first number barcode image of each video frame to be evaluated to obtain a second number barcode image of each video frame to be evaluated;

[0032] an identifying sub-unit, configured to perform barcode identification on the second number barcode image of each video frame to be evaluated to obtain the number information of each video frame to be evaluated.

[0033] In some embodiments, the identifying sub-unit comprises:

[0034] a processing module, configured to perform gamma transformation processing on the pixel value of each pixel in the second number barcode image of each video frame to be evaluated to obtain a third number barcode image of each video frame to be evaluated;

[0035] an identifying module, configured to perform barcode identification on the third number barcode image of each video frame to be evaluated to obtain the number information of each video frame to be evaluated.

[0036] In some embodiments, the comparing unit comprises:

[0037] a first calculating sub-unit, configured to calculate the structural similarity between the video frame to be evaluated corresponding to each number information and the corresponding target reference video frame to obtain a first image quality evaluation result corresponding to each number information;

[0038] The second calculation sub-unit is configured to calculate a mean square error between the to-be-evaluated video frame corresponding to each numbering information and the target reference video frame corresponding to each numbering information.

[0039] The third calculation sub-unit is configured to calculate a peak signal-to-noise ratio based on the mean square error, to obtain a second image quality evaluation result corresponding to each numbering information.

[0040] The first determination sub-unit is configured to determine an image quality evaluation result corresponding to each numbering information according to the first image quality evaluation result corresponding to each numbering information and the second image quality evaluation result corresponding to each numbering information.

[0041] In some embodiments, the video quality evaluation apparatus provided in the present application further comprises:

[0042] The first elimination sub-unit is configured to eliminate the numbering bar code in the to-be-evaluated video frame corresponding to each numbering information, to obtain a to-be-evaluated image corresponding to each numbering information.

[0043] The second elimination sub-unit is configured to eliminate the numbering bar code in the target reference video frame corresponding to each numbering information, to obtain a reference image corresponding to each numbering information.

[0044] The first calculation sub-unit is further configured to:

[0045] calculate a structural similarity between the to-be-evaluated image corresponding to each numbering information and the reference image corresponding to each numbering information, to obtain the first image quality evaluation result corresponding to each numbering information.

[0046] The second calculation sub-unit is further configured to:

[0047] calculate a mean square error between the to-be-evaluated image corresponding to each numbering information and the reference image corresponding to each numbering information.

[0048] In some embodiments, the video quality evaluation apparatus provided in the present application further comprises:

[0049] The second determination sub-unit is configured to determine a target numbering information whose image quality evaluation score is lower than a preset value, according to the image quality evaluation result corresponding to each numbering information.

[0050] The second acquisition sub-unit is configured to acquire the to-be-evaluated image corresponding to each target numbering information and the reference image corresponding to each target numbering information.

[0051] The positioning sub-unit is configured to perform image processing problem positioning based on the to-be-evaluated image corresponding to each target numbering information and the reference image corresponding to each target numbering information, to determine a target problem of image processing.

[0052] In some embodiments, the video quality evaluation apparatus provided in the present application further comprises:

[0053] a comparison subunit, configured to compare the number information of each to-be-evaluated video frame with the number information of each original video frame to obtain number information of lost video frames;

[0054] a fourth calculation subunit, configured to calculate a frame loss rate based on a quantity of the number information of lost video frames and a quantity of the number information of original video frames.

[0055] In some embodiments, the video quality evaluation device provided in the present application further comprises:

[0056] a first sorting subunit, configured to sort the number information of each to-be-evaluated video frame according to an order of the to-be-evaluated video frames in the to-be-evaluated video to obtain a first sorting sequence;

[0057] a second sorting subunit, configured to sort the number information of each original video frame according to an order of the original video frames in the original video to obtain a second sorting sequence;

[0058] a detection subunit, configured to detect the first sorting sequence based on the second sorting sequence to obtain a detection result.

[0059] The third aspect of the present application further provides a computer readable storage medium, which stores a plurality of instructions, and the instructions are adapted to be loaded by a processor to execute steps in the video quality evaluation method provided in the first aspect of the present application.

[0060] The fourth aspect of the present application provides a computer device, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, and the processor implements steps in the video quality evaluation method provided in the first aspect of the present application when executing the computer program.

[0061] The fifth aspect of the present application provides a computer program product, which comprises computer programs / instructions, and the computer programs / instructions implement steps in the video quality evaluation method provided in the first aspect when executed by a processor.

[0062] The video quality evaluation method provided in the embodiments of the present application comprises the following steps: obtaining a video to be evaluated, performing frame splitting on the video to be evaluated, and obtaining a plurality of video frames to be evaluated, wherein each video frame to be evaluated comprises a number code; identifying the number code in each video frame to be evaluated, and obtaining number information of each video frame to be evaluated; determining a target reference video frame corresponding to each number information from reference video frames based on the number information, wherein the reference video frames are video frames obtained by adding a number code to original video frames; performing image quality comparison on the video frame to be evaluated corresponding to each number information and the target reference video frame corresponding to the number information, and obtaining an image quality evaluation result corresponding to each number information; and determining a video quality evaluation result of the video to be evaluated based on the image quality evaluation result corresponding to each number information.

[0063] Therefore, the video quality evaluation method provided in the present application can quickly and accurately determine the corresponding target reference video frame in the reference video frames according to the number code contained in the video frame to be evaluated, and determine the video quality evaluation result according to the comparison result of the target reference video frame and the video frame to be evaluated. The method can greatly improve the accuracy of video quality evaluation. BRIEF DESCRIPTION OF DRAWINGS

[0064] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0065] Figure 1A is a scene schematic diagram of video quality evaluation in the present application;

[0066] Figure 1B is another scene schematic diagram of video quality evaluation in the present application;

[0067] Figure 2 is a flow schematic diagram of the video quality evaluation method provided in the present application;

[0068] Figure 3A is an initial frame of the original video frame obtained by performing frame splitting on the original video;

[0069] Figure 3B is a number code generated based on the initial frame of the original video frame;

[0070] Figure 3Cis the initial frame of the reference video frame obtained by adding the number barcode of the initial frame of the original video frame to the initial frame of the original video frame;

[0071] Figure 4A is a target reference video frame corresponding to target number information whose image quality evaluation score is lower than a preset value;

[0072] Figure 4B is a to-be-evaluated video frame corresponding to the target number information;

[0073] Figure 5A is another flowchart of the video quality evaluation method provided by the present application;

[0074] Figure 5B is still another flowchart of the video quality evaluation method provided by the present application;

[0075] Figure 6 is a structural diagram of the video quality evaluation device provided by the present application;

[0076] Figure 7 is a structural diagram of the computer device provided by the present application. DETAILED DESCRIPTION

[0077] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0078] The embodiments of the present application provide a video quality evaluation method, device, computer readable storage medium and computer device. The video quality evaluation method can be used in a video quality evaluation device. The video quality evaluation device can be integrated in a computer device, which can be a terminal or a server. The terminal can be a mobile phone, a tablet computer, a notebook computer, a smart television, a wearable smart device, a personal computer (PC) and a vehicle-mounted terminal, etc. The server can be a standalone physical server, a server cluster or a distributed system composed of multiple physical servers, a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, network acceleration services (CDN), and basic cloud computing services such as big data and artificial intelligence platforms. The server can be a node in a blockchain.

[0079] Please refer toFigure 1A A scene diagram of a video quality evaluation method provided by the present application is shown in FIG. 1. As shown in the figure, a server A obtains a video to be evaluated from a terminal B, and performs frame splitting on the video to be evaluated to obtain a plurality of video frames to be evaluated, wherein each video frame to be evaluated contains a number barcode; the number barcode in each video frame to be evaluated is identified to obtain number information of each video frame to be evaluated; a target reference video frame corresponding to each number information is determined from reference video frames based on the number information, wherein the reference video frames are video frames obtained by adding number barcodes to original video frames; the video frame to be evaluated corresponding to each number information and the target reference video frame corresponding to the number information are compared in terms of image quality to obtain an image quality evaluation result corresponding to each number information; and a video quality evaluation result of the video to be evaluated is determined based on the image quality evaluation result corresponding to each number information. Then, the server A can further send the video quality evaluation result to the terminal B.

[0080] Please refer to Figure 1B Another scene diagram of a video quality evaluation provided by the present application is shown in FIG. 2. As shown in the figure, when a video quality evaluation is performed on a video processing application, a two-dimensional code can be added to an original video to obtain a processed two-dimensional code video; then, the two-dimensional code video with the added two-dimensional code can be uploaded to the video processing application to be evaluated to obtain a video to be evaluated output by the video processing application. Further, the video quality evaluation method provided by the present application can be used to perform a video quality evaluation on the video to be evaluated and the two-dimensional code video to obtain a video quality evaluation result.

[0081] It should be noted that Figure 1A and Figure 1B The scene diagrams of the video quality evaluation shown in FIGS. 1 and 2 are only two examples, and the scene of the video quality evaluation described in the embodiments of the present application is to more clearly illustrate the technical solutions of the present application, and does not constitute a limitation on the technical solutions provided by the present application. It can be known by those skilled in the art that, as the scene of the video quality evaluation evolves and new business scenes appear, the technical solutions provided by the present application are also applicable to similar technical problems.

[0082] Based on the above-mentioned implementation scene, the following will be described in detail.

[0083] In the related art, when evaluating the quality of a video, a full-reference video quality evaluation method is generally used to evaluate the quality of the video, which is generally converted into image quality evaluation, that is, the video is first de-framed, or referred to as frame splitting. Then the video frame to be evaluated and the original video frame are frame-aligned, and the image quality is calculated based on the frame-aligned image frame. Because the principle of image quality evaluation is to compare and calculate two pictures of the same scene, the accuracy of frame alignment is particularly important for image quality evaluation. Currently, the frame alignment test methods mainly include physical identification and code identification, wherein the physical identification is to make physical labels on the video frame, for example, using optical character recognition (OCR) to make labels. However, this method increases a lot of workload in the later stage of frame identification, and the OCR recognition is inaccurate in the case of video ghosting and high frame rate, and the high error rate of identification leads to the decrease of the accuracy of frame alignment. In addition, the image quality evaluation method based on the comparison of image features is difficult to guarantee the accuracy of frame alignment because the similarity between the de-framed image frames in the video scene is high, and thus the accurate video quality evaluation cannot be guaranteed. To solve the above problem of inaccurate video quality evaluation, the present application provides a video quality evaluation method to improve the accuracy of video quality evaluation.

[0084] Embodiments of the present application will be described from the perspective of a video quality evaluation device, which can be integrated in a computer device. The computer device can be a terminal or a server. The terminal can be a mobile phone, a tablet computer, a notebook computer, a smart television, a wearable smart device, a personal computer (PC), and a vehicle-mounted terminal, etc. The server can be a standalone physical server, a server cluster or a distributed system composed of multiple physical servers, a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery network (CDN), and basic cloud computing services such as big data and artificial intelligence platforms. As shown in the figure, the flowchart of the video quality evaluation method provided by the present application includes the following steps: Figure 2

[0085] In step 101, a video to be evaluated is obtained, and the video to be evaluated is frame-split to obtain multiple video frames to be evaluated.

[0086] ​The to-be-evaluated video can be a video processed by a video processing application. Generally, various video processing applications further process the original video uploaded to the application. Since the encoding manner and the set frame rate in the processing of the original video by the video processing application can be different from those of the original video, there can be frame loss, frame repetition, disorder, and picture quality change in the processing. In order to ensure the quality of the video presented to the audience by the video processing application, the video output by the video processing application needs to be evaluated. The evaluation of the video quality is actually the evaluation of the image quality. Specifically, the to-be-evaluated video output by the video processing application can be frame-aligned with the original video, and then the images in the frame intersection of the to-be-evaluated video and the original video are evaluated. In the embodiments of the present application, a unique frame alignment method is provided, which can align the frames according to the number barcodes in the video frames, thereby greatly improving the accuracy of frame alignment.

[0087] The to-be-evaluated video can be obtained from the to-be-evaluated video output by the video processing application client of the terminal loaded with the video processing application client, or from the to-be-evaluated video stored in the server. After obtaining the to-be-evaluated video, the to-be-evaluated video can be first de-framed, that is, the to-be-evaluated video is frame-split to split the to-be-evaluated video into multiple to-be-evaluated video frames. In the embodiments of the present application, each to-be-evaluated video frame obtained by splitting contains a number barcode.

[0088] In some embodiments, the to-be-evaluated video is obtained, and the to-be-evaluated video is frame-split to obtain multiple to-be-evaluated video frames, wherein each to-be-evaluated video frame contains a number barcode before.

[0089] 1. An original video is obtained, and the original video is frame-split to obtain multiple original video frames;

[0090] 2. A number barcode is added to each original video frame based on the order of each original video frame in the original video to obtain a reference video frame corresponding to each original video frame;

[0091] 3. A reference video is generated according to the reference video frame corresponding to each original video frame, and the reference video is input into the video processing application to obtain the output to-be-evaluated video.

[0092] In the embodiments of the present application, before obtaining the video to be evaluated, the original video corresponding to the video to be evaluated can be pre-processed. Specifically, the original video can be obtained first, and the original video can be frame-split to obtain multiple original video frames. Specifically, the original video can be split into 100 original video frames. The 100 original video frames can be numbered in order in the original video, and each original video frame has a corresponding number, which can be 0-99. Then, a number code can be added to each original video frame based on the order of each original video frame in the original video. The number code can be a one-dimensional code or a two-dimensional code, and the two-dimensional code can be a two-dimensional code. The number code added to each original video frame can be determined according to the number of the original video frame, and the original video frame with the number code added can be referred to as a reference video frame.

[0093] As shown in Figures 3A to 3C , it is a schematic diagram of adding a number code to an original video frame. Specifically, it is an initial frame of an original video frame obtained by frame-splitting the original video. As shown in Figure 3B , it is a number code generated for the initial frame of the original video frame. As shown in Figure 3C , it is an initial frame of a reference video frame obtained by adding the number code of the initial frame of the original video frame to the initial frame of the original video frame. Similarly, for other frames of the original video frame, a corresponding number code can also be generated accordingly, and the number code can be added to the corresponding video frame to obtain a corresponding reference video frame with the number code added.

[0094] After obtaining the reference video frame corresponding to each original video frame, multiple reference video frames can be combined into a video, which can be referred to as a reference video. The reference video can be used as the output of the video processing application and as the rating benchmark of the video to be evaluated output by the video processing application. After the reference video is input into the video processing application, the video to be evaluated output by the video processing application can be obtained. The video processing application can be a video playing application, a short video application, or a live broadcast application, which can collect, process, and play videos.

[0095] In the embodiments of the present application, the pre-processing of the original video can be performed by a video quality evaluation device or by other devices.

[0096] In some embodiments, based on the order of each original video frame in the original video, a number code is added to each original video frame to obtain a reference video frame corresponding to each original video frame, comprising:

[0097] 2.1, numbering multiple original video frames in order to obtain the number information of each original video frame;

[0098] 2.2, generating a number barcode of each original video frame based on the number information of each original video frame;

[0099] 2.3, adding the number barcode of each original video frame to the corresponding original video frame to obtain a reference video frame corresponding to each original video frame.

[0100] In the embodiments of the present application, the number barcode is added to each original video frame. The multiple original video frames can be numbered in sequence to obtain the number information of each original video frame. The sequence can be the playing sequence of the original video frames in the original video. Then, the number barcode of each original video frame can be generated based on the number information of each original video frame. The number barcode can be a two-dimensional code. The two-dimensional code generated according to the number information can be scanned and recognized to obtain the corresponding number information. After the number barcode corresponding to each original video frame is generated, the number barcode can be added to the corresponding original video frame to obtain a reference video frame corresponding to each original video frame.

[0101] In some embodiments, the number barcode of each original video frame is generated based on the number information of each original video frame, comprising:

[0102] 2.2.1, creating a quick response matrix code object;

[0103] 2.2.2, adding data to the quick response matrix code object one by one according to the number information of each original video frame to obtain a target quick response matrix code object corresponding to each original video frame;

[0104] 2.2.3, generating a number barcode corresponding to each original video frame based on the target quick response matrix code object corresponding to each original video frame.

[0105] In the embodiments of the present application, the number barcode of each original video frame is generated based on the number information of each original video frame. Specifically, a quick response matrix code (QRCode) object for generating a two-dimensional code can be created. Then, data can be added to the QRCode object one by one. The data added is the number information of each original video frame. Then, the number two-dimensional code corresponding to each original video frame can be further generated according to each target QRCode object to which data is added.

[0106] Step 102, identifying the number barcode in each video frame to be evaluated to obtain the number information of each video frame to be evaluated.

[0107] In the video quality evaluation process of the to-be-evaluated video, after the to-be-evaluated video is obtained and the to-be-evaluated video frame is split into a plurality of to-be-evaluated video frames, the number code in each to-be-evaluated video frame can be further recognized to obtain the number information contained in each to-be-evaluated video frame. The number code in each to-be-evaluated video frame can be recognized one by one according to the order of each to-be-evaluated video frame in the to-be-evaluated video.

[0108] In some embodiments, the number code in each to-be-evaluated video frame is recognized to obtain the number information of each to-be-evaluated video frame, including:

[0109] 1. The number code in each to-be-evaluated video frame is cropped to obtain a first number code image of each to-be-evaluated video frame;

[0110] 2. The first number code image of each to-be-evaluated video frame is subjected to pixel enhancement processing to obtain a second number code image of each to-be-evaluated video frame;

[0111] 3. The second number code image of each to-be-evaluated video frame is subjected to barcode recognition to obtain the number information of each to-be-evaluated video frame.

[0112] In the embodiments of the present application, when the number code in each to-be-evaluated video frame is recognized, the number code in each video frame can be first cropped to obtain a first number code pattern of each to-be-evaluated video frame. Then, the first number code image of each to-be-evaluated video frame that is cropped can be subjected to pixel enhancement processing to improve the clarity of the number code, thereby improving the accuracy of the recognition result obtained by recognizing the barcode image, and further improving the accuracy of frame alignment, so as to improve the accuracy of video quality evaluation. After the first number code pattern of each to-be-evaluated video frame is subjected to pixel enhancement processing, a second number code pattern of each to-be-evaluated video frame is obtained, and then the second number code pattern of each to-be-evaluated video frame can be further subjected to barcode recognition to obtain more accurate number information of each to-be-evaluated video frame. Specifically, the first number code pattern of each to-be-evaluated video frame can be enhanced by reserving the G channel of the pixels of the first number code pattern according to the RGB channel, and setting the other channels to white, thereby enhancing the contrast of the first number code pattern.

[0113] In some embodiments, the second number code image of each to-be-evaluated video frame is subjected to barcode recognition to obtain the number information of each to-be-evaluated video frame, including:

[0114] A. The pixel value of each pixel in the second number code image of each to-be-evaluated video frame is subjected to gamma transformation processing to obtain a third number code image of each to-be-evaluated video frame;

[0115] B. performing bar code recognition on the third numbered bar code image of each video frame to be evaluated to obtain numbered information of each video frame to be evaluated.

[0116] In the embodiment of the present application, after the first numbered bar code pattern of each video frame to be evaluated is enhanced to obtain the second numbered bar code pattern, the second numbered bar code pattern can be further processed to improve the definition. In the embodiment of the present application, the method for improving the definition can specifically adopt gamma change processing on the second numbered bar code pattern. Gamma change refers to power change on the pixel value of the second numbered bar code pattern, amplifying the pixel gray value difference, so that the details in the image are clearer. Thus, the accuracy of numbered bar code recognition can be further improved, and the accuracy of video quality evaluation can be further improved.

[0117] Step 103, determining the target reference video frame corresponding to each numbered information from the reference video frame based on the numbered information.

[0118] After the numbered bar code contained in each video frame to be evaluated is recognized to obtain the bar code information of each video frame to be evaluated, the video to be evaluated and the reference video can be frame-aligned according to the bar code information of each video frame to be evaluated, to obtain the frame intersection of the video to be evaluated and the reference video. Specifically, the numbered sequence composed of the numbered information of the video frame to be evaluated can be determined first, and then the numbered sequence can be de-duplicated to remove the duplicate numbered information. Then, the target reference video frame corresponding to each numbered information in the reference video can be further determined according to the numbered information in the de-duplicated numbered sequence. Further, the video frame to be evaluated and the target reference video frame with the same numbered information can be combined to form an evaluation frame group, to complete the frame alignment of the video to be evaluated and the reference video.

[0119] In the embodiment of the present application, the two-dimensional code with more convenient recognition and high recognition accuracy is used to identify the video frame, so that the accuracy of frame alignment can be greatly improved, and the accuracy of video quality evaluation can be improved.

[0120] Step 104, performing image quality comparison on the video frame to be evaluated corresponding to each numbered information and the target reference video frame corresponding to each numbered information to obtain the image quality evaluation result corresponding to each numbered information.

[0121] After the video frame to be evaluated corresponding to each numbered information and the target reference video frame corresponding to each numbered information are determined, i.e., after the evaluation frame group corresponding to each numbered information is determined, the image quality of each video frame to be evaluated can be further evaluated according to the evaluation frame group corresponding to each numbered information, to obtain the image quality evaluation result corresponding to each numbered information.

[0122] In some embodiments, the image quality of the to-be-evaluated video frame corresponding to each numbering information and the corresponding target reference video frame is compared to obtain an image quality evaluation result corresponding to each numbering information, including:

[0123] 1. Structural similarity between the to-be-evaluated video frame corresponding to each numbering information and the corresponding target reference video frame is calculated to obtain a first image quality evaluation result corresponding to each numbering information;

[0124] 2. Mean square error between the to-be-evaluated video frame corresponding to each numbering information and the corresponding target reference video frame is calculated;

[0125] 3. Peak signal to noise ratio is calculated based on the mean square error to obtain a second image quality evaluation result corresponding to each numbering information;

[0126] 4. The image quality evaluation result corresponding to each numbering information is determined according to the first image quality evaluation result corresponding to each numbering information and the second image quality evaluation result corresponding to each numbering information.

[0127] In the embodiments of the present application, the image quality is evaluated, and two indexes of structural similarity (SSIM) and peak signal to noise ratio (PSNR) can be used for evaluation. That is, the structural similarity between the to-be-evaluated video frame corresponding to each numbering information and the corresponding target reference video frame is calculated to obtain a first image quality evaluation result corresponding to each numbering information. Then, the mean square error between the to-be-evaluated video frame corresponding to each numbering information and the corresponding target reference video frame is calculated, and the peak signal to noise ratio corresponding to each numbering information is further calculated according to the mean square error, which is used as a second image quality evaluation result corresponding to each numbering information. Finally, the image quality evaluation result of the to-be-evaluated video frame corresponding to each numbering information is calculated according to the first image quality evaluation result and the second image quality evaluation result corresponding to each numbering information. Specifically, the first image quality evaluation result and the second image quality evaluation result corresponding to each numbering information are weighted and calculated with a certain weight to obtain an image quality evaluation score of the to-be-evaluated video frame corresponding to each numbering information.

[0128] In some embodiments, before the structural similarity between the to-be-evaluated video frame corresponding to each numbering information and the corresponding target reference video frame is calculated to obtain a first image quality evaluation result corresponding to each numbering information, the method further includes:

[0129] A. The numbering bar code in the to-be-evaluated video frame corresponding to each numbering information is removed to obtain a to-be-evaluated image corresponding to each numbering information;

[0130] B. Remove the barcode from the target reference video frame corresponding to each number information to obtain the reference image corresponding to each number information;

[0131] Calculate the structural similarity between the video frame to be evaluated and the corresponding target reference video frame for each number information to obtain the first image quality evaluation result for each number information, including:

[0132] C. Calculate the structural similarity between the image to be evaluated and the corresponding reference image for each number information to obtain the first image quality evaluation result for each number information;

[0133] Calculate the mean square error between the video frame to be evaluated and the corresponding target reference video frame for each number information, including:

[0134] D. Calculate the mean square error between the image to be evaluated and the corresponding reference image for each numbered information.

[0135] In this embodiment, to further improve the accuracy of image quality evaluation results, before performing image quality evaluation, the barcodes in the video frames to be evaluated and the target reference video frames in each evaluation frame group can be removed. Then, image quality evaluation is performed based on the video frames to be evaluated and the target reference video frames after removing the barcodes. Specifically, the barcodes in the video frames to be evaluated corresponding to each number information can be removed first to obtain the image to be evaluated corresponding to each number information; then, the barcodes in the target reference video frames corresponding to each number information can be removed to obtain the reference image corresponding to each number information. Then, the SSIM value and PSNR value between the image to be evaluated and the reference image corresponding to each number information are calculated respectively. Finally, the image quality evaluation result corresponding to the video frame to be evaluated for each number information is calculated based on the SSIM value and PSNR value of each number information.

[0136] In some embodiments, the video quality evaluation method provided in this application may further include:

[0137] a. Determine the target number information whose image quality evaluation score is lower than the preset value based on the image quality evaluation result corresponding to each number information;

[0138] b. Obtain the image to be evaluated and the corresponding reference image for each target number;

[0139] c. Based on the image to be evaluated and the corresponding reference image for each target number, locate the image processing problem and determine the target problem of image processing.

[0140] In the embodiments of the present application, after determining the image quality evaluation score of each numbered information corresponding to the to-be-evaluated video frame, the image quality evaluation score of each to-be-evaluated video frame can be compared with a preset score value respectively. When the image quality evaluation score is lower than the preset value, the to-be-evaluated video frame can be determined as a video frame with abnormal quality. At this time, the target numbered information with the image quality evaluation score lower than the preset value can be obtained, and the to-be-evaluated image and the reference image corresponding to the numbered information are further obtained, and then the image processing problem positioning is performed based on the to-be-evaluated image and the corresponding reference image, and the target problem existing in the image processing is located.

[0141] As shown in Figures 4A to 4B , it is a schematic diagram of the image processing problem positioning provided in the present application. Among them Figure 4A is the target reference video frame corresponding to the target numbered information with the image quality evaluation score lower than the preset value, Figure 4B is the to-be-evaluated video frame corresponding to the aforementioned target numbered information. As shown in the figure, the content displayed in the display area 11 of the target reference video frame 10 is obviously more than the content displayed in the corresponding display area 21 of the to-be-evaluated video frame 20; similarly, the content displayed in the display area 12 of the target reference video frame 10 is obviously more than the content displayed in the corresponding display area 22 of the to-be-evaluated video frame 20. Therefore, it can be determined that the video processing application has cropped the target reference video frame corresponding to the target numbered information when performing video processing. Further, since the target reference video frame 10 and the to-be-evaluated video frame 20 have the same pixels, it can be determined that the video processing application has further enlarged after cropping the target reference video frame. Therefore, the target problem of image processing can be located as the video processing application has cropped and enlarged part of the image, resulting in a serious decline in the image quality of these images. Therefore, targeted modification can be made for this part of the problem to improve the image quality evaluation score, and thus the video quality evaluation score can be improved.

[0142] In step 105, the video quality evaluation result of the to-be-evaluated video is determined based on the image quality evaluation result corresponding to each numbered information.

[0143] Among them, after determining the image quality evaluation result corresponding to each numbered information, the video quality evaluation result of the to-be-evaluated video can be further determined according to the image quality evaluation result corresponding to each numbered information. Specifically, the image quality evaluation score corresponding to each numbered information can be weighted and calculated by a preset weight coefficient to obtain the video quality evaluation score of the to-be-evaluated video.

[0144] In some embodiments, the video quality evaluation method provided in the present application can further include:

[0145] 1. Comparing the number information of each to-be-evaluated video frame and the number information of each original video frame to obtain the number information of lost video frames;

[0146] 2. Calculating the frame loss rate based on the number of the number information of lost video frames and the number of the number information of original video frames.

[0147] In the embodiments of the present application, the video quality of the to-be-evaluated video can also be evaluated from the dimension of the frame loss rate. Specifically, after obtaining the number information of all to-be-evaluated video frames, the number information of all to-be-evaluated video frames is grouped into a first number information set. Then, the number information of all original video frames is grouped into a second number information set. Further, the first number information set and the second number information set can be compared to obtain a third number information set of the number information of lost video frames. The number information belonging to the second number information set but not belonging to the first number information set is the number information of lost video frames. Specifically, for example, there are 100 number information in the second number information set, and there are 80 number information in the first number information set, then 20 video frames are lost, and the frame loss rate is 20%.

[0148] In some embodiments, the video quality evaluation method provided by the present application can further include:

[0149] A. The number information of each to-be-evaluated video frame is sorted according to the order of the to-be-evaluated video frame in the to-be-evaluated video to obtain a first sorting sequence;

[0150] B. The number information of each original video frame is sorted according to the order of the original video frame in the original video to obtain a second sorting sequence;

[0151] C. The first sorting sequence is detected based on the second sorting sequence to obtain a detection result.

[0152] In the embodiments of the present application, whether the video frames are out of order can also be further used as an index for video quality evaluation. Specifically, the sorting sequence of the original video frame can be determined first, which can be recorded as the second sorting sequence. When the number information of each to-be-evaluated video frame is obtained, the number information of each to-be-evaluated video frame can be sorted based on the sorting order of each to-be-evaluated video frame in the to-be-evaluated video to obtain a first sorting sequence. Then, the first sorting sequence can be detected based on the second sorting sequence to determine whether the arrangement order of the number information in the first sorting sequence is consistent with the sorting order of the number information in the second sorting sequence. When the sorting order of the number information in the first sorting sequence is inconsistent with the sorting order of the number information in the second sorting sequence, it is determined that the to-be-detected video has an out-of-order problem.

[0153] According to the above description, the video quality evaluation method provided in the embodiments of the present application can obtain a video to be evaluated, and frame splitting is performed on the video to be evaluated to obtain a plurality of video frames to be evaluated, wherein each video frame to be evaluated contains a number barcode; the number barcode in each video frame to be evaluated is identified to obtain the number information of each video frame to be evaluated; the target reference video frame corresponding to each number information is determined from the reference video frame based on the number information, wherein the reference video frame is a video frame obtained by adding a number barcode to an original video frame; the image quality evaluation result corresponding to each number information is obtained by performing image quality comparison on the video frame to be evaluated corresponding to each number information and the target reference video frame corresponding thereto; and the video quality evaluation result of the video to be evaluated is determined based on the image quality evaluation result corresponding to each number information.

[0154] Therefore, the video quality evaluation method provided in the present application can add a number barcode to each video frame of an original video in advance to obtain a reference video, so that each video frame to be evaluated in the video to be evaluated obtained by processing the reference video using a video processing application contains a number barcode. In this way, when the video to be evaluated is evaluated, the corresponding target reference video frame can be accurately determined in the reference video frame according to the number barcode contained in the video frame to be evaluated, and the video quality evaluation result can be determined according to the comparison result of the target reference video frame and the video frame to be evaluated. The method can greatly improve the accuracy of video quality evaluation.

[0155] The present application also provides a video quality evaluation method, which can be used in a computer device, which can be a terminal or a server. As shown in Figure 5A The method specifically includes the following steps:

[0156] In step 201, the computer device obtains an original video, and frame splitting is performed on the original video to obtain a plurality of original video frames.

[0157] After obtaining the original video, the computer device can perform frame splitting on the original video, that is, the original video is cut into a plurality of original video frames. The original video can be cut into a plurality of original video frames by using a lossless cutting method. Specifically, in the embodiments of the present application, FFmpeg cutting or Python+OpenCV cutting can be used, and the picture format of the original video frame obtained by cutting can be png format. FFmpeg is a set of open source computer programs that can be used to record, convert digital audio, video, and convert them into streams. Python is a computer programming language that provides efficient high-level data structures and can be easily and effectively object-oriented. OpenCV is a cross-platform computer vision and machine learning software library.

[0158] Step 202, the computer device numbers the plurality of original video frames, and generates a two-dimensional code corresponding to each original video frame based on the number of each original video frame.

[0159] After cutting the original video into a plurality of original video frames, the computer device can further number the plurality of original video frames. Specifically, the number of each original video frame can be determined according to the order of the original video frame in the original video. After determining the number of each original video frame, a two-dimensional code corresponding to each original video frame can be further generated according to the number of each original video frame.

[0160] The step of generating a two-dimensional code corresponding to each original video frame according to the number of each original video frame can specifically include:

[0161] 1. Create a QRCode object;

[0162] 2. Add data using the add_data() function, where the added data is the number of each original video frame;

[0163] 3. Create a two-dimensional code using the make_image() function (return an im type picture object)

[0164] 4. Automatically open the picture using the im_show() function.

[0165] The function includes the following parameters, respectively:

[0166] Version (version): This parameter is an integer ranging from 1 to 40, indicating the size of the two-dimensional code (the minimum value is 1, which is a 12x12 matrix). If you want the program to automatically generate, you can set the value to None and use the fit=True parameter.

[0167] Error correction (error_correction): This parameter identifies the error correction range of the two-dimensional code, and can select the following four constants:

[0168] (1). ERROR_CORRECT_L, indicating that errors below 7% will be corrected

[0169] (2). ERROR_CORRECT_M (default), indicating that errors below 15% will be corrected

[0170] (3). ERROR_CORRECT_Q, indicating that errors below 25% will be corrected

[0171] (4). ERROR_CORRECT_H, indicating that errors below 30% will be corrected

[0172] boxsize: This parameter represents the number of pixels in each dot (box)

[0173] border: This parameter represents the distance between the two-dimensional code and the image peripheral border, and the default value is 4.

[0174] The size of the two-dimensional code can be selected as 64x64 units, and is placed at a position with a coordinate of 64 times division. A block-level coding unit of High Efficiency Video Coding (HEVC) is used to minimize the impact on coding efficiency.

[0175] The frame number of the video frame after frame deinterlacing is an incremental number, and therefore the content of the two-dimensional code is the same number as the frame number. The same number of two-dimensional codes as the number of original video frames is generated to identify the video frames. The generated two-dimensional code information can be referred to as two-dimensional code numbering, and the two-dimensional code number mentioned herein has this meaning.

[0176] In step 203, the computer device adds the two-dimensional code corresponding to each original video frame to the corresponding original video frame to obtain a plurality of two-dimensional code video frames.

[0177] After generating the two-dimensional code corresponding to each original video frame, the generated two-dimensional code can be further pasted into the corresponding original video frame to obtain a video frame with a pasted two-dimensional code, which can be referred to as a two-dimensional code video frame here. Then, the video frame with the pasted two-dimensional code is synthesized into a video, which can be referred to as a two-dimensional code video here. The video frame with the pasted two-dimensional code can also be synthesized to generate a two-dimensional code video using FFmpeg or OpenCV.

[0178] In step 204, the computer device inputs the two-dimensional code video into a video application to obtain a to-be-compared video output by the video application.

[0179] After the computer device generates the two-dimensional code video, the two-dimensional code video can be further input into a video application, and a to-be-compared video is output after the generated two-dimensional code video is processed by the video application. The to-be-compared video is a video to be detected for video quality. The video application can be a video number, a short video application, a video playback application, or a live broadcast application, and the like, which can collect, process, and play a video.

[0180] In step 205, the computer device deinterlaces the to-be-compared video to obtain a plurality of to-be-compared video frames.

[0181] After the video application outputs the to-be-compared video, the computer device can further deinterlace the to-be-compared video to obtain a plurality of to-be-compared video frames. The deinterlacing of the to-be-compared video can be performed by using the aforementioned lossless frame cutting method.

[0182] In step 206, the computer device crops the two-dimensional code in each to-be-compared video frame to obtain a two-dimensional code image of each to-be-compared video frame.

[0183] In the angle of video frames, the two-dimensional code corresponding to each video frame before and after the video application processing is consistent. Therefore, the key to frame alignment is to analyze the two-dimensional code information on the to-be-compared video frame. In the embodiment of the present application, after the to-be-compared video is de- framed to obtain a plurality of to-be-compared video frames, the two-dimensional code in each to-be-compared video frame can be cropped to obtain a two-dimensional code image of each to-be-compared video frame. Then the two-dimensional code image is further analyzed to obtain the serial number information of each to-be-compared video frame.

[0184] In step 207, the computer device performs pixel enhancement and clarity enhancement processing on the two-dimensional code image of each to-be-compared video frame to obtain a target two-dimensional code image of each to-be-compared video frame.

[0185] In the embodiment of the present application, after the computer device crops the two-dimensional code image from each to-be-compared video frame, the two-dimensional code image in each to-be-compared video frame can be further subjected to pixel enhancement and clarity enhancement processing. The pixel enhancement refers to reserving the G channel of the pixel of the two-dimensional code information of the cropped two-dimensional code image according to the RGB channel, and setting the other channels to white [255, 255, 255], so as to enhance the contrast of the two-dimensional code image. The clarity enhancement processing refers to enlarging the pixel gray value difference, so that the details in the image are clearer. The present application can use gamma transformation, which performs power transformation on the pixel value, mainly changes the gray level of the image, and the conversion principle formula is as follows:

[0186] O(x, y) = I(x, y) γ

[0187] Where O(x, y) is the output pixel value, and I(x, y) is the input pixel value.

[0188] In step 208, the computer device performs two-dimensional code recognition on the target two-dimensional code image of each to-be-compared video frame to obtain the serial number information of each to-be-compared video frame.

[0189] Wherein, after the two-dimensional code image of each to-be-compared video frame is cropped, the pixel of the two-dimensional code image is enhanced, and the definition of the two-dimensional code image is improved, the target two-dimensional code image of each to-be-compared video frame obtained by processing can be further subjected to two-dimensional code recognition to obtain the number information of each to-be-compared video frame. Since the video application is used to process the two-dimensional code video, due to the different encoding modes and frame rates, there is a difference between the number information of the to-be-compared video frame obtained by cutting the to-be-compared video after processing and the number information of the original video frame.

[0190] Step 209, the computer device determines the frame loss rate of the to-be-compared video according to the difference between the number information of each to-be-compared video frame and the number information of the original video frame.

[0191] After the number information of each to-be-compared video frame is obtained by recognizing the two-dimensional code image of each to-be-compared video frame, the number sequence of the to-be-compared video frame and the number sequence of the original video frame can be compared, and the frame loss and the frame loss rate can be determined according to the difference between the two.

[0192] Wherein, the number sequence of the original video frame can be represented as:

[0193] [{frames(i):QR_frames(i),{frames(i+1):QR_frames(i

[0194] +1),……{frames(i):QR_frames(iR_frames(num_in))}]

[0195] Wherein, 0≤i≤num_in, num_in is the number of original video frames, that is, the length of the number sequence of the original video frame.

[0196] The number sequence of the to-be-compared video frame can be represented as:

[0197] [{frames(i′+1):QR_frames(j),{frames(i′+1):QR_frames(j),……{frames(a):QR_frames(b)}]

[0198] Wherein, 0≤i′≤a; 0≤j≤b; 0≤a≤num_in; 0≤b≤num_in. Since there may be repeated frames, missing frames, and out-of-order frames in the to-be-compared video frame, a and b are often not equal.

[0199] After the number sequence of the to-be-compared video frame and the number sequence of the original video frame are determined, the number information of the missing video frame can be determined according to the comparison result of the two number sequences, and the number of missing video frames and the frame loss rate can be determined.

[0200] Specifically, the difference set of the two number sequences can obtain the number information of the missing frames. The difference set here refers to the elements in the number sequence of the original video frames but not in the number sequence of the to-be-contrasted video frames. Specifically, it is expressed as follows:

[0201]

[0202] Wherein, A is the number sequence of the original video frames, and B is the number sequence of the to-be-contrasted video frames.

[0203] The formula of the frame loss rate is as follows:

[0204]

[0205] Wherein, len_missing_frames is the number of the missing video frames.

[0206] Wherein, in some cases, it can also be judged whether there is a repeated frame in the to-be-contrasted video frames. When there is a repeated frame, the repetition rate can also be calculated. Specifically, the frequency of the elements in the number sequence B of the to-be-contrasted video frames can be counted. If the frequency is greater than 1, the two-dimensional code number is a repeated frame. The number of repeated frames is count_repeat. And the repeated frames are recorded to facilitate positioning the problem.

[0207] Wherein, the formula for calculating the repetition rate is as follows:

[0208]

[0209] Step 210, the computer device determines the out-of-order situation of the to-be-contrasted video according to the sorting order of the number information of each to-be-contrasted video frame and the sorting order of the number information of the original video frames.

[0210] Further, after determining the number sequence of the to-be-contrasted video frames and the number sequence of the original video frames, it can be further judged whether the to-be-contrasted video frames exist out-of-order situation according to the number sequence of the original video frames.

[0211] Step 211, the computer device performs frame alignment on the to-be-contrasted video and the two-dimensional code video according to the number information of each to-be-contrasted video frame to obtain the frame intersection.

[0212] Wherein, after determining the number information of each to-be-contrasted video frame, the to-be-contrasted video and the aforementioned two-dimensional code video can be aligned based on the number information of each to-be-contrasted video frame. Specifically, before performing frame alignment, the number information of each to-be-contrasted video frame can also be de-duplicated to remove the number information of the repeated video frames.

[0213] Based on the serial number information of each video frame to be compared, the video to be compared and the QR code video are frame aligned. Specifically, this can be done by identifying target QR code video frames from the QR code video frames that have the same serial number information as each video frame to be compared, and grouping the QR code video frames with the same serial number information and the video frames to be compared into a frame group. Multiple frame groups constitute the frame intersection. The frame intersection can be specifically represented as:

[0214] A∩B={QR_frames(x)|QR_frames(x)∈A, and QR_frames(x)∈B}.

[0215] Once the frame intersection is obtained, frame alignment is achieved.

[0216] Step 212: The computer device calculates the structural similarity and peak signal-to-noise ratio of each video frame to be compared based on the frame intersection.

[0217] After determining the frame intersection, the SSIM value and PSNR value can be calculated for each frame group in the frame intersection. The formula for calculating the SSIM value of each frame group is as follows:

[0218] SSIM(x, y) = [l(x, y)] α [c(x, y)] β [s(x, y)] γ ,

[0219]

[0220] Where l(x, y) represents the brightness of x and y, c(x, y) represents the contrast of x and y, s(x, y) represents the structure of x and y, α > 0, β > 0, γ > 0, and μ are parameters that adjust the relative importance of l(x, y), c(x, y), and s(x, y). x and μ y , σ x and σ y The mean and standard deviation of x and y are respectively, σ xy Let C1, C2, and C3 be the covariances of x and y, respectively. C1, C2, and C3 are constants. These are used to maintain the stability of l(x, y), c(x, y), and s(x, y).

[0221] The formula for calculating the PSNR of each frame group is as follows:

[0222]

[0223] Wherein, MSE is the mean square error between the video frame to be compared and the corresponding QR code video frame in each frame group, specifically expressed as follows:

[0224]

[0225] where MAX is the maximum possible pixel value of the entire picture. I is the maximum possible pixel value of the entire picture.

[0226] In step 213, the computer device determines the video quality evaluation result of the video to be compared according to the frame loss rate, the out-of-order situation, and the structural similarity and peak signal-to-noise ratio of each frame to be compared.

[0227] After the SSIM and PSNR values of each frame group are calculated, the video quality evaluation result of the video to be compared can be determined by comprehensively considering the frame loss rate, the out-of-order situation, the repeated frame situation, and the SSIM and PSNR data of the frames to be compared in the frame exchange, so as to obtain a more accurate video quality evaluation result.

[0228] Please refer to Figure 5B Another flowchart of the video evaluation method provided in the present application is shown in FIG. 6. As shown in the figure, when video quality evaluation of a video processing application is needed, the original video can be obtained first, and then the original video is frame-split to obtain a plurality of original video frames. Then, the plurality of original video frames can be further sorted and numbered, and a number two-dimensional code corresponding to each original video frame is generated. Then, the number two-dimensional code of each original video frame is added to the corresponding video frame to obtain a plurality of two-dimensional code video frames, and the plurality of two-dimensional code video frames are synthesized into a two-dimensional code video. Further, the two-dimensional code video can be input into the video processing application for processing to obtain a video to be evaluated output by the video processing application. Then, the video to be evaluated can be further frame-split to obtain a plurality of video frames to be evaluated, and then the two-dimensional code contained in each video frame to be evaluated is identified, and the video frame to be evaluated and the two-dimensional code video frame are frame-aligned according to the identification result. In the frame alignment process, the video evaluation results of the video to be processed after being processed by the video processing application, such as the frame loss rate, the repeated frame rate, and whether the video frames exist out-of-order problems, can be obtained. For the two-dimensional code video frame and the video frame to be evaluated obtained by frame alignment, the structural similarity score and the peak signal-to-noise ratio score can be further calculated as the video evaluation result of the video to be evaluated.

[0229] As described above, the video quality evaluation method provided in this application involves acquiring a video to be evaluated and splitting it into multiple video frames, each containing a unique barcode. The barcode in each video frame is then identified to obtain its unique identifier. Based on this identifier, a target reference video frame is determined from the reference video frames corresponding to each unique identifier. The reference video frame is obtained by adding a unique barcode to the original video frame. Image quality is compared between the video frame to be evaluated and the corresponding target reference video frame for each unique identifier to obtain an image quality evaluation result. Finally, the video quality evaluation result for the video to be evaluated is determined based on the image quality evaluation result for each unique identifier.

[0230] Therefore, the video quality evaluation method provided in this application obtains a reference video by pre-adding a numbered barcode to each frame of the original video. This ensures that each frame of the video to be evaluated, after processing by a video processing application, contains a numbered barcode. Thus, when evaluating the video to be evaluated, the corresponding target reference video frame can be quickly and accurately determined from the reference video frames based on the numbered barcodes contained in the video frames to be evaluated. The video quality evaluation result is then determined based on the comparison between the target reference video frame and the video frames to be evaluated. This method can significantly improve the accuracy of video quality evaluation.

[0231] To better implement the above video quality evaluation method, this application also provides a video quality evaluation device, which can be integrated into a terminal or server.

[0232] For example, such as Figure 6 The diagram shown is a structural schematic of a video quality evaluation device provided in an embodiment of this application. The video quality evaluation device may include an acquisition unit 301, an identification unit 302, a first determination unit 303, a comparison unit 304, and a second determination unit 305, as follows:

[0233] The acquisition unit 301 is used to acquire the video to be evaluated and split the video to be evaluated into multiple video frames to be evaluated, wherein each video frame to be evaluated contains a numbered barcode.

[0234] The identification unit 302 is used to identify the number barcode in each video frame to be evaluated, and obtain the number information of each video frame to be evaluated.

[0235] The first determining unit 303 is used to determine the target reference video frame corresponding to each number information from the reference video frames based on the number information. The reference video frame is a video frame obtained by adding a number barcode to the original video frame.

[0236] The comparison unit 304 is configured to compare the to-be-evaluated video frame corresponding to each numbering information with the corresponding target reference video frame in image quality, to obtain an image quality evaluation result corresponding to each numbering information.

[0237] The second determination unit 305 is configured to determine a video quality evaluation result of the to-be-evaluated video based on the image quality evaluation result corresponding to each numbering information.

[0238] In some embodiments, the video quality evaluation device provided in the present application further comprises:

[0239] The first obtaining subunit is configured to obtain an original video, and split the original video into a plurality of original video frames;

[0240] The adding subunit is configured to add a numbering barcode to each original video frame based on the sequence of each original video frame in the original video, to obtain a reference video frame corresponding to each original video frame;

[0241] The generating subunit is configured to generate a reference video according to the reference video frame corresponding to each original video frame, and input the reference video into a video processing application to obtain an output to-be-evaluated video.

[0242] In some embodiments, the adding subunit comprises:

[0243] The numbering module is configured to number the plurality of original video frames in sequence, to obtain numbering information of each original video frame;

[0244] The generating module is configured to generate a numbering barcode of each original video frame based on the numbering information of each original video frame;

[0245] The adding module is configured to add the numbering barcode of each original video frame to the corresponding original video frame, to obtain a reference video frame corresponding to each original video frame.

[0246] In some embodiments, the generating module comprises:

[0247] The creating sub-module is configured to create a quick response matrix code object;

[0248] The adding sub-module is configured to add data to the quick response matrix code object one by one according to the numbering information of each original video frame, to obtain a target quick response matrix code object corresponding to each original video frame;

[0249] The generating sub-module is configured to generate a numbering barcode corresponding to each original video frame based on the target quick response matrix code object corresponding to each original video frame.

[0250] In some embodiments, the identifying unit comprises:

[0251] a cropping subunit configured to crop the number bar in each to-be-evaluated video frame to obtain a first number bar image of each to-be-evaluated video frame;

[0252] a processing subunit configured to perform pixel enhancement processing on the first number bar image of each to-be-evaluated video frame to obtain a second number bar image of each to-be-evaluated video frame;

[0253] a recognition subunit configured to perform bar code recognition on the second number bar image of each to-be-evaluated video frame to obtain number information of each to-be-evaluated video frame.

[0254] In some embodiments, the recognition subunit includes:

[0255] a processing module configured to perform gamma transformation processing on a pixel value of each pixel in the second number bar image of each to-be-evaluated video frame to obtain a third number bar image of each to-be-evaluated video frame;

[0256] a recognition module configured to perform bar code recognition on the third number bar image of each to-be-evaluated video frame to obtain number information of each to-be-evaluated video frame.

[0257] In some embodiments, the comparison unit includes:

[0258] a first calculation subunit configured to calculate a structural similarity between the to-be-evaluated video frame corresponding to each number information and the target reference video frame corresponding to the number information to obtain a first image quality evaluation result corresponding to each number information;

[0259] a second calculation subunit configured to calculate a mean square error between the to-be-evaluated video frame corresponding to each number information and the target reference video frame corresponding to the number information;

[0260] a third calculation subunit configured to calculate a peak signal-to-noise ratio based on the mean square error to obtain a second image quality evaluation result corresponding to each number information;

[0261] a first determination subunit configured to determine an image quality evaluation result corresponding to each number information according to the first image quality evaluation result corresponding to each number information and the second image quality evaluation result corresponding to each number information.

[0262] In some embodiments, the video quality evaluation device provided in the present application further includes:

[0263] a first elimination subunit configured to eliminate the number bar in the to-be-evaluated video frame corresponding to each number information to obtain a to-be-evaluated image corresponding to each number information;

[0264] a second elimination subunit configured to eliminate the number bar in the target reference video frame corresponding to each number information to obtain a reference image corresponding to each number information.

[0265] The first calculation subunit is further configured to:

[0266] calculate a structural similarity between the to-be-evaluated image corresponding to each numbering information and the corresponding reference image, to obtain a first image quality evaluation result corresponding to each numbering information;

[0267] The second calculation subunit is further configured to:

[0268] calculate a mean square error between the to-be-evaluated image corresponding to each numbering information and the corresponding reference image.

[0269] In some embodiments, the video quality evaluation apparatus provided in the present application further includes:

[0270] The second determination subunit is configured to determine target numbering information with an image quality evaluation score lower than a preset value according to the image quality evaluation result corresponding to each numbering information;

[0271] The second acquisition subunit is configured to acquire the to-be-evaluated image corresponding to each target numbering information and the corresponding reference image;

[0272] The positioning subunit is configured to perform image processing problem positioning based on the to-be-evaluated image corresponding to each target numbering information and the corresponding reference image, to determine a target problem of image processing.

[0273] In some embodiments, the video quality evaluation apparatus provided in the present application further includes:

[0274] The comparison subunit is configured to compare the numbering information of each to-be-evaluated video frame with the numbering information of each original video frame, to obtain numbering information of lost video frames;

[0275] The fourth calculation subunit is configured to calculate a frame loss rate based on the number of numbering information of lost video frames and the number of numbering information of original video frames.

[0276] In some embodiments, the video quality evaluation apparatus provided in the present application further includes:

[0277] The first sorting subunit is configured to sort the numbering information of each to-be-evaluated video frame according to the order of the to-be-evaluated video frame in the to-be-evaluated video, to obtain a first sorting sequence;

[0278] The second sorting subunit is configured to sort the numbering information of each original video frame according to the order of the original video frame in the original video, to obtain a second sorting sequence;

[0279] The detection subunit is configured to perform order detection on the first sorting sequence based on the second sorting sequence, to obtain a detection result.

[0280] In practice, the above units can be implemented as independent entities, or combined as the same or several entities, and the implementation of the above units can refer to the method embodiments above, which will not be repeated here.

[0281] According to the above description, the video quality evaluation device provided by the embodiment of the application can obtain the video to be evaluated by the obtaining unit 301, and perform frame splitting on the video to be evaluated to obtain a plurality of video frames to be evaluated, wherein each video frame to be evaluated contains a number barcode; the identification unit 302 identifies the number barcode in each video frame to be evaluated to obtain the number information of each video frame to be evaluated; the first determination unit 303 determines the target reference video frame corresponding to each number information from the reference video frame based on the number information, wherein the reference video frame is the video frame obtained by adding the number barcode to the original video frame; the comparison unit 304 compares the image quality of the video frame to be evaluated corresponding to each number information and the corresponding target reference video frame to obtain the image quality evaluation result corresponding to each number information; and the second determination unit 305 determines the video quality evaluation result of the video to be evaluated based on the image quality evaluation result corresponding to each number information.

[0282] Therefore, the video quality evaluation method provided by the application can add the number barcode to each video frame of the original video in advance to obtain the reference video, so that each video frame to be evaluated in the video to be evaluated obtained by processing the reference video by the video processing application contains the number barcode. In this way, when the video to be evaluated is evaluated, the corresponding target reference video frame can be accurately determined in the reference video frame according to the number barcode contained in the video frame to be evaluated, and the video quality evaluation result can be determined according to the comparison result of the target reference video frame and the video frame to be evaluated. The method can greatly improve the accuracy of video quality evaluation.

[0283] The embodiment of the application also provides a computer device, which can be a terminal or a server, as shown in Figure 7 The computer device provided by the application is a structural schematic diagram of the computer device. Specifically:

[0284] The computer device can include a processing unit 401 with one or more processing cores, a storage unit 402 with one or more storage media, a power module 403, and an input module 404. Those skilled in the art can understand that the computer device structure shown in Figure 7 does not constitute a limitation on the computer device, and can include more or fewer components than shown, or combine certain components, or different component arrangements. Among them:

[0285] The processing unit 401 is the control center of the computer device, and connects various parts of the computer device through various interfaces and lines, and performs various functions and processes data of the computer device by running or executing software programs and / or modules stored in the storage unit 402 and calling data stored in the storage unit 402. Optionally, the processing unit 401 can include one or more processing cores; preferably, the processing unit 401 can integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, the object interface and the application program, etc., and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor can also not be integrated into the processing unit 401.

[0286] The storage unit 402 can be used to store software programs and modules, and the processing unit 401 executes various functions and data processing by running the software programs and modules stored in the storage unit 402. The storage unit 402 can mainly include a program storage area and a data storage area, wherein the program storage area can store the operating system, at least one application program required by the function (such as sound playing function, image playing function and web page access, etc.), etc.; the data storage area can store data created according to the use of the computer device, etc. In addition, the storage unit 402 can include a high-speed random access memory, and can also include a non-volatile memory, for example, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state memory device. Accordingly, the storage unit 402 can also include a memory controller to provide access of the processing unit 401 to the storage unit 402.

[0287] The computer device further includes a power module 403 for supplying power to various components, and preferably, the power module 403 can be logically connected to the processing unit 401 through a power management system, so as to realize the functions of managing charging, discharging and power consumption management, etc. through the power management system. The power module 403 can also include one or more than one direct current or alternating current power supply, a recharging system, a power failure detection circuit, a power converter or inverter, a power state indicator and any other components.

[0288] The computer device can also include an input module 404, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to object settings and function control.

[0289] Although not shown, the computer device can also include a display unit and the like, which will not be described here. Specifically in the present embodiment, the processing unit 401 in the computer device will load the executable file corresponding to the process of one or more application programs into the storage unit 402 according to the following instructions, and run the application program stored in the storage unit 402 by the processing unit 401, thereby realizing various functions, as follows:

[0290] The video to be evaluated is acquired, and frame splitting is performed on the video to be evaluated to obtain a plurality of video frames to be evaluated, wherein each video frame to be evaluated contains a numbered barcode; the numbered barcode in each video frame to be evaluated is identified to obtain numbered information of each video frame to be evaluated; a target reference video frame corresponding to each numbered information is determined from reference video frames based on the numbered information, the reference video frame being a video frame obtained by adding a numbered barcode to an original video frame; the video frame to be evaluated corresponding to each numbered information and the corresponding target reference video frame are subjected to image quality comparison to obtain an image quality evaluation result corresponding to each numbered information; and a video quality evaluation result of the video to be evaluated is determined based on the image quality evaluation result corresponding to each numbered information.

[0291] It should be noted that the computer device provided by the embodiments of the present application and the method in the above embodiments belong to the same concept, and the specific implementation of each operation can be referred to the previous embodiments, which will not be described here.

[0292] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions, or by related hardware controlled by the instructions, which can be stored in a computer readable storage medium and loaded and executed by a processor.

[0293] To this end, the embodiments of the present application provide a computer readable storage medium, which stores a plurality of instructions, the instructions can be loaded by a processor to execute the steps in any one of the methods provided by the embodiments of the present application. For example, the instructions can execute the following steps:

[0294] The video to be evaluated is acquired, and frame splitting is performed on the video to be evaluated to obtain a plurality of video frames to be evaluated, wherein each video frame to be evaluated contains a numbered barcode; the numbered barcode in each video frame to be evaluated is identified to obtain numbered information of each video frame to be evaluated; a target reference video frame corresponding to each numbered information is determined from reference video frames based on the numbered information, the reference video frame being a video frame obtained by adding a numbered barcode to an original video frame; the video frame to be evaluated corresponding to each numbered information and the corresponding target reference video frame are subjected to image quality comparison to obtain an image quality evaluation result corresponding to each numbered information; and a video quality evaluation result of the video to be evaluated is determined based on the image quality evaluation result corresponding to each numbered information.

[0295] The specific implementation of each operation can refer to the foregoing embodiments, which will not be repeated here.

[0296] The computer readable storage medium can include a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0297] The computer readable storage medium stores instructions, and the instructions can execute the steps in any method provided by the embodiments of the present application, thus achieving the beneficial effects of any method provided by the embodiments of the present application. Details are described in the foregoing embodiments, which will not be repeated here.

[0298] According to an aspect of the present application, a computer program product or computer program is provided, which includes computer instructions stored in a storage medium. A processor of a computer device reads the computer instructions from the storage medium, and the processor executes the computer instructions to enable the computer device to perform the method provided in any optional implementation manner of the video quality evaluation method.

[0299] The video quality evaluation method, device and computer readable storage medium provided by the embodiments of the present application are described in detail above, and the principles and implementation manners of the present application are described by applying specific examples. The foregoing embodiment is only used to help understand the method and core idea of the present application; meanwhile, for those skilled in the art, the specific implementation manner and application range can be changed according to the idea of the present application. In conclusion, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A video quality evaluation method, characterized in that, The method includes: The video to be evaluated is obtained, and the video to be evaluated is split into frames to obtain multiple video frames to be evaluated, wherein each video frame to be evaluated contains a numbered barcode. The process involves identifying the numbered barcode in each video frame to be evaluated to obtain the numbering information for each video frame, including: cropping the numbered barcode in each video frame to obtain a first numbered barcode image for each video frame; retaining the G channel of the pixels in the first numbered barcode image according to the RGB channels, and setting the other channels to white to obtain a second numbered barcode image for each video frame; and performing barcode recognition on the second numbered barcode image for each video frame to obtain the numbering information for each video frame. The frame drop rate of the video to be evaluated is determined based on the difference between the numbering information of each video frame to be evaluated and the numbering information of the original video frames; the disorder status of the video to be evaluated is determined based on the sorting order of the numbering information of each video frame to be evaluated and the sorting order of the numbering information of the original video frames; and the duplication rate is calculated based on whether there are duplicate frames between the numbering information of each video frame to be evaluated and the numbering information of the original video frames. Determining the target reference video frame corresponding to each number information from the reference video frames based on the number information includes: first determining a number sequence composed of the number information of the video frames to be evaluated, and deduplicating the number sequence; determining the target reference video frame corresponding to each number information in the reference video one by one according to the number information in the deduplicated number sequence; forming an evaluation frame group by combining the video frames to be evaluated and the target reference video frames with the same number information; wherein the reference video frame is a video frame obtained by adding a number barcode to the original video frame. The barcodes in the video frames to be evaluated corresponding to each number information are removed to obtain the image to be evaluated corresponding to each number information; the barcodes in the target reference video frames corresponding to each number information are removed to obtain the reference image corresponding to each number information. Image quality comparison is performed on the video frame to be evaluated and the corresponding target reference video frame for each number information to obtain the image quality evaluation result for each number information. The video quality evaluation result for the video to be evaluated is determined based on the image quality evaluation result corresponding to each number information. Obtain the target number information whose image quality evaluation score is lower than the preset value, and obtain the image to be evaluated and the reference image corresponding to the target number information; If the content displayed in the display area of ​​the reference image is more than the content displayed in the corresponding display area of ​​the image to be evaluated, then it is determined that the video processing application has cropped the target reference video frame corresponding to the target number information during video processing; furthermore, if the reference image and the image to be evaluated have the same number of pixels, then it is determined that the video processing application has also enlarged the target reference video frame after cropping it.

2. The method according to claim 1, characterized in that, Before acquiring the video to be evaluated and splitting it into multiple video frames to be evaluated, wherein each video frame contains a numbered barcode, the process further includes: The original video is acquired, and the original video is split into multiple original video frames. Based on the order of each original video frame in the original video, a numbered barcode is added to each original video frame to obtain the reference video frame corresponding to each original video frame. A reference video is generated based on the reference video frame corresponding to each original video frame, and the reference video is input into the video processing application to obtain the output video to be evaluated.

3. The method according to claim 2, characterized in that, The step of adding a numbered barcode to each original video frame based on the order of each original video frame in the original video to obtain a reference video frame corresponding to each original video frame includes: The multiple original video frames are numbered sequentially to obtain the numbering information for each original video frame; A barcode for each original video frame is generated based on the numbering information of each original video frame. Add the barcode number of each original video frame to the corresponding original video frame to obtain the reference video frame corresponding to each original video frame.

4. The method according to claim 3, characterized in that, A barcode for each original video frame is generated based on its serial number information, including: Create a fast response matrix graphic object; Data is added to the fast response matrix code object one by one according to the number information of each original video frame to obtain the target fast response matrix code object corresponding to each original video frame. Generate a numbered barcode for each original video frame based on the target fast response matrix barcode object corresponding to each original video frame.

5. The method according to claim 1, characterized in that, The step of performing barcode recognition on the second numbered barcode image of each video frame to be evaluated to obtain the numbering information of each video frame to be evaluated includes: Perform gamma transformation on the pixel value of each pixel in the second numbered barcode image of each video frame to be evaluated to obtain the third numbered barcode image of each video frame to be evaluated. Barcode recognition is performed on the third barcode image of each video frame to be evaluated to obtain the number information of each video frame to be evaluated.

6. The method according to claim 1, characterized in that, The step of comparing the image quality of the video frame to be evaluated and the corresponding target reference video frame corresponding to each number information to obtain the image quality evaluation result corresponding to each number information includes: Calculate the structural similarity between the video frame to be evaluated and the corresponding target reference video frame corresponding to each number information to obtain the first image quality evaluation result corresponding to each number information; Calculate the mean square error between the video frame to be evaluated and the corresponding target reference video frame for each number information; The peak signal-to-noise ratio is calculated based on the mean square error to obtain the second image quality evaluation result corresponding to each number information; The image quality evaluation result corresponding to each number information is determined based on the first image quality evaluation result corresponding to each number information and the second image quality evaluation result corresponding to each number information.

7. The method according to claim 6, characterized in that, The step of calculating the structural similarity between the video frame to be evaluated and the corresponding target reference video frame corresponding to each number information to obtain the first image quality evaluation result corresponding to each number information includes: Calculate the structural similarity between the image to be evaluated and the corresponding reference image for each number information to obtain the first image quality evaluation result for each number information; The calculation of the mean square error between the video frame to be evaluated and the corresponding target reference video frame for each number information includes: Calculate the mean square error between the image to be evaluated and the corresponding reference image for each numbered information.

8. The method according to claim 3, characterized in that, The step of determining the frame drop rate of the video to be evaluated based on the difference between the numbering information of each video frame to be evaluated and the numbering information of the original video frames includes: The numbering information of each video frame to be evaluated is compared with the numbering information of each original video frame to obtain the numbering information of the lost video frames. The frame loss rate is calculated based on the number of lost video frame numbers and the number of original video frame numbers.

9. The method according to claim 8, characterized in that, The step of determining the disorder of the videos to be evaluated based on the sorting order of the numbering information of each video frame to be evaluated and the sorting order of the numbering information of the original video frames includes: The numbering information of each video frame to be evaluated is sorted according to the order of the video frames to be evaluated in the video to be evaluated, to obtain a first sorting sequence; The numbering information of each original video frame is sorted according to the order of the original video frames in the original video to obtain the second sorting sequence; The first sorted sequence is subjected to sequence detection based on the second sorted sequence to obtain the detection result.

10. A video quality evaluation device, characterized in that, The device includes: The acquisition unit is used to acquire the video to be evaluated and to split the video to be evaluated into multiple video frames to be evaluated, wherein each video frame to be evaluated contains a numbered barcode. The identification unit is used to identify the numbered barcode in each video frame to be evaluated to obtain the numbering information of each video frame to be evaluated, including: cropping the numbered barcode in each video frame to be evaluated to obtain a first numbered barcode image of each video frame to be evaluated; retaining the G channel of the pixels in the first numbered barcode image according to the RGB channel and setting the other channels to white to obtain a second numbered barcode image of each video frame to be evaluated; and performing barcode recognition on the second numbered barcode image of each video frame to be evaluated to obtain the numbering information of each video frame to be evaluated. The processing unit is used to determine the frame drop rate of the video to be evaluated based on the difference between the numbering information of each video frame to be evaluated and the numbering information of the original video frames; to determine the disorder status of the video to be evaluated based on the sorting order of the numbering information of each video frame to be evaluated and the sorting order of the numbering information of the original video frames; and to calculate the duplication rate based on whether there are duplicate frames between the numbering information of each video frame to be evaluated and the numbering information of the original video frames. The first determining unit is configured to determine a target reference video frame corresponding to each number information from the reference video frames based on the number information, including: first determining a number sequence composed of the number information of the video frames to be evaluated, and deduplicating the number sequence; determining the target reference video frame corresponding to each number information in the reference video frame according to the number information in the deduplicated number sequence; and forming an evaluation frame group by combining the video frames to be evaluated and the target reference video frames with the same number information; wherein the reference video frame is a video frame obtained by adding a number barcode to the original video frame. The first elimination subunit is used to eliminate the numbered barcode in the video frame to be evaluated corresponding to each numbered information, so as to obtain the image to be evaluated corresponding to each numbered information. The second removal subunit is used to remove the numbered barcodes in the target reference video frame corresponding to each numbered information to obtain the reference image corresponding to each numbered information. The comparison unit is used to perform image quality comparison between the video frame to be evaluated and the corresponding target reference video frame corresponding to each number information, and to obtain the image quality evaluation result corresponding to each number information. The second determining unit is used to determine the video quality evaluation result of the video to be evaluated based on the image quality evaluation result corresponding to each number information. The analysis module is used to obtain target ID information whose image quality evaluation score is lower than a preset value, and to obtain the image to be evaluated and the reference image corresponding to the target ID information; if the content displayed in the display area of ​​the reference image is more than the content displayed in the corresponding display area of ​​the image to be evaluated, it is determined that the video processing application has cropped the target reference video frame corresponding to the target ID information during video processing; furthermore, if the reference image and the image to be evaluated have the same number of pixels, it is determined that the video processing application has also enlarged the target reference video frame after cropping it.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a plurality of instructions adapted for loading by a processor to perform the steps of the video quality evaluation method according to any one of claims 1 to 9.

12. A computer device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the video quality evaluation method according to any one of claims 1 to 9.

13. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps in the video quality evaluation method according to any one of claims 1 to 9.

Images