Video transcoding quality evaluation system and method

Abstract

The embodiment of the invention discloses a video transcoding quality evaluation system and method, and the system comprises a data collection module which is used for collecting video data from a video transcoding service; the data processing module is used for selecting a test video, performing video scoring processing and judging whether an alarm is needed or not; and the data storage module is used for acquiring and storing the data processing result and the corresponding video information and storing the data processing result and the corresponding video information. According to the method, visual evaluation of manual spot check watching can be replaced, the labor cost is saved, the evaluation efficiency and the evaluation accuracy are improved, and evaluation service is provided for mass video transcoding; improved data support can be provided for a transcoding system, multi-dimensional comprehensive evaluation is realized, and continuous improvement and training of a video transcoding algorithm are assisted.

Description

Technical Field

[0001] The present invention relates to the field of image and video, and particularly to a video transcoding quality evaluation system and method, which can evaluate the quality of the transcoded video, analyze the video quality situation, and be used to assist the continuous improvement of video transcoding algorithms. Background Art

[0002] With the development of 5G and high-speed wired / wireless networks, high-quality videos have become an important medium for content display at the application layer. Due to different user network conditions and interface sizes, the same video source often requires transcoding services with different bitrates and resolutions to match different application scenarios. In order to continuously improve video transcoding services, it is necessary to evaluate the quality of video transcoding. However, there is no mature system for evaluating the quality of video transcoding in the prior art, and usually the quality of the transcoded video is evaluated by human eye observation. This method cannot cover most videos, and the subjective evaluation method for individuals is relatively strong and the accuracy is poor.

[0003] In addition, for long and medium-length transcoded videos, there will be a situation where the video quality is relatively poor during a certain period of the video. At present, there is no system to support the analysis of the location of the part with video quality deviation.

[0004] Furthermore, for the transcoding project of the company's massive videos, there is no mature evaluation system, and it cannot give the impact of transcoding parameters on the quality of the output video and the advantages and disadvantages of the output video.

[0005] That is, for the evaluation of video transcoding service quality, how to provide an automatically running, mature, and highly matching video transcoding quality evaluation system has become a technical problem that needs to be solved urgently in the prior art. Summary of the Invention

[0006] In view of this, the embodiments of the present invention provide a video transcoding quality evaluation system and method, which can evaluate the quality of online transcoded videos, replace the intuitive evaluation of manual spot-check viewing, save labor costs, improve the efficiency and accuracy of evaluation, and automatically evaluate the video from multiple dimensions to assist the training of transcoding algorithms.

[0007] A video transcoding quality evaluation system includes:

[0008] A data acquisition module, configured to collect video data from video transcoding services;

[0009] A data processing module, including a video scoring sub-module and a result processing sub-module, is used to select test videos from the collected video data according to decision configuration rules, and send the selected test videos to the video scoring sub-module. The video scoring sub-module is used to perform video scoring processing on the test videos to obtain video scoring results, and send the results to the result processing sub-module. The result processing sub-module is used to obtain the alarm flag corresponding to the video by integrating the video scoring results and the decision configuration rules;

[0010] A data storage module is used to obtain the data processing results of the data processing module and the corresponding video information, and save them.

[0011] Optionally, in the data processing module, the decision configuration rules include video duration, the sampling rate and passing score corresponding to the video duration.

[0012] Optionally, in the data processing module, the video scoring includes one or more of PSNR scoring, SSIM scoring, and comprehensive scoring.

[0013] Optionally, in the data storage module, the video information includes: video name, video transcoding duration, and video transcoding parameters; the data processing results include video scoring results and alarm flags.

[0014] Optionally, there is also a data display module, which is used to graphically display the data processing results and video information in the data storage module. The graphical display includes one or more of line charts, bar charts, and pie charts.

[0015] Optionally, an alarm module 50 is used to obtain the alarm flag and provide it to the staff. The sending methods include one or more of text messages, emails, or instant messaging software.

[0016] Optionally, the decision configuration rules are adjusted according to the data processing results; and / or,

[0017] The data processing results can be provided to the transcoding service provider.

[0018] The present invention further discloses a method for evaluating video transcoding quality, including the following steps:

[0019] A data collection step, which is used to collect video data from video transcoding services;

[0020] A data processing step, for selecting a test video from the collected video data according to the decision configuration rule, and using the selected test video in a video scoring substep, wherein the video scoring substep is used to perform video scoring processing on the test video to obtain a video scoring result, and the result is used in a result processing substep, wherein the result processing substep is used to obtain an alarm mark of the corresponding video by combining the video scoring result and the decision configuration rule;

[0021] The data storage step is used to obtain the data processing results of the data processing step and the corresponding video information, and save them.

[0022] Optionally, it further includes a data display step for graphically displaying the data processing results and video information in the data storage step S130, wherein the graphical display includes one or more of a line graph, a bar graph, and a pie chart; and / or,

[0023] The alarm step S150 is used to obtain the alarm sign and provide it to the staff, and the sending method includes one or more of text messages, emails or instant messaging software.

[0024] The present invention also discloses a storage medium for storing computer executable instructions, wherein the computer executable instructions execute the above-mentioned video transcoding quality evaluation method when executed by a processor.

[0025] In summary, the present invention has the following advantages:

[0026] 1) Evaluate the quality of online transcoded videos, replacing intuitive evaluation by manual spot checks, saving labor costs, improving evaluation efficiency and accuracy, and providing evaluation services for massive video transcoding;

[0027] 2) It can detect the location of quality deviation after transcoding of medium and long videos, accurately locate the deviation, provide video elements and deviation scores at the deviation location, provide improved data support for the transcoding system, and realize multi-dimensional comprehensive evaluation.

[0028] 3) It can conduct 24-hour uninterrupted evaluation on massive transcoded videos, and combine video transcoding parameters to show the impact of different transcoding parameters on the quality of videos with different resolutions. It can also provide data to the transcoding system to optimize the transcoding algorithm, engineer video evaluation, and save human evaluation costs.

[0029] 4) This system is combined with the transcoding system to open up data transmission, and as an auxiliary function of the transcoding system, it provides test support for the optimized transcoding algorithm, and transmits the test data back to the transcoding system as data support for algorithm training, providing a test function for video transcoding and assisting the continuous improvement and training of the video transcoding algorithm. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Through the following description of the embodiments of the present invention with reference to the accompanying drawings, the above and other objects, features, and advantages of the present invention will become clearer. In the drawings:

[0031] Figure 1 is a module diagram of a video transcoding quality evaluation system according to a specific embodiment of the present invention;

[0032] Figure 2 is a data flow diagram of a video transcoding quality evaluation system according to a specific embodiment of the present invention;

[0033] Figure 3 is a flowchart of a video transcoding quality evaluation method according to a specific embodiment of the present invention. Detailed Embodiments

[0034] The following is a description of the present application based on embodiments, but the present application is not limited to these embodiments. In the following detailed description of the present application, some specific details are described in detail. Those skilled in the art can fully understand the present application without the description of these details. In order to avoid obscuring the essence of the present application, well-known methods, processes, flows, components, and circuits are not described in detail.

[0035] In addition, those of ordinary skill in the art should understand that the accompanying drawings provided herein are for illustrative purposes only, and the drawings are not necessarily drawn to scale.

[0036] Unless the context clearly requires otherwise, words such as "including" and "comprising" in the entire application document should be interpreted as having an inclusive meaning rather than an exclusive or exhaustive meaning; that is, it is the meaning of "including but not limited to".

[0037] In the description of the present application, it should be understood that terms such as "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance. In addition, in the description of the present application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0038] The main idea of the present invention is as follows: A data acquisition module is set up to collect video streams from the transcoding service; the data processing module is used to sample and select videos according to pre-set rules, score the selected videos using a scoring rule, and perform data processing on the scoring results; finally, the obtained results are saved in the data storage module, and the scoring results are respectively used for subsequent display, decision-making adjustment, and transcoding improvement, so as to realize the 24-hour uninterrupted quality evaluation of the transcoded videos online and provide data support for video transcoding improvement.

[0039] Specifically, refer to Figure 1 and Figure 2, respectively showing the module diagram and data flow diagram of the video transcoding quality evaluation system of the present invention. The video transcoding quality evaluation system includes:

[0040] A data acquisition module 10, configured to acquire video data from a video transcoding service;

[0041] In the present invention, the video transcoding service (Video Transcoding Service) refers to converting a compressed and encoded video bitstream into another video bitstream to adapt to different network bandwidths, different terminal processing capabilities, and different user requirements. Different bitrate and resolution video data can be obtained in this service.

[0042] A data processing module 20, including a video scoring sub-module and a result processing sub-module, configured to select a test video from the acquired video data according to a decision configuration rule, and send the selected test video to the video scoring sub-module. The video scoring sub-module 21 is configured to perform video scoring processing on the test video to obtain a video scoring result, and send the result to the result processing sub-module 22. The result processing sub-module 22 is configured to obtain an alarm flag corresponding to the video by integrating the video scoring result and the decision configuration rule.

[0043] In one embodiment, if the video scoring result for a certain 60S video is 70 points, while the passing score for videos of this duration is 85 points, then an alarm flag is assigned to this video.

[0044] Among them, the decision configuration rule includes the video duration, the sampling rate corresponding to this video duration, and the passing score, that is, the lowest allowable score.

[0045] In a specific embodiment, the sampling rate for videos with 1S < duration ≤ 60S is 20%, the sampling rate for videos with 60S < duration ≤ 300S is 25%, and the sampling rate for videos with duration > 300S is 15%.

[0046] The decision configuration rule is only an example and can be configured according to user needs. And in the present invention, it can be adjusted according to the feedback information of the scoring result. For example, for some videos with low scoring quality, the sampling intensity is increased until the required quality inspection standard is reached.

[0047] The video scoring includes one or more of: PSNR scoring, SSIM scoring, and comprehensive scoring.

[0048] The comprehensive scoring can be a score obtained by integrating multiple scores in the prior art. For example, it is the average of the PSNR score and the SSIM score.

[0049] The data storage module 30 is used to obtain the data processing results of the data processing module 20, as well as the corresponding video information, and save them.

[0050] In a specific embodiment, the video information includes: video name, video transcoding duration, and video transcoding parameters; the data processing results include video scoring results and alarm flags.

[0051] The alarm flag indicates whether an alarm should be issued for this video. For example, when the data bit is 0, it means that this video meets the transcoding service standard; when the data bit is 1, it means that this video should issue a warning.

[0052] Furthermore, the present invention also has a data display module 40, which is used to graphically display the data processing results and video information in the data storage module 30. The graphical display includes various types such as line charts, bar charts, and pie charts.

[0053] The alarm module 50 is used to obtain the alarm flag and provide it to the staff. The sending methods include various information transmission modes such as text messages, emails, or instant messaging software.

[0054] Among them, the alarm flag can be obtained from the data processing service. And since the results of the data processing service are stored in the data storage, therefore, the alarm flag can also be obtained from the data storage. The present invention includes but is not limited to the above two obtaining methods, as long as the alarm flag can be obtained and provided to the staff.

[0055] The data stored in the data storage module 30 of the present invention can also be used for the improvement and iteration of video transcoding.

[0056] In a specific embodiment, the decision configuration rule is adjusted according to the data processing results.

[0057] In another specific embodiment, the data processing results can be provided to the transcoding service provider to optimize the transcoding model and improve the video transcoding service.

[0058] Furthermore, referring to Figure 3 , the present invention discloses a method for evaluating the quality of video transcoding, including the following steps:

[0059] The data acquisition step S110 is used to collect video data from the video transcoding service;

[0060] In the present invention, the Video Transcoding Service refers to converting a compressed and encoded video stream into another video stream to adapt to different network bandwidths, different terminal processing capabilities, and different user requirements, and different bitrate and resolution video data can be obtained in this service.

[0061] The data processing step S120 is used to select a test video from the collected video data according to the decision configuration rule, and use the selected test video in the video scoring sub-step S121. The video scoring sub-step S121 is used to perform video scoring processing on the test video to obtain a video scoring result, and use the result in the result processing sub-step S122. The result processing sub-step S122 is used to obtain the alarm flag corresponding to the video by integrating the video scoring result and the decision configuration rule.

[0062] In one embodiment, if the video scoring result for a certain 60S video is 70 points, while the passing score for videos of this duration is 85 points, then an alarm flag is assigned to this video.

[0063] Among them, the decision configuration rule includes the video duration, the sampling rate corresponding to this video duration, and the passing score.

[0064] In a specific embodiment, the sampling rate for videos with 1S < duration ≤ 60S is 20%, the sampling rate for videos with 60S < duration ≤ 300S is 25%, and the sampling rate for videos with duration > 300S is 15%.

[0065] The decision configuration rule is only an example and can be configured according to user needs. And in the present invention, it can be adjusted according to the feedback information of the scoring result. For example, for some videos with low scoring quality, the sampling intensity is increased until the required quality inspection standard is reached.

[0066] The video scoring includes one or more of: PSNR scoring, SSIM scoring, and comprehensive scoring.

[0067] The comprehensive scoring can be a score obtained by integrating multiple scores in the prior art. For example, it is the average of the PSNR score and the SSIM score.

[0068] The data storage step S130 is used to obtain the data processing result of the data processing step S120 and the corresponding video information, and save them.

[0069] In a specific embodiment, the video information includes: video name, video transcoding duration, and video transcoding parameters; the data processing result includes the video scoring result and the alarm flag.

[0070] The alarm flag refers to whether an alarm should be issued for the video. For example, when the data bit is 0, it means the video meets the transcoding service standard; when the data bit is 1, it means a warning should be issued for the video.

[0071] Furthermore, the present invention further has a data display step S140 for graphically displaying the data processing result and video information in the data storage step S130. The graphical display includes various types such as line charts, bar charts, pie charts, etc.

[0072] The alarm step S150 is used to obtain the alarm flag in the data processing result and provide it to the staff. The sending methods include various information transmission modes such as text messages, emails, or instant messaging software.

[0073] Among them, the alarm flag can be obtained from the result of the data processing step. Since the result of the data processing step is stored in the data storage step S130, the alarm flag can also be obtained from the data storage step S130. The present invention includes but is not limited to the above two obtaining methods, as long as the alarm flag can be obtained and provided to the staff.

[0074] The data stored in the data storage step S130 of the present invention can also be used for the improvement and iteration of video transcoding.

[0075] In a specific embodiment, the decision configuration rule is adjusted according to the data processing result.

[0076] In another specific embodiment, the data processing result can be provided to the transcoding service provider to optimize the transcoding model and improve the video transcoding service.

[0077] The present invention further discloses a storage medium for storing computer-executable instructions, and the computer-executable instructions execute the above video transcoding quality evaluation method when executed by a processor.

[0078] Therefore, the present invention has the following advantages:

[0079] 1) Evaluate the quality of online transcoded videos, replacing the intuitive evaluation of manual spot-check viewing, saving labor costs, improving the efficiency and accuracy of evaluation, and providing evaluation services for massive video transcoding;

[0080] 2) It can find the positions where quality deviations occur after transcoding of medium and long videos, accurately locate the deviations, provide video elements and deviation scores at the deviation positions, and provide data support for improvement to the transcoding system, realizing multi-dimensional comprehensive evaluation.

[0081] 3) It can conduct continuous 24-hour evaluation on a large number of transcoded videos, display the impact of different transcoding parameters on the video quality of different resolutions in combination with video transcoding parameters, and provide the data to the transcoding system to optimize the transcoding algorithm, engineering the video evaluation process and saving the human evaluation cost.

[0082] 4) Through this system, it connects the data transmission in combination with the transcoding system, provides test support for the optimized transcoding algorithm as an auxiliary function of the transcoding system, and feeds back the test data to the transcoding system as data support for algorithm training, providing a test function for video transcoding and assisting in the continuous improvement and training of the video transcoding algorithm.

[0083] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a device (equipment), or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can be implemented as a computer program product on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0084] The present application is described with reference to the flowcharts of methods, devices (equipment), and computer program products according to the embodiments of the present application. It should be understood that each process in the flowchart can be implemented by computer program instructions.

[0085] These computer program instructions can be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including an instruction device that implements the process Figure 1 specified functions in one or more of the processes.

[0086] These computer program instructions can also be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices produce a device for implementing the Figure 1 specified functions in one or more of the processes.

[0087] Another embodiment of the present invention relates to a non-volatile storage medium for storing a computer-readable program, and the computer-readable program is used for a computer to execute the above-mentioned partial or all method embodiments.

[0088] That is, those skilled in the art can understand that all or part of the steps in the methods of the above embodiments can be implemented by specifying relevant hardware through a program. The program is stored in a storage medium and includes several instructions to enable a device (which can be a single-chip microcomputer, a chip, etc.) or a processor to execute all or part of the steps of the methods described in the embodiments of the present application. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs.

[0089] The foregoing are only the preferred embodiments of the present application and are not intended to limit the present application. For those skilled in the art, various modifications and changes can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. A video transcoding quality evaluation system, characterized in that, including: A data acquisition module, configured to acquire video data from a video transcoding service; A data processing module, including a video scoring sub-module and a result processing sub-module, configured to select a test video from the acquired video data according to decision configuration rules, and send the selected test video to the video scoring sub-module. The video scoring sub-module is configured to perform video scoring processing on the test video to obtain a video scoring result, and send the result to the result processing sub-module. The result processing sub-module is configured to obtain an alarm flag for the corresponding video by synthesizing the video scoring result and the decision configuration rules; A data storage module, configured to obtain the data processing result of the data processing module and the corresponding video information, and save them.

2. The video transcoding quality evaluation system according to claim 1, wherein: In the data processing module, the decision configuration rules include video duration, the sampling rate corresponding to the video duration, and the passing score.

3. The video transcoding quality evaluation system according to claim 1, wherein: In the data processing module, the video scoring includes one or more of PSNR scoring, SSIM scoring, and comprehensive scoring.

4. The video transcoding quality evaluation system according to any one of claims 1-3, wherein: In the data storage module, the video information includes: video name, video transcoding duration, and video transcoding parameters; the data processing result includes a video scoring result and an alarm flag.

5. The video transcoding quality evaluation system according to claim 4, wherein: It further has a data display module, configured to graphically display the data processing result and the video information in the data storage module. The graphical display includes one or more of line charts, bar charts, and pie charts.

6. The video transcoding quality evaluation system according to claim 4, wherein: An alarm module 50, configured to obtain the alarm flag and provide it to the staff. The sending methods include one or more of text messages, emails, or instant messaging software.

7. The video transcoding quality evaluation system according to claim 4, wherein: The decision configuration rules are adjusted according to the data processing result; and / or, The data processing result can be provided to the transcoding service provider.

8. A video transcoding quality evaluation method, characterized in that, including the following steps: A data acquisition step, configured to acquire video data from a video transcoding service; A data processing step, configured to select a test video from the acquired video data according to decision configuration rules, and use the selected test video in a video scoring sub-step. The video scoring sub-step is configured to perform video scoring processing on the test video to obtain a video scoring result, and use the result in a result processing sub-step. The result processing sub-step is configured to obtain an alarm flag for the corresponding video by synthesizing the video scoring result and the decision configuration rules; A data storage step, configured to obtain the data processing result of the data processing step and the corresponding video information, and save them.

9. The video transcoding quality evaluation method according to claim 8, wherein: It further includes a data display step for graphically displaying the data processing results and video information in the data storage step S130, and the graphical display includes one or more of a line chart, a bar chart, and a pie chart; and / or, An alarm step S150 for obtaining the alarm flag and providing it to the staff, and the sending methods include one or more of text messages, emails, or instant messaging software.

10. A storage medium for storing computer-executable instructions, characterized in that: The computer-executable instructions, when executed by a processor, execute the video transcoding quality evaluation method according to claim 8 or 9.

Images