Video lag detection method and device and electronic equipment

Abstract

The invention provides a video lagging detection method and device and electronic equipment, and relates to the technical field of video data processing, and the video lagging detection method comprises the steps: carrying out the synchronous collection of video frames of N pieces of equipment; performing lagging identification on the current video frames collected from the N devices, and determining suspected lagging video frames of each device; and secondary lagging identification is performed based on the suspected lagging video frames of different devices, and the real lagging video frame is determined, so that the technical problems of low video lagging detection accuracy and limited test field in the prior art are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of video data processing, and particularly relates to a video freezing detection method and device and electronic equipment. BACKGROUND

[0002] For video playing scenes such as major events, major live broadcasts or online videos, video freezing tests are performed in advance. Video freezing is an important indicator reflecting the quality of live broadcasts on various platforms. Video playing is affected by terminals, networks and the like, and freezing conditions are different in different regions and different devices. Therefore, freezing tests often involve test scenes of multiple devices, multiple environments and multiple regions.

[0003] The current freezing detection method through video comparison is only applicable to the case of video freezing and audio freezing. For real video freeze detection, abnormalities may occur, the accuracy is low, and the test field is limited. SUMMARY

[0004] The present application aims to at least solve one of the technical problems in the related art to some extent.

[0005] To this end, a first object of the present application is to provide a video freezing detection method to achieve accurate video freezing detection.

[0006] A second object of the present application is to provide a video freezing detection device.

[0007] A third object of the present application is to provide an electronic device.

[0008] A fourth object of the present application is to provide a computer readable storage medium.

[0009] A fifth object of the present application is to provide a computer program product.

[0010] To achieve the above objects, a first aspect of the present application provides a video freezing detection method, comprising: synchronously collecting video frames from N devices, wherein N is an integer greater than or equal to 2; respectively identifying freezing of current video frames collected from the N devices to determine suspected freezing video frames of each device; performing secondary freezing identification based on the suspected freezing video frames of different devices to determine real freezing video frames. To achieve the above objects, a second aspect of the present application provides a video freezing detection device, comprising: a collecting module configured to synchronously collect video frames from N devices, wherein N is an integer greater than or equal to 2; The identification module is configured to respectively perform frame freezing identification on current video frames collected from the N devices, and determine suspected frame freezing video frames of each device. The detection module is configured to perform secondary frame freezing identification based on the suspected frame freezing video frames of different devices, and determine real frame freezing video frames. To achieve the above object, the third aspect of the present application provides an electronic device, comprising: a processor, and a memory connected with the processor in communication; The memory stores computer execution instructions. The processor executes the computer execution instructions stored in the memory to implement the method according to the first aspect of the present application.

[0011] To achieve the above object, the fourth aspect of the present application provides a computer readable storage medium, wherein the computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by a processor to implement the method according to the first aspect of the present application.

[0012] To achieve the above object, the fifth aspect of the present application provides a computer program product, comprising a computer program, which is executed by a processor to implement the method according to the first aspect of the present application.

[0013] The video frame freezing detection method, device and electronic device provided by the present application can improve the identification accuracy and efficiency of real frame freezing video frames.

[0014] Additional aspects and advantages of the present application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0015] The above and / or additional aspects and advantages of the present application will become apparent and be readily appreciated from the following description, including the accompanying drawings, wherein: Figure 1 A flowchart of a video frame freezing detection method provided by an embodiment of the present application; Figure 2 A flowchart of another video frame freezing detection method provided by an embodiment of the present application; Figure 3 A structural diagram of a video frame freezing detection device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0016] Embodiments of the present application are described below in detail, examples of which are shown in the drawings, wherein the same or similar notations represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by reference to the drawings are exemplary and are intended to explain the present application, and cannot be understood as a limitation of the present application.

[0017] A method for detecting video freezing, an apparatus and an electronic device are described below with reference to the accompanying drawings.

[0018] Figure 1 A flowchart of a method for detecting video freezing is provided in the embodiments of the present application. As shown in the figure, the method comprises the following steps: Figure 1 S101, synchronously collecting video frames of N devices.

[0019] Optionally, a test video can be randomly determined to be played, and the N devices synchronously collect video frames of the played test video, wherein N is an integer greater than or equal to 2.

[0020] In some embodiments, a personal computer (PC) can be used to control each terminal device to synchronously collect video frames. The N devices can be connected to the PC, and the terminal devices can be controlled by the screen projection or other functions of the PC to play videos, so that each device synchronously collects video frames.

[0021] In some embodiments, the device can take screenshots or record videos of the video playing area through a screenshot or any other screen recording component to obtain video frames. In the process of obtaining video frames on different devices, the video frames can be collected at the same time interval, and the interval time of the video frame rate can also be used as the interval time for obtaining video frames to improve the effect of synchronous collection of video frames.

[0022] S102, respectively identifying freezing of the current video frames collected from the N devices to determine suspected freezing video frames of each device.

[0023] In some embodiments, the video frame sequence collected by each device can be obtained, and similarity of each adjacent two video frames in the video frame sequence can be identified. If the similarity between the adjacent two video frames is high, the video frame is determined to be a suspected freezing video frame.

[0024] For example, for any adjacent two video frames in the video frame sequence and , if the similarity between and is greater than or equal to a similarity threshold, the video frame is determined to be a suspected freezing video frame.​

[0025] It can be understood that the similarity of two adjacent video frames in the video frame sequence collected by each device is calculated to determine the suspected frozen video frame of each device, and the number of suspected frozen video frames in different devices can be the same or different.

[0026] S103, performing secondary frozen frame identification based on the suspected frozen video frames of different devices to determine the real frozen video frame.

[0027] It can be understood that the video frozen frame can be caused by signal instability or low device configuration, and the video frozen frame between different devices should be randomly generated.

[0028] Optionally, the similarity of the suspected frozen video frames of different devices can be obtained, and if the similarity between the suspected frozen video frames of two devices is high, it is determined that the suspected frozen video frame is not a real frozen video frame; correspondingly, if the similarity between the suspected frozen video frames of two devices is low, it is determined that the suspected frozen video frame can be a real frozen video frame.

[0029] In some embodiments, to improve the accuracy of the determination of the real frozen video frame, for any device, the similarity between the suspected frozen video frame of the device and the suspected frozen video frame of each of the other devices can be obtained, and if the similarity is low, it is determined that the suspected frozen video frame of the device is a real frozen video frame.

[0030] In this embodiment, the video frames are synchronously collected by multiple devices, and the frozen frame identification is performed on the video frames collected by each device to obtain the suspected frozen video frame of each device. The secondary frozen frame identification is performed based on the suspected frozen video frames of different devices. The real frozen video frame is obtained by performing the primary frozen frame identification on the video frames of each device and verifying the suspected frozen video frames of multiple devices, thereby improving the identification accuracy of the real frozen video frame.

[0031] On the basis of the above embodiments, Figure 2 Another flowchart of a method for detecting a video frozen frame provided by the embodiments of the present application is shown in FIG. 6. Figure 2 As shown in the figure, the method comprises the following steps: S201, synchronously collecting video frames of N devices.

[0032] In the embodiments of the present application, the implementation method of step S201 can be realized by any one of the embodiments of the present disclosure, and here it is not limited, and will not be repeated.

[0033] S202, for device i in the N devices, obtaining the first similarity of the current video frame and the previous adjacent video frame.

[0034] wherein i is an integer, and 1≤i≤N.

[0035] Optionally, a Template Matching algorithm, a Scale-invariant feature transform (SIFT) algorithm, or a Binary Robust Invariant Scalable Keypoints (BRISK) algorithm, etc. can be used for similarity calculation. The first similarity between two adjacent video frames is calculated by calculating the pixel difference or feature similarity between the two video frames. In this embodiment, the value range of the first similarity is 0-1, wherein 0 represents the minimum similarity, and 1 represents the maximum similarity.

[0036] Exemplarily, for device 1 of N devices, the corresponding video frame sequence is represented as The first similarity between video frame and video frame , the first similarity between video frame and video frame , and so on until the first similarity between video frame and video frame is calculated.

[0037] S203, in response to the first similarity being greater than or equal to the first set threshold, determining that the current video frame is a suspected freezing video frame of device i.

[0038] Exemplarily, assuming that the first similarity between video frame and video frame of device i is greater than or equal to the first set threshold, it is determined that is a suspected freezing video frame of device i. Assuming that the first similarity between video frame and video frame is greater than or equal to the first set threshold, it is determined that is a suspected freezing video frame of device i.

[0039] In some embodiments, the suspected freezing video frames corresponding to each device can be extracted to form a suspected freezing frame set. Before the video playback starts, the suspected freezing frame set of each device is empty. As the video playback time increases, the suspected freezing video frames in the suspected freezing frame set of each device gradually increase. Assuming that there are three devices, the corresponding suspected freezing frame sets are represented as , and , respectively. Each set includes the suspected freezing video frames corresponding to the device.

[0040] In some embodiments, a delay time of T seconds can be added for the case of latency of each device, and after T seconds, T being a value greater than the delay time in this embodiment, each suspected stutter video frame is updated to the suspected stutter frame set again, excluding the influence of possible delay.

[0041] In S204, the second similarity between suspected stutter video frames of different devices is determined, and whether the suspected stutter video frame is a real stutter video frame is identified according to the second similarity between suspected stutter video frames.

[0042] Optionally, for the suspected stutter video frame of any device j in the N devices, the second similarity between the suspected stutter video frame of device j and the suspected stutter video frame of any device k in the N devices can be determined, where 1≤j, 1≤k; that is, the second similarity between the suspected stutter video frame of device j and the suspected stutter video frame of device k is calculated, which reflects the similarity of suspected stutter video frames between different devices, and if the suspected stutter video frames between different devices are more similar, the suspected stutter video frame is likely not a real stutter video frame.

[0043] In some embodiments, whether the suspected stutter video frame of device j is a real stutter video frame can be determined according to the second similarity associated with the suspected stutter video frame of device j.

[0044] Optionally, a first number of second similarities less than a second set threshold can be determined from the second similarities associated with the suspected stutter video frame of device j; a recognition condition of a second stutter is determined according to N; and in response to the first number satisfying the recognition condition of the second stutter, the suspected stutter video frame of device j is determined to be a real stutter video frame.

[0045] Optionally, the recognition condition of the second stutter in this embodiment can be a preset device number, for example, the preset device number is N-1.

[0046] It can be understood that for the suspected candidate stutter video frame with the second similarity less than the second set threshold, it can be a real stutter video frame of the device, which is recorded as a candidate stutter frame in this embodiment; for example, if the second similarity between the suspected stutter video frame of device j and the suspected stutter video frame of device k is less than the second set threshold, the suspected stutter video frame of device j is a candidate stutter frame compared with device k. It can be understood that for the suspected candidate stutter video frame with the second similarity less than the second set threshold, it can be a real stutter video frame of the device, which is recorded as a candidate stutter frame in this embodiment; for example, if the second similarity between the suspected stutter video frame of device j and the suspected stutter video frame of device k is less than the second set threshold, the suspected stutter video frame of device j is a candidate stutter frame compared with device k.

[0047] It should be noted that the suspected stutter video frame of device j is a candidate stutter frame compared with device j itself; and the suspected stutter video frame of device j is a candidate stutter frame compared with device k. It should be noted that the suspected stutter video frame of device j is a candidate stutter frame compared with device j itself; and the suspected stutter video frame of device j is a candidate stutter frame compared with device k.​ is also a candidate frozen frame compared to the device without the suspected frozen video frame.

[0048] It can be understood that the first number of the second similarity less than the second device threshold, that is, the number of the suspected frozen video frame of the device j as a candidate frozen frame compared to other devices, the suspected frozen video frame of the device j is added to the first number as a candidate frozen frame compared to the device j itself, to obtain the second number, and the second number is the first number plus 1.

[0049] In this embodiment, the first number is determined whether to meet the identification condition of the second frozen, in response to the second number greater than or equal to the preset device number, it is determined that the first number meets the identification condition of the second frozen, so as to determine that the suspected frozen video frame of the device j is a real frozen video frame; otherwise, if the second number is less than the preset device number, it is determined that the first number does not meet the identification condition of the second frozen, and the suspected frozen video frame of the device j is not a real frozen video frame.

[0050] Exemplarily, assuming that the total number of devices N is 3, the suspected frozen frame set corresponding to each device is , and , that is, the suspected frozen video frame corresponding to the device 1 is , and the suspected frozen video frames of the devices 2 and 3 do not exist; at this time, the suspected frozen video frame corresponding to the device 1 is compared to the device 1 itself and the devices 2 and 3 without the suspected frozen video frame, it is a candidate frozen frame, so the second number is 3, the preset device number is N-1=2, the second number 3>2, and it is determined that the suspected frozen video frame corresponding to the device 1 is a real frozen video frame.

[0051] Exemplarily, assuming that the total number of devices N is 3, the suspected frozen frame set corresponding to each device is , and , that is, the suspected frozen video frame corresponding to the device 1 is , the suspected frozen video frame corresponding to the device 2 is , and the suspected frozen video frame of the device 3 does not exist; the second similarity between and is obtained, if the second similarity between and is greater than the second device threshold, then is not a candidate frozen frame compared to the device 2, Compared with the device 1 itself and the device 3 without the suspected frozen video frame, the device 1 is a candidate frozen frame, so the second number is 2, the preset device number is N-1 = 2, the second number 2 = 2, and the suspected frozen video frame corresponding to the device 1 is determined a real frozen video frame.

[0052] Exemplarily, assuming that the total number of devices N is 3, the suspected frozen frame set corresponding to each device is 、 and That is, the suspected frozen video frame corresponding to the device 1 is , the suspected frozen video frame corresponding to the device 2 is , and the suspected frozen video frame corresponding to the device 3 is ; the second similarity between and , the second similarity between and , if the second similarity between and is greater than the second device threshold, and is greater than the second device threshold, then is not a candidate frozen frame compared with the device 2 and the device 3, is a candidate frozen frame compared with the device 1 itself, so the second number is 1, the preset device number is N-1 = 2, the second number 1 < 2, and the suspected frozen video frame corresponding to the device 1 is determined is not a real frozen video frame.

[0053] By analogy, the suspected frozen video frame of each device is analyzed in turn to determine the real frozen video frame in each device.

[0054] Further, the frozen duration of the video can also be obtained. In this embodiment, the subsequent video frames of the device where the real frozen video frame is located are continuously collected; the third similarity between the subsequent video frames and the real frozen video frame is determined; and based on the third similarity, the video frozen duration is obtained.

[0055] In response to the third similarity being greater than or equal to the first set threshold, that is, the similarity between the subsequent video frames and the real frozen video frame is high, it is determined that the video frozen of the device has not ended, the subsequent video frames of the device are continuously collected and the third similarity is determined, until the third similarity is less than the first set threshold, it is determined that the video frozen of the device has ended, and the video frozen duration is obtained.

[0056] In response to the third similarity being less than the first set threshold, it is determined that the video frozen of the device has ended, and the video frozen duration is obtained.

[0057] Optionally, the duration of the video stutter is obtained based on the acquisition time of the actual stuttering video frame and the acquisition time of subsequent video frames. For example, the time of the subsequent video frame when the third similarity is less than the first set threshold is... The actual time frame where the video stutters is at is The duration of the video stutter is... . In this embodiment, after synchronously acquiring video frames from N devices, for each device, based on the first similarity between two adjacent video frames, suspected stuttering video frames in the device are initially identified. Then, secondary stuttering identification is performed based on the suspected stuttering video frames between different devices. This eliminates the need to analyze all video frames from all devices, reducing computational resource consumption and improving testing efficiency. When performing secondary stuttering identification on suspected stuttering video frames, the second similarity between suspected stuttering video frames from different devices is calculated, and a first number of second similarities less than a second set threshold is determined. The identification conditions for secondary stuttering are customized based on the number of all devices. Based on the first number and the customized identification conditions, the identification of real stuttering video frames is performed. This approach offers high flexibility and improves the accuracy of obtaining real stuttering video frames through secondary identification. It can be widely applied to stuttering tests in multiple locations and on multiple devices. Furthermore, the duration of video stuttering can be obtained based on real stuttering video frames, achieving efficient, accurate, and complete video stuttering detection.

[0058] To achieve the above embodiments, this application also proposes a video stuttering detection device.

[0059] Figure 3 This is a schematic diagram of a video stuttering detection device provided in an embodiment of this application. Figure 3 As shown, the video stuttering detection device 300 includes: Acquisition module 301 is used to synchronously acquire video frames from N devices, where N is an integer greater than or equal to 2; The identification module 302 is used to identify stuttering in the current video frames collected from N devices and determine the suspected stuttering video frames for each device. The detection module 303 is used to perform secondary stuttering identification based on suspected stuttering video frames from different devices to determine the actual stuttering video frames.

[0060] Furthermore, in one possible implementation of this application embodiment, the identification module 302 is used for: For device i among N devices, obtain the first similarity between the current video frame and the previous adjacent video frame, where i is an integer and 1≤i≤N; In response to a first similarity greater than or equal to a first set threshold, the current video frame is determined to be a suspected stuttering video frame of device i.

[0061] Further, in a possible implementation of the embodiment of the application, the detection module 303 is configured to: determine the second similarity between the suspected frozen video frames of different devices, and identify whether the suspected frozen video frame is a real frozen video frame according to the second similarity between the suspected frozen video frames.

[0062] Further, in a possible implementation of the embodiment of the application, the detection module 303 is configured to: for the suspected frozen video frame of any device j in the N devices, determine the second similarity between the suspected frozen video frame of the device j and the suspected frozen video frame of any device k in the N devices, where 1≤j, 1≤k; determine whether the suspected frozen video frame of the device j is a real frozen video frame according to the second similarity associated with the suspected frozen video frame of the device j.

[0063] Further, in a possible implementation of the embodiment of the application, the detection module 303 is configured to: from the second similarities associated with the suspected frozen video frame of the device j, determine a first number of second similarities less than a second set threshold value; determine a recognition condition of the second freezing according to N; in response to that the first number meets the recognition condition of the second freezing, determine that the suspected frozen video frame of the device j is a real frozen video frame.

[0064] Further, in a possible implementation of the embodiment of the application, the detection module 303 is further configured to: continuously collect subsequent video frames of the device where the real frozen video frame is located; determine a third similarity between the subsequent video frames and the real frozen video frame; obtain a video freezing duration based on the third similarity.

[0065] Further, in a possible implementation of the embodiment of the application, the detection module 303 is configured to: in response to that the third similarity is less than a first set threshold value, determine that the video freezing of the device ends; obtain the video freezing duration based on a collection time of the real frozen video frame and a collection time of the subsequent video frame.

[0066] Further, in a possible implementation of the embodiment of the application, the detection module 303 is configured to: In response to the third similarity being greater than or equal to the first set threshold, it is determined that the video freezing of the device has not ended, the subsequent video frames of the device are continuously captured, and the third similarity is determined until the third similarity is less than the first set threshold, it is determined that the video freezing of the device has ended, and the duration of the video freezing is obtained.

[0067] It should be noted that the foregoing explanation of the video freezing detection method embodiment is also applicable to the video freezing detection device of this embodiment, which will not be described here.

[0068] In the embodiments of the present application, after the synchronous capture of the video frames of the N devices, for each device, the suspected freezing video frame in the device is preliminarily identified based on the first similarity between the adjacent two video frames, and then the secondary freezing identification is performed based on the suspected freezing video frames between different devices. Without analyzing all the video frames of all the devices, the consumption of computing resources is reduced, and the test efficiency is higher. When the secondary freezing identification is performed on the suspected freezing video frames, the second similarity between the suspected freezing video frames of different devices is calculated, the first number of the second similarities less than the second set threshold is determined, and the identification condition of the secondary freezing is customized based on the number of all the devices. The identification of the real freezing video frame is performed based on the first number and the customized identification condition. The identification flexibility is higher, the acquisition accuracy of the real freezing video frame is improved through the secondary identification, and the method can be widely applied to freezing test of multiple places and multiple devices. Further, the duration of the video freezing can be obtained based on the real freezing video frame, and efficient, accurate and complete video freezing detection is achieved.

[0069] To achieve the above-mentioned embodiments, the present application further provides an electronic device, comprising a processor and a memory connected with the processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory to realize the method provided in the foregoing embodiments. To achieve the above-mentioned embodiments, the present application further provides a computer readable storage medium, wherein the computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by the processor to realize the method provided in the foregoing embodiments.

[0070] To achieve the above-mentioned embodiments, the present application further provides a computer program product, comprising a computer program, which is executed by the processor to realize the method provided in the foregoing embodiments.

[0071] The collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in the present application comply with relevant laws and regulations and do not violate public order and good customs.

[0072] It should be noted that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. Furthermore, such collection / sharing should only be conducted after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes authorization of relevant user information before the user uses the function. In addition, any necessary steps must be taken to protect and safeguard access to such personal information data and ensure that others with access to personal information data comply with their privacy policies and procedures.

[0073] This application is intended to provide an implementation scheme for users to selectively prevent the use or access to their personal information data. Specifically, this disclosure is intended to provide hardware and / or software to prevent or block access to such personal information data. Once personal information data is no longer needed, risks can be minimized by restricting data collection and deleting data. Furthermore, where applicable, such personal information is de-identified to protect user privacy.

[0074] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0075] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0076] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0077] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0078] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0079] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0080] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0081] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for detecting video stuttering, the method comprising: The method comprises: synchronous acquisition of video frames by N devices, wherein N is an integer greater than or equal to 2; respectively identifying the current video frames collected from the N devices for stutter, to determine the suspected stutter video frames of each device; based on the suspected stutter video frames of different devices, secondary stutter identification is performed to determine the real stutter video frames.

2. The method of claim 1, wherein, The method comprises: for device i in the N devices, a first similarity between the current video frame and the previous adjacent video frame is obtained, wherein i is an integer, and 1≤i≤N; in response to the first similarity being greater than or equal to a first set threshold, the current video frame is determined as the suspected stutter video frame of the device i.

3. The method according to claim 1 or 2, characterized in that, The method comprises: determining the second similarity between the suspected stutter video frames of different devices, and according to the second similarity between the suspected stutter video frames, identifying whether the suspected stutter video frames are real stutter video frames.

4. The method of claim 3, wherein, The method comprises: for the suspected stutter video frame of any device j in the N devices, determining the second similarity between the suspected stutter video frame of the device j and the suspected stutter video frame of any device k in the N devices, wherein 1≤j, 1≤k; according to the second similarity associated with the suspected stutter video frame of the device j, determining whether the suspected stutter video frame of the device j is a real stutter video frame.

5. The method of claim 4, wherein, The method comprises: from the second similarity associated with the suspected stutter video frame of the device j, determining a first number of second similarities less than a second set threshold; according to the N, determining the identification condition of secondary stutter; in response to the first number satisfying the identification condition of secondary stutter, determining that the suspected stutter video frame of the device j is a real stutter video frame.

6. The method of claim 1, wherein, The method further comprises: continuously collecting subsequent video frames of the device where the real stutter video frame is located; determining the third similarity between the subsequent video frames and the real stutter video frame; based on the third similarity, obtaining the video stutter duration.

7. The method of claim 6, wherein, The method comprises: in response to the third similarity being less than a first set threshold, determining that the video stutter of the device is over; based on the collection time of the real stutter video frame and the collection time of the subsequent video frame, obtaining the video stutter duration.

8. The method of claim 6, wherein, The method comprises: In response to the third similarity being greater than or equal to a first set threshold, it is determined that the video freezing of the device has not ended, the subsequent video frames of the device are continuously captured, and the third similarity is determined until the third similarity is less than the first set threshold, it is determined that the video freezing of the device has ended, and the duration of the video freezing is obtained.

9. An apparatus for detecting video stuttering, the apparatus comprising: The method comprises the steps of: capturing a plurality of N devices for synchronous acquisition of video frames, wherein N is an integer greater than or equal to 2; identifying the suspected freezing video frames of each device by respectively identifying the current video frames captured from the N devices; detecting the real freezing video frames by performing secondary freezing identification based on the suspected freezing video frames of different devices.

10. An electronic device, comprising: The method comprises the steps of: a processor, and a memory connected in communication with the processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory to implement the method according to any one of claims 1-8.

Images