Video quality detection method, device, equipment and medium

Abstract

The present invention provides a video quality detection method, device, equipment and medium, which relates to the field of digital media technology. The method obtains a marked video by superimposing marking information on each frame image in the original video, and plays the marked video, then collects each frame image during the playback process as a test image, and finally detects whether there are mosaics, flower screens, static frames, frame skipping, freezes, fast forwards and rewinds in the video decoding process based on the test image, thereby detecting the video quality. The video quality detection method provided by the present invention does not need to rely on video player software to detect video quality, so that the detection result is true and reliable, and accurate and efficient detection of video quality is achieved.

Description

Technical Field

[0001] The present invention relates to the field of digital media technology, and in particular to a video quality detection method, device, equipment and medium. Background Art

[0002] Using soft decoding to decode videos places high demands on system performance. Under limited system performance conditions, it is likely to cause excessive load on the CPU, GPU, and memory, resulting in abnormal situations such as mosaics, screen distortion, freezes, still frames, frame skipping, or fast forwarding when the decoded video is played.

[0003] Therefore, it is necessary to detect video playback, but the existing technology often relies on video player software for detection. Before detection, the player software needs to be modified to achieve it, and it cannot be used independently, and the method is relatively limited. In addition, this method of using player software to detect whether there is an abnormality during video playback is equivalent to white box testing. The software test results in the tested box are easy to falsify. Therefore, it is inaccurate to use this test result for video quality detection. Summary of the invention

[0004] The present invention provides a video quality detection method, device, equipment and medium to solve the above problems existing in the prior art.

[0005] The present invention provides a video quality detection method, comprising the following steps.

[0006] Superimposing first marking information on each frame image in the original video to obtain a marked video; the first marking information is used to mark each frame image in the original video; Play the marked video, and collect each frame of the image during the playback process to obtain the image to be tested; The video quality during playback is determined based on each frame image of the marked video and the image to be tested.

[0007] According to a video quality detection method provided by the present invention, the step of superimposing first marking information on each frame of an original video to obtain a marked video includes: Generate second marking information according to each frame image of the original video in sequence; Encoding the second tag information to obtain the first tag information; The first marking information is superimposed on each frame of the original video to obtain the marked video.

[0008] According to a video quality detection method provided by the present invention, the video quality during playback is determined based on each frame image of the marked video and the image to be tested, including: Building a standard database based on each frame image of the labeled video; The video quality during playback is determined based on the standard database and the image to be tested.

[0009] According to a video quality detection method provided by the present invention, the method of determining the video quality during playback based on the standard database and the image to be tested includes: According to the first marking information of each frame of the image to be tested, a corresponding standard image is acquired from the standard database; Calculate the similarity between each frame of the image to be tested and the corresponding standard image; Based on the similarity, it is determined whether a first abnormal scene occurs during the playback process.

[0010] According to a video quality detection method provided by the present invention, the step of acquiring a corresponding standard image from the standard database according to the first marking information of each frame of the image to be tested comprises: Obtaining first marking information of each frame of the image to be tested; Decoding the first tag information to obtain second tag information; According to the second marking information, a corresponding standard image is acquired from the standard database.

[0011] According to a video quality detection method provided by the present invention, the video quality during playback is determined based on each frame image of the marked video and the image to be tested, including: Calculate the frame interval between any two frames of the image to be tested that are played continuously; Based on the frame interval, it is determined whether a second abnormal scene occurs during the player playback.

[0012] According to a video quality detection method provided by the present invention, the method further includes: Generate log files for image frames with abnormal scenes during playback.

[0013] According to the present invention, a video quality detection device is provided, comprising the following modules: A marking module, used to superimpose first marking information on each frame of the original video to obtain a marked video; the first marking information is used to mark each frame of the original video; An acquisition module is used to play the marked video and acquire each frame of the image during the playback process to obtain an image to be tested; The recognition module is used to determine the video quality during the playback process based on each frame image of the marked video and the image to be tested.

[0014] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above-mentioned video quality detection methods when executing the computer program.

[0015] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the video quality detection method described above is implemented.

[0016] The video quality detection method provided by the present invention obtains a marked video by superimposing first marking information on each frame image in the original video, plays the marked video, then collects each frame image during the playback process as a test image, and finally detects the video quality based on the test image. There is no need to rely on video player software to detect the video quality, so that the detection result is true and reliable, and accurate and rapid detection of video quality is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is a flow chart of a video quality detection method provided by the present invention.

[0019] Figure 2 It is a schematic diagram of encoding a PTS value into a two-dimensional code image and superimposing it on a single-frame video screen in a video quality detection method provided by the present invention.

[0020] Figure 3 It is a structural schematic diagram of a video quality detection device provided by the present invention.

[0021] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0022] In the prior art, the video freeze detection method depends on the video player software and cannot be used independently. The player software needs to be modified before testing. This has great limitations in the method for set-top box video playback testing.

[0023] Using playback software to detect freezes and mosaics during video playback is based on the software test results in the box being tested, which is equivalent to white box testing. Given any set-top box, if software that does not rely on the box is used to test the playback effect, it is a black box test, which is the technical solution provided by the present invention.

[0024] In addition, the test results of this white box test are easy to falsify based on the software test results in the box being tested. In other words, the test results of the object being tested itself are unreliable and inaccurate, so it is necessary to use the results measured by external testing means as the basis, which is a video quality detection method provided by the present invention.

[0025] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] The video quality detection method provided by the present invention first needs to mark the original video file, then use the acquisition module to collect data of the marked video file and store it in a database, then the video decoder plays the pre-marked video file or network code stream, and the video output is connected to the video acquisition card on the PC end. The PC software (identification module) monitors the video frame in real time. The PC software can calculate and analyze each frame of the video playback, such as whether there is a frame interval timeout, whether the video frame is continuous, and whether there is a mosaic on the screen. Abnormal scenes, finally, the decoded video content and abnormal scenes in the entire video test process are stored to generate a test report and realize automated testing.

[0027] Combine the following Figures 1 to 4 The video quality detection method provided by the present invention is described. Figure 1 is a flow chart of a video quality detection method provided by the present invention, such as Figure 1 As shown, the method comprises the following steps: Step 101: superimpose first marking information on each frame image in the original video to obtain a marked video; the marking information is used to mark each frame image in the original video.

[0028] Optionally, superimposing the first marking information on each frame of the original video to obtain the marked video includes: Generate second marking information according to each frame image of the original video in sequence; Encoding the second tag information to obtain the first tag information; The first marking information is superimposed on each frame of the original video to obtain the marked video.

[0029] Specifically, after obtaining the original video, first, the original video needs to be processed, that is, each frame of the video file is read in sequence, the second marking information is generated, and then the second marking information is encoded to obtain the first marking information, and finally the first marking information is used to mark each frame image in the original video to obtain a marked video.

[0030] There are multiple options for the second mark information, such as a frame number, an image number or a PTS (Presentation Time Stamp) value, which is used to measure the playback time of each frame of the image during video decoding. The embodiment of the present invention is described using the PTS value as an example.

[0031] In order to quickly obtain the sequence number of the current frame during playback detection, and thus quickly find the corresponding original image data, the embodiment of the present invention obtains the first tag information by encoding the second tag information. The second tag information can be encoded in a variety of ways. For example, the second tag information can be encoded using text, barcodes, or QR codes.

[0032] The embodiment of the present invention uses the example of using a two-dimensional code to encode the PTS value. The two-dimensional code generated according to the PTS value corresponding to the image is superimposed on each frame of the original video, so that each frame includes frame sequence information, so that the original image data can be quickly found during playback detection.

[0033] Figure 2 Schematic diagram of encoding a PTS value into a two-dimensional code image and superimposing it on a single-frame video screen in a video quality detection method provided by the present invention, such as Figure 2 Finally, convert it into the required video format file (video formats include but are not limited to TS, MP4, avi and other video file formats) to obtain the marked video.

[0034] Step 102: Play the marked video, and collect each frame of the image during the playback process to obtain the image to be tested.

[0035] In the embodiment of the present invention, the device for playing the video includes but is not limited to a video decoder and player software such as Xunlei Video Player. The embodiment of the present invention is described by taking the video decoder as an example. The video decoder is used to play the video file or network stream (i.e., the marked video) that has been processed as described above, and the screen output by the video decoder is connected to the PC video capture card (the device for capturing the video includes but is not limited to a PC video capture card, a camera or other cameras, etc., and the embodiment of the present invention is described by taking the PC video capture card as an example), and each frame of the image during the playback process is captured to obtain the image to be tested.

[0036] In addition, during the process of capturing the video, the capture frame rate of each frame of the image can be greater than or equal to the frame rate of the video being played. For example, when the capture frame rate is greater than the frame rate of the video being played, the frame rate during playback is 30fps. If the capture frame rate is 30fps, each frame of the image captured at this time is the image to be tested corresponding to each frame of the image in the marked video; if the capture frame rate is 90fps, that is, for each frame of the image played, three frames of corresponding images will be captured, and one frame can be selected from the three frames of the image captured as the image to be tested to avoid the problem of false detection caused by missing images during capture.

[0037] Step 103: Determine the video quality during playback based on each frame of the marked video and the image to be tested.

[0038] By performing calculations and comparisons on each frame of the marked video and the corresponding image to be tested, such as similarity calculation or frame interval calculation, and comparing the calculation result with the preset threshold, it is possible to determine whether there are abnormal conditions such as mosaics, screen distortion, still frames, frame skipping, freezes, fast forwards, and fast rewinds during video playback, and to determine the quality of the video.

[0039] The present invention provides a video quality detection method, which obtains a marked video by superimposing first marking information on each frame image in an original video, and uses a video decoder to play the marked video, and then uses a video capture card to capture each frame image in the playback process as a test image, and finally performs calculation and analysis based on PC software to detect whether the test image has mosaics, distorted screens, still frames, frame skipping, freezes, fast forwards, and fast rewinds in the video decoding process, thereby detecting the video quality. There is no need to rely on video player software to detect the video quality, so that the detection result is true and reliable, and accurate and efficient detection of video quality is achieved.

[0040] Optionally, superimposing the first marking information on each frame of the original video to obtain the marked video includes: Generate second marking information according to each frame image of the original video in sequence; Encoding the second tag information to obtain the first tag information; The first marking information is superimposed on each frame of the original video to obtain the marked video.

[0041] Specifically, each frame of the original video is read in sequence, and the second mark information (such as PTS value) of each frame is generated frame by frame. The second mark information is encoded to generate the first mark information. The purpose of the encoding process is to reduce the amount of calculation and improve the recognition efficiency of the image to be tested in subsequent detection. The first mark information is then superimposed on each frame of the original video frame by frame to generate a marked video.

[0042] Optionally, the determining the video quality during playback based on each frame image of the marked video and the image to be tested includes: Building a standard database based on each frame image of the labeled video; The video quality during playback is determined based on the standard database and the image to be tested.

[0043] Specifically, before playing the marked video, first use computer software to perform a second processing on each frame of the image after the first processing. The purpose of the second processing is to reduce the amount of calculation and improve the recognition efficiency of the image to be tested in subsequent detection. Then, use each frame of the image that has undergone the second processing to build a standard database, wherein each frame of the image that has undergone the second processing is a standard image and is stored in the standard database; finally, based on the standard images in the standard database and the image to be tested captured by the video capture card, determine the video quality during playback or during decoding by the video decoder.

[0044] Optionally, determining the video quality during playback based on the standard database and the image to be tested includes: According to the first marking information of each frame of the image to be tested, a corresponding standard image is acquired from the standard database; Calculate the similarity between each frame of the image to be tested and the corresponding standard image; Based on the similarity, determine whether the first abnormal scene occurs during the playback process. Specifically, obtain the picture (i.e., the image to be tested) in the video capture card in real time, and analyze and process each frame in real time. The specific analysis and processing process is as follows: The first marking information (i.e., QR code) in a single frame of the image to be tested is obtained, and then the corresponding standard image is quickly obtained from the standard database according to the QR code, wherein the standard image is the image of the marking image corresponding to the image to be tested after the second processing, and then the similarity between the image to be tested and the corresponding original image is calculated. If the calculated similarity is lower than the first threshold, it is considered that there is a difference between the playback picture and the original picture, that is, the first abnormal scene, including but not limited to mosaic or flower screen, etc., and the lower the similarity, the greater the difference in the picture, and the image with the difference is the abnormal image. The playback time and abnormal image at this time are recorded and saved locally for later inspection and analysis, so as to facilitate the generation of test reports and realize automated testing.

[0045] In an embodiment of the present invention, algorithms for calculating image similarity include but are not limited to a structural similarity (SSIM) algorithm, a cosine similarity algorithm, and a histogram algorithm. In the process of constructing a standard database, in order to reduce the amount of calculation and improve the recognition efficiency of the image to be tested in subsequent detection, the present invention performs a second processing such as scaling and grayscale processing on each frame of the pre-processed image and then stores the processed data into a database to construct a standard database. The SSIM algorithm is an image processing algorithm that calculates the similarity before and after the image has undergone scaling and grayscale processing, and is used to measure the similarity before and after the image is scaled and grayscale processed. Therefore, the SSIM algorithm is used as an example for explanation below.

[0046] The similarity calculated by the SSIM algorithm is in the interval [0, 1]. Therefore, in an embodiment of the present invention, the first threshold is set to 0.99. However, in other embodiments or other cases, it can also be adjusted to any value between [0, 1], such as 0.8 or 0.9.

[0047] The SSIM algorithm takes into account the human eye's perception of brightness, contrast, and structure, and is therefore more consistent with human subjective perception. It is more sensitive to overall image changes. Compared with other algorithms, it has higher accuracy in image similarity detection and can identify even subtle image changes.

[0048] The specific implementation method of the SSIM algorithm is: obtain an image, scale down the image to reduce the amount of calculation and improve the comparison efficiency, then grayscale process the image to convert it into a grayscale image, and finally calculate the similarity of the converted grayscale image.

[0049] The mathematical model of the SSIM algorithm is as follows: Among them, X represents the corresponding image data in the marked video, and Y represents the image data to be tested collected by the video capture card. represents the average value of X, represents the mean value of Y, represents the covariance of X and Y, represents the variance of X, Represents the variance of Y. The constants C1 and C2 are used to avoid instability when the denominator is 0.

[0050] The embodiment of the present invention uses the first marking information of each frame of the image to be tested to obtain the corresponding standard image from the standard database, and then uses the SSIM algorithm to calculate the similarity between each frame of the image to be tested and the corresponding standard image, so as to determine whether a first abnormal scene occurs during the video playback, such as mosaic or flowery screen, thereby realizing accurate and efficient detection of video quality.

[0051] Optionally, acquiring a corresponding standard image from the standard database according to the first marking information of each frame of the image to be tested includes: Obtaining first marking information of each frame of the image to be tested; Decoding the first tag information to obtain second tag information; According to the second marking information, a corresponding standard image is acquired from the standard database.

[0052] Specifically, a video decoder plays a marked video, and the output of the decoder is connected to a video capture card, each frame of the image in the video capture card is acquired in real time to obtain a video to be tested, each frame of the image in the video to be tested is analyzed and processed in real time, the QR code content corresponding to each frame is acquired, the QR code on each frame of the image to be tested (i.e., the first marking information) is decoded, and a PTS value (i.e., the second marking information) is obtained, so as to quickly acquire the corresponding standard image from the standard database according to the PTS value, and then the SSIM algorithm is used to calculate the similarity between each frame of the image to be tested and the corresponding standard image.

[0053] The embodiment of the present invention performs a decoding operation according to the encoded first mark information to obtain the second mark information, thereby reducing the amount of calculation, so that the corresponding standard image can be quickly found from the standard database, and the efficiency of video quality detection is improved. In addition, since the encoding and decoding processes are added, it is ensured that the image to be tested and the corresponding standard image can correspond one-to-one, thereby improving the accuracy of video quality detection.

[0054] Optionally, the determining the video quality during playback based on each frame image of the marked video and the image to be tested includes: Calculate the frame interval between any two frames of the image to be tested that are played continuously; Based on the frame interval, it is determined whether a second abnormal scene occurs during the player playback.

[0055] Specifically, the second abnormal scene includes any one of freeze, frame skipping, still frame, fast forward and fast rewind. By calculating the frame interval between any two frames of the image to be tested that are played continuously, it can be determined whether the second abnormal scene occurs in the video frame during the player playback process.

[0056] For example, when detecting whether the second abnormal scene is any one of freeze, frame skipping and still frame, determine whether the PTS value in the mark information of each frame of the image to be tested and the PTS value of the previous frame in the currently played marked video belong to continuous video frames. If not, frame loss occurs and the current frame time is recorded in the log file for later inspection and subsequent generation of test reports to achieve automated testing. The specific judgment criteria are as follows: Whether it is continuous: (PTS2-PTS1)==second threshold; Stuttering: (PTS2-PTS1) < the second threshold; Frame skipping: (PTS2-PTS1)> second threshold; Still frame: (PTS2-PTS1)==0; Among them, in an embodiment of the present invention, the second threshold is set to 1000fps, but in other embodiments or other cases, it can also be adjusted to other values, such as 800fps or 900fps, etc.; PTS2 is the PTS value of the current video frame captured by the video capture card during real-time detection, PTS1 is the PTS value of the previous frame captured by the video capture card, and fps is the original video frame rate.

[0057] For another example, when the second abnormal scene is detected as fast forward or fast rewind, the PTS value of the current video frame captured by the video capture card is PTS2, the PTS value of the previous frame is PTS1, the current video frame playback time T2 and the previous frame playback time T1. The fast forward and rewind judgment criteria are as follows: Fast forward: (PTS2-PTS1)-(T2-T1)>third threshold; Fast rewind: (T2-T1)-(PTS2-PTS1)> the third threshold; In the embodiment of the present invention, the third threshold value may be set to 1 / the frame rate of the original video, and may be flexibly set according to the frame rate of the original video; If the second abnormal scenario exists, that is, fast forward or fast rewind occurs, the current frame time is recorded in the log file for later inspection.

[0058] The embodiment of the present invention determines whether a video has static frames, frame skipping, freezes, fast forwards, and fast rewinds by calculating frame intervals, and makes scientific judgments with a relatively small amount of calculation, thus having the characteristics of accurate and efficient recognition.

[0059] Optionally, the method further comprises: Generate log files for image frames with abnormal scenes during playback.

[0060] Based on any of the above embodiments, the real-time images captured by the video capture card (including all images to be tested and all abnormal scenes that occur during the detection process, including the first abnormal scene and the second abnormal scene, etc.) are saved to the PC to generate a log file, which is convenient for generating a test report and realizing automated testing. It is also convenient to play back the place where the abnormal scene occurs according to the log file later to check for problems or faults, thereby forming an effective feedback mechanism and improving the quality of video playback in a targeted manner.

[0061] A video quality detection device provided by the present invention is described below. The video quality detection device described below and the video quality detection method described above can be referred to each other.

[0062] Based on any of the above embodiments, Figure 3 is a structural diagram of a video quality detection device provided by the present invention, such as Figure 3 As shown, the embodiment of the present invention provides a video quality detection device, including a marking module 301, a collection module 302 and an identification module 303, wherein: The marking module 301 is used to superimpose first marking information on each frame image in the original video to obtain a marked video; the first marking information is used to mark each frame image in the original video; the acquisition module 302 is used to play the marked video and acquire each frame image during the playback process to obtain the image to be tested; the recognition module 303 is used to determine the video quality during the playback process based on each frame image of the marked video and the image to be tested.

[0063] The present invention provides a video quality detection device, which obtains a marked video by superimposing first marking information on each frame image in an original video, and uses a video decoder to play the marked video, and then uses a video capture card to capture each frame image in the playback process as a test image, and finally performs calculation and analysis based on PC software to detect whether the test image has mosaics, distorted screens, still frames, frame skipping, freezes, fast forwards and rewinds in the video decoding process, thereby detecting the video quality. There is no need to rely on video player software to detect the video quality, so that the detection result is true and reliable, and accurate and efficient detection of video quality is achieved.

[0064] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communication interface 420 and the memory 430 communicate with each other through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the video quality detection method, which includes: Superimposing first marking information on each frame image in the original video to obtain a marked video; the first marking information is used to mark each frame image in the original video; Play the marked video, and collect each frame of the image during the playback process to obtain the image to be tested; The video quality during playback is determined based on each frame image of the marked video and the image to be tested.

[0065] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0066] On the other hand, the present invention further provides a computer program product, the computer program product includes a computer program, the computer program can be stored in a computer-readable storage medium, when the computer program is executed by a processor, the computer can execute the video quality detection method provided by the above methods, the method includes: Superimposing first marking information on each frame image in the original video to obtain a marked video; the first marking information is used to mark each frame image in the original video; Play the marked video, and collect each frame of the image during the playback process to obtain the image to be tested; The video quality during playback is determined based on each frame image of the marked video and the image to be tested.

[0067] In another aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the video quality detection method provided by the above methods is implemented, and the method includes: Superimposing first marking information on each frame image in the original video to obtain a marked video; the first marking information is used to mark each frame image in the original video; Play the marked video, and collect each frame of the image during the playback process to obtain the image to be tested; The video quality during playback is determined based on each frame image of the marked video and the image to be tested.

[0068] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0069] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0070] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0071] It should also be noted that the terms "first", "second", "third", etc. in the present invention are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", and "third" are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more.

[0072] "Determine B based on A" in the embodiments of the present application means that the factor A should be considered when determining B. It is not limited to "B can be determined based on A alone", but should also include: "Determine B based on A and C", "Determine B based on A, C and E", "Determine C based on A, and further determine B based on C", etc. In addition, it can also include taking A as a condition for determining B, for example, "When A meets the first condition, use the first method to determine B"; for another example, "When A meets the second condition, determine B", etc.; for another example, "When A meets the third condition, determine B based on the first parameter", etc. Of course, it can also be a condition that takes A as a factor for determining B, for example, "When A meets the first condition, use the first method to determine C, and further determine B based on C", etc.

[0073] In the present invention, the term "plurality" refers to two or more than two, and other quantifiers are similar to them.

[0074] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A video quality detection method, characterized in that: include: Superimposing first marking information on each frame of the original video to obtain a marked video; The first marking information is used to mark each frame of the original video; Play the marked video, and collect each frame of the image during the playback process to obtain the image to be tested; The video quality during playback is determined based on each frame image of the marked video and the image to be tested.

2. The video quality detection method according to claim 1, characterized in that: The step of superimposing the first marking information on each frame of the original video to obtain the marked video includes: Generate second marking information according to each frame image of the original video in sequence; Encoding the second tag information to obtain the first tag information; The first marking information is superimposed on each frame of the original video to obtain the marked video.

3. The video quality detection method according to claim 1, characterized in that: The determining of the video quality during playback based on each frame image of the marked video and the image to be tested includes: Building a standard database based on each frame image of the labeled video; The video quality during playback is determined based on the standard database and the image to be tested.

4. The video quality detection method according to claim 3, characterized in that: The determining of the video quality during playback based on the standard database and the image to be tested includes: According to the first marking information of each frame of the image to be tested, a corresponding standard image is acquired from the standard database; Calculate the similarity between each frame of the image to be tested and the corresponding standard image; Based on the similarity, it is determined whether a first abnormal scene occurs during the playback process.

5. The video quality detection method according to claim 4, characterized in that: The step of acquiring a corresponding standard image from the standard database according to the first marking information of each frame of the image to be tested includes: Obtaining first marking information of each frame of the image to be tested; Decoding the first tag information to obtain second tag information; According to the second marking information, a corresponding standard image is acquired from the standard database.

6. The video quality detection method according to claim 1, characterized in that: The determining of the video quality during playback based on each frame image of the marked video and the image to be tested includes: Calculate the frame interval between any two frames of the image to be tested that are played continuously; Based on the frame interval, it is determined whether a second abnormal scene occurs during the player playback.

7. The video quality detection method according to any one of claims 1 to 6, characterized in that: The method further comprises: Generate log files for image frames with abnormal scenes during playback.

8. A video quality detection device, characterized in that: include: A marking module, used for superimposing first marking information on each frame of the original video to obtain a marked video; The first marking information is used to mark each frame of the original video; An acquisition module is used to play the marked video and acquire each frame of the image during the playback process to obtain an image to be tested; The recognition module is used to determine the video quality during the playback process based on each frame image of the marked video and the image to be tested.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the video quality detection method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the video quality detection method according to any one of claims 1 to 7 is implemented.

Images