A method and device for detecting video repetition

By detecting the feature combination of video frame images and the target object ratio frame by frame, the efficiency of video repeatability detection is improved, the problems of low efficiency and resource waste in the prior art are solved, and the repeated content in the video frame images are quickly recognized.

CN112507875BActive Publication Date: 2024-12-03SHANGHAI LIANSHANG NETWORK TECHNOLOGY GROUP CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202011436367.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-12-10
Publication Date
2024-12-03
Estimated Expiration
2040-12-10

AI Technical Summary

Technical Problem

The prior art is inefficient in detecting video repetition and is wasted computing resources, making it difficult to effectively identify duplicate content in video frame images.

Method used

By acquiring video frame images, using feature combinations to detect target video frame images frame by frame, calculate the ratio of target objects to all objects in the target detection area, determine the single frame repetition degree, and calculate the video repetition degree based on this, improve detection efficiency and save calculations resource.

Benefits of technology

It significantly improves the efficiency of video repetition detection, reduces the consumption of computing resources, can quickly identify duplicate content in video frame images, and supports effective video plagiarism detection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112507875B_ABST
    Figure CN112507875B_ABST
Patent Text Reader

Abstract

The purpose of the present application is to provide a method and device for detecting video repetition, the method comprising: obtaining one or more first video frame images of first video information; detecting frame by frame whether there is a target video frame image that meets the repetition detection condition in one or more first video frame images according to the first feature combination of the second video information; for each target video frame image that meets the repetition detection condition, determining the single-frame repetition of the target video frame image according to the ratio of the number of second target objects appearing in the target detection area of ​​the target video frame image to the total number of all objects appearing in the target detection area; determining the video repetition of the first video information and the second video information according to the single-frame repetition of each target video frame image in the one or more target video frame images that are finally determined. The method of the present application can improve the efficiency of video repetition detection and save detection computing resources.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of communications, and in particular to a technology for detecting video repetition. Background Art

[0002] With the development of the times, more and more users upload videos to the Internet. In particular, the popularity of short videos has given rise to the video economy. For example, users can earn certain income by uploading short videos. At the same time, it has also given rise to the pirated copying industry. Pirated videos are often partially modified from the original videos or uploaded directly to the Internet as their own videos without modification, resulting in damage to the interests of the creators of the original videos. Summary of the invention

[0003] An object of the present application is to provide a method and device for detecting video repetition.

[0004] According to one aspect of the present application, a method for detecting video repetition is provided, the method comprising:

[0005] Acquire one or more first video frame images of first video information;

[0006] Detecting, frame by frame, whether there is a target video frame image that meets a repetition detection condition in the one or more first video frame images according to the first feature combination of the second video information;

[0007] For each frame of the target video frame image that meets the repetition detection condition, determining the single-frame repetition of the target video frame image according to the ratio of the number of second target objects appearing in the target detection area of ​​the target video frame image to the total number of all objects appearing in the target detection area;

[0008] The video repetition degree of the first video information and the second video information is determined according to the single frame repetition degree of each target video frame image in the one or more target video frame images that are finally determined.

[0009] According to one aspect of the present application, a device for detecting video repetition is provided, the device comprising:

[0010] A module, configured to obtain one or more first video frame images of first video information;

[0011] A second module is used to detect, frame by frame, whether there is a target video frame image that meets a repetition detection condition in the one or more first video frame images according to the first feature combination of the second video information;

[0012] A module 3 is used to determine the single-frame repetition of the target video frame image according to the ratio of the number of second target objects appearing in the target detection area of ​​the target video frame image to the total number of all objects appearing in the target detection area for each frame of the target video frame image that meets the repetition detection condition;

[0013] A module 4 is used to determine the video repetition degree of the first video information and the second video information according to the single frame repetition degree of each target video frame image in one or more target video frame images that are finally determined.

[0014] According to one aspect of the present application, a device for detecting video repetition is provided, wherein the device comprises:

[0015] Processor; and

[0016] A memory arranged to store computer executable instructions which, when executed, cause the processor to perform the operations of any of the methods described above.

[0017] According to one aspect of the present application, a computer-readable medium storing instructions is provided, wherein when the instructions are executed, the system performs the operation of any of the methods described above.

[0018] Compared with the prior art, the present application obtains one or more first video frame images of the first video information when detecting the video repetition between the first video information and the second video information. The target video frame image is determined frame by frame according to the first feature combination of the second video information. The target video frame image is determined by screening, and only the target video frame image is further tested for repetition, thereby improving the detection efficiency.

[0019] In order to further improve the detection efficiency, for each frame of the target video frame image, the single-frame repetition of the target video frame image is determined according to the ratio of the number of second target objects appearing in the target detection area of ​​the target video frame image to the total number of all objects appearing in the target detection area. By only identifying the number of second target objects in the target detection area and the total number of all objects in the target detection area to determine the single-frame repetition of the target video frame image, the repetition detection area is further narrowed to the target detection area, thereby further improving the efficiency of repetition detection.

[0020] Finally, for the video repetition between the first video information and the second video information, the overall video repetition between the first video information and the second video information can be determined according to the single frame repetition of each target video frame image in the one or more target video frame images.

[0021] In summary, the present application provides a method that can greatly improve the efficiency of video repetition detection and save detection computing resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0023] Figure 1 A flow chart of a method for detecting video repetition according to an embodiment of the present application is shown;

[0024] Figure 2 A flowchart of extracting a first feature combination and a second feature combination of second video information according to an embodiment of the present application is shown;

[0025] Figure 3 A structural diagram of a device for detecting video repetition according to an embodiment of the present application is shown;

[0026] Figure 4 An exemplary system is shown that can be used to implement the various embodiments described in this application.

[0027] The same or similar reference numerals in the drawings represent the same or similar components. DETAILED DESCRIPTION

[0028] The present application is described in further detail below in conjunction with the accompanying drawings.

[0029] In a typical configuration of the present application, the terminal, the device of the service network and the trusted party all include one or more processors (eg, a central processing unit (CPU)), an input / output interface, a network interface and a memory.

[0030] Memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash memory. Memory is an example of a computer-readable medium.

[0031] Computer readable media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer readable instructions, data structures, modules of programs or other data. Examples of computer storage media include, but are not limited to, Phase-Change Memory (PCM), Programmable Random Access Memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of random access memory (RAM), Read-Only Memory (ROM), Electrically-Erasable Programmable Read-Only Memory (EEPROM), Flash memory or other memory technology, Compact Disc Read-Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0032] The devices referred to in this application include but are not limited to terminals, network devices, or devices formed by integrating terminals and network devices through a network. The terminal includes but is not limited to any mobile electronic product that can interact with a user (for example, interact with a user through a touchpad), such as a smart phone, a tablet computer, etc. The mobile electronic product can use any operating system, such as an Android operating system, an iOS operating system, etc. Among them, the network device includes an electronic device that can automatically perform numerical calculations and information processing according to pre-set or stored instructions, and its hardware includes but is not limited to a microprocessor, an application specific integrated circuit (ASIC), a programmable logic device (PLD), a field programmable gate array (FPGA), a digital signal processor (DSP), an embedded device, etc. The network device includes but is not limited to a computer, a network host, a single network server, a plurality of network server sets or a cloud composed of multiple servers; here, the cloud is composed of a large number of computers or network servers based on cloud computing (Cloud Computing), wherein cloud computing is a type of distributed computing, a virtual supercomputer composed of a group of loosely coupled computer sets. The network includes but is not limited to the Internet, wide area network, metropolitan area network, local area network, VPN network, wireless self-organizing network (Ad Hoc network), etc. Preferably, the device may also be a program running on the terminal, network device, or a device formed by integrating the terminal and network device, network device, touch terminal, or network device and touch terminal through a network.

[0033] Of course, those skilled in the art should understand that the above-mentioned devices are only examples, and other existing or future devices that are applicable to the present application should also be included in the scope of protection of the present application and are included here by reference.

[0034] In the description of the present application, “plurality” means two or more, unless otherwise clearly and specifically defined.

[0035] Here, it should be noted that the execution subject of the method for detecting video repetition described in the present application can be a network device or a user device. For example, the user uploads the first video information to the network device, and the network device detects the video repetition of the first video information and the second video information. For another example, the user transmits the first video information to the user device, and the user device detects the video repetition of the first video information and the second video information. In some embodiments, the network device includes but is not limited to a server (for example, a server corresponding to a video repetition detection APP). In some embodiments, the user device includes but is not limited to computing devices such as mobile phones, computers, and tablet computers. The "object" described in this application includes but is not limited to various items such as houses, cars, and books. For example, based on image recognition technology, objects appearing in video frame images or objects appearing in a certain area can be identified.

[0036] Figure 1 A flow chart of a method for detecting video repetition according to an embodiment of the present application is shown, and the method includes step S11, step S12, step S13 and step S14. Specifically, in step S11, one or more first video frame images of the first video information are obtained. In step S12, whether there is a target video frame image that meets the repetition detection condition in the one or more first video frame images is detected frame by frame according to the first feature combination of the second video information. In step S13, for each frame of the target video frame image that meets the repetition detection condition, the single-frame repetition of the target video frame image is determined according to the ratio of the number of second target objects appearing in the target detection area of ​​the target video frame image to the total number of all objects appearing in the target detection area. In step S14, the video repetition of the first video information and the second video information is determined according to the single-frame repetition of each target video frame image in the one or more target video frame images that are finally determined.

[0037] Specifically, in step S11, one or more first video frame images of the first video information are obtained. In some embodiments, the first video information includes video information to be detected. In some embodiments, the video information includes one or more video frame images arranged in a time sequence. In some embodiments, the one or more first video frame images are all video frame images of the first video information; in other embodiments, the one or more first video frame images are partial video frame images extracted from the first video information (for example, one or more first video frame images of the first video information are extracted for detection).

[0038] In step S12, the one or more first video frame images are detected frame by frame based on the first feature combination of the second video information to see whether there is a target video frame image that meets the repetition detection condition. In some embodiments, the second video information includes the video information to be compared, for example, it is necessary to detect the video repetition between the first video information and the second video information. In some embodiments, in order to improve detection efficiency and save computing resources, the target video frame image that meets the repetition detection condition is determined from the acquired one or more first video frame images, and then the single-frame repetition of the target video frame image is further detected. For the first video frame image that does not meet the repetition detection condition, it is discarded and the single-frame repetition of the first video frame image is no longer calculated. For example, the acquired one or more first video frame images include: first video frame image 1, first video frame image 2, first video frame image 3, first video frame image 4, first video frame image 5 (in some embodiments, the first video frame image 1, first video frame image 2, first video frame image 3, first video frame image 4, first video frame image 5 are partial video frame images extracted from the first video information, wherein the 1, 2, 3, 4, 5 are only used to indicate the order of the video frame images, but do not represent the specific number of frames, for example, the first video frame image 2 is located after the first video frame image 1), if the first video frame image 1 meets the repetition detection condition, the first video frame 1 is determined as the target video frame image. If the first video frame 1 does not meet the repetition detection condition, the first video frame image 2 is sequentially detected to see if it meets the repetition detection condition. If the first video frame image 2 meets the repetition detection condition, the first video frame image 2 is determined as the target video frame image, and so on, the detection is performed frame by frame in the order of the one or more first video frame images. In some embodiments, a first video frame image having a higher matching degree with the first feature combination is searched in the one or more frames of the first video image according to the first feature combination, and the first video frame image is determined as the target video frame image that meets the repetition detection condition. For example, the first feature combination includes one or more first feature objects, and the one or more frames of the first video frame image are detected frame by frame according to the one or more first feature objects to determine whether there is an object matching the one or more first feature objects. If so, it is determined that the first video frame image meets the repetition detection condition. In some embodiments, a feature database is established in the network device (for example, when the execution subject is a network device) or the user device (for example, when the execution subject is a user device), and the network device or the user device can obtain the first feature combination of the second video information from the feature database.

[0039] In step S13, for each frame of the target video frame image that meets the repeatability detection condition, the single-frame repeatability of the target video frame image is determined according to the ratio of the number of second target objects appearing in the target detection area of ​​the target video frame image to the total number of all objects appearing in the target detection area. In some embodiments, in order to further improve the detection efficiency and save computing resources, when calculating the single-frame repeatability of the target video frame image, it is necessary to determine the target detection area of ​​the target video frame image, and then further identify the second target object in the target detection area, and determine the single-frame repeatability of the target video frame image by calculating the ratio of the number of the second target object to the total number of all objects in the target detection area. In some embodiments, the target detection area is determined based on the first target object. For the determination process of the target detection area, please refer to the following embodiments, which will not be repeated here. In some embodiments, the second target object is identified according to the second feature combination corresponding to the first feature combination. For the identification process of the second target object, please refer to the following embodiments, which will not be repeated here. For example, the number of the second target objects appearing in the target detection area is 2, and the total number of all objects appearing in the target detection area is 5, then the single-frame repetition degree of the target video frame image is 0.4.

[0040] In step S14, the video repetition of the first video information and the second video information is determined based on the single-frame repetition of each target video frame image in the one or more target video frame images. In some embodiments, the determination of the video repetition of the first video information and the second video information is based on the single-frame repetition of each target video frame image. For example, for one or more first video frame images of the first video information, a total of three target video frame images are determined, wherein the single-frame repetition of the target video frame image 1 is 0.4, the single-frame repetition of the target video frame image 2 is 0.2, and the single-frame repetition of the target video frame image 3 is 0.1, then the video repetition of the first video information and the second video information is 0.4+0.2+0.1=0.7. Further, the video repetition can be compared with a preset video repetition threshold. If the calculated video repetition is greater than or equal to the video repetition threshold, it can be determined that the first video information has the possibility of plagiarizing the second video information, or the second video information has the possibility of plagiarizing the first video information.

[0041] In some embodiments, the first feature combination includes at least three first feature objects, and the step S12 includes: detecting whether there are at least three first target objects in each of the one or more first video frame images according to the at least three first feature objects, wherein the at least three first target objects match the at least three first feature objects; if so, determining the first video frame image as the target video frame image that meets the repetition detection condition; the method further includes step S14 (not shown) before step S13, in which, for each frame of the target video frame image, the target detection area of ​​the target video frame image is determined according to the at least three first target objects existing in the target video frame image. In some embodiments, the first feature combination includes at least three first feature objects (for example, a cup, a notebook, a pencil), and the determination of the target video frame image is to detect whether there are at least three first target objects matching the at least three first feature objects (for example, matching content and / or matching position) in the one or more first video frame images according to the at least three first feature objects, and if so, the first video frame image is used as the target video frame image. In some embodiments, for each frame of the target video frame image that satisfies the repetition detection condition, the target detection area of ​​the target video frame image is determined based on the at least three first target objects in the target video frame image, so as to further identify the second target object in the target detection area and calculate the single frame repetition of the target video frame image. In some embodiments, in the second video information, the at least three first feature objects are used to determine the feature area. Therefore, the target detection area determined based on at least three first target objects matching the at least three first feature objects corresponds to the feature area of ​​the second video information, so that the repetition detection between the first video information and the second video information can be limited to the target detection area (for example, the ratio of the number of second target objects in the target detection area to the total number of objects in the target detection area) to improve the detection efficiency. In some embodiments, in order to ensure that the target detection area can be determined based on the first target object, the number of the first target objects needs to be at least three.

[0042] In some embodiments, the at least three first target objects match the at least three first feature objects, including: the content information of the at least three first target objects matches the content information of the at least three first feature objects, and the position information of the at least three first target objects matches the position information of the at least three first feature objects. In some embodiments, the content information matching includes but is not limited to matching size, color, image content, etc. For example, the first feature combination includes 5 first feature objects (for example, a cup, a notebook, a pencil, a tissue, and a school bag), and the first video frame image is detected frame by frame based on image recognition technology to see whether there is a cup, notebook, pencil, tissue, or school bag similar to the cup, notebook, pencil, tissue, or school bag. In some embodiments, the position information matching includes but is not limited to: similar coordinates (for example, the first feature combination also records the specific coordinates of each first feature object, and the coordinates of the object matched with the first feature object are compared with the coordinates of the first feature object. If the difference is equal to or less than the difference threshold, it is determined that the position information is matched), or the orientation between the objects is the same (for example, the orientation between the first feature objects is recorded in the first feature combination, for example, the first feature object 1 is at the lower left of the first feature object 2... If the orientation between the object 1 matched with the first feature object 1 and the first feature object 2 and the object 2 is also object 1 at the lower left of object 2, it is determined that the position information is matched). If it is detected that there is a cup, notebook, pencil, tissue, or schoolbag in the first video frame image that matches the content information and position information of the cup, notebook, pencil, tissue, or schoolbag, it is determined that the first video frame image is a target video frame image that meets the repetition detection condition, and the cup, notebook, pencil, tissue, or schoolbag in the first video frame image is used as the first target object.

[0043] In some embodiments, the target detection area of ​​the target video frame image is determined based on the at least three first target objects present in the target video frame image, including: using the at least three first target objects as connection endpoints to determine the target detection area of ​​the target video frame image. For example, the first feature combination includes: first feature object 1, first feature object 2, first feature object 3, and the first feature object 1 is at the lower left of the first feature object 2, and the first feature object 3 is at the lower right of the first feature object 2, then the target detection area composed of the first feature object 1, the first feature object 2, and the first feature object 3 as connection endpoints is a triangle. In some embodiments, the target detection area is determined based on the first target object so as to identify the second target object in the target detection area.

[0044] In some embodiments, the step S13 includes step S131 (not shown) and step S132. In step S131, for each frame of the target video frame image, the second target object appearing in the target detection area of ​​the target video image is identified according to the second feature combination corresponding to the first feature combination; in step S132, the single frame repetition of the target video frame image is determined according to the ratio of the number of the second target objects to the total number of all objects appearing in the target detection area. In some embodiments, the first feature combination has a corresponding second feature combination. In some embodiments, the corresponding relationship between the first feature combination and the second feature combination is reflected in that the first feature combination and the second feature combination are determined based on the same frame of the second video frame image of the second video information. In some embodiments, the first feature combination is used to determine a target video frame image with a higher matching degree with the first feature combination. For example, the first feature combination includes at least three first feature objects, and according to the at least three first feature objects, a target video frame image including at least three first target objects matching the at least three first feature objects is queried from the one or more frames of the first video frame image. In some embodiments, the second feature combination is used to identify the second target object in the target detection area. For example, the second feature combination includes a second feature object, and the second target object matching the second feature object in the target detection area is identified according to the second feature object. Further, the single-frame repetition of the target detection area is determined according to the ratio of the number of the identified second target objects to the total number of objects in the target detection area. In some embodiments, in the second video information, the first feature object combination is used to determine the feature area. Therefore, the target detection area determined based on at least three first target objects matching the first feature combination corresponds to the feature area of ​​the second video information, so that the repetition detection between the first video information and the second video information can be limited to the target detection area (for example, the ratio of the number of second target objects in the target detection area to the total number of objects in the target detection area) to improve the detection efficiency. In some embodiments, the second feature combination is determined based on the feature area (for example, identifying the object in the feature area and taking the object as the second feature object in the second feature combination). Therefore, the single-frame repetition of the target video frame image is detected by identifying the second target object matching the second feature combination in the target detection area according to the second feature combination.

[0045] In some embodiments, the second feature combination includes a second feature object, and the step S131 includes: for each frame of the target video frame image, identifying a second target object that appears in the target detection area of ​​the target video frame image according to the second feature object, wherein the content information of the second target object matches the content information of the second feature object, and the position information of the second target object matches the position information of the second feature object. In some embodiments, the second feature object is not limited to objects such as houses and trees. In some embodiments, the content information matching includes but is not limited to matching of size, color, image content, etc. For example, the second feature combination includes 3 second feature objects (e.g., a cup, a notebook, and a pencil), and based on image recognition technology, it is identified whether there is a cup, a notebook, or a pencil similar to the cup, notebook, or pencil in the target video frame image. In some embodiments, the position information matching includes but is not limited to: similar coordinates (for example, the second feature combination also records the specific coordinates of each second feature object, and the coordinates of the identified object matching the second feature object are compared with the coordinates of the second feature object. If the difference is equal to or less than the difference threshold, it is determined that the position information is matched), or the orientation between objects is the same (for example, the orientation between each second feature object is recorded in the second feature combination, for example, second feature object 1 is at the lower left of second feature object 2... If the orientation between object 1 identified to match the second feature object 1 and second feature object 2 and object 2 is also object 1 at the lower left of object 2, it is determined that the position information is matched).

[0046] In some embodiments, the first feature combination includes at least three first feature objects, the second feature combination includes a second feature object, and the at least three first feature objects and the second feature object exist in the same frame of the second video frame image of the second video information. In some embodiments, the correspondence between the first feature combination and the second feature combination is reflected in that the first feature combination and the second feature combination are determined based on the same frame of the second video frame image of the second video information. In some embodiments, at least three first feature objects in the first feature combination include a group that appears in the same second video frame image at the same time and appears more times. For the case where there are several groups of object combinations that appear more times, the largest group can be selected as the first feature combination, or a group can be randomly selected from the top N groups of object combinations as the first feature combination. For example, in multiple frames of the second video frame images of the second video information A, a group of object combinations that appear in the same frame of the second video frame image at the same time and appear more times include: cup, notebook, pencil, tissue, and it is determined that the first feature combination of the second video information includes the first feature objects of the cup, notebook, pencil, and tissue. In some embodiments, in each frame of the second video frame image including the first feature combination, a feature area can be determined based on at least three first feature objects of the first feature combination, and the second feature object is an object within the feature area. Since the first feature combination is a group of object combinations that appear simultaneously in multiple frames of the second video frame image and appear a large number of times, the first feature combination in each frame of the second video frame image can determine a feature area, and the second feature object can be identified in each feature area. Therefore, one first feature combination may correspond to multiple second feature combinations. In some embodiments, the second feature combination used to identify the target detection area can be a second feature combination determined randomly.

[0047] In some embodiments, the method further includes step S15 (not shown), in which the first feature combination of the second video information is determined. In some embodiments, it is necessary to determine the first feature combination of the second video information so as to perform video repetition detection based on the first feature combination and other video information (e.g., the first video information). In some embodiments, after determining the first feature combination of the second video information, the first feature combination can be stored in a feature database so that when used, the first feature combination of the second video information can be queried from the feature database to facilitate timely video repetition detection with other video information.

[0048] In some embodiments, the second video information includes one or more frames of second video frame images, and the step S15 includes step S151 (not shown), step S152, and step S153. In step S151, objects appearing in each of the one or more frames of second video frame images are identified; in step S152, one or more object combinations appearing simultaneously in multiple frames of second video frame images are determined, wherein each of the object combinations includes at least three first feature objects; in step S153, the first feature combination is determined according to the number of times each of the one or more object combinations appears. In some embodiments, for each frame of the second video frame image, an object in the second video frame image is identified. For example, the second video information includes second video frame image 1, second video frame image 2, second video frame image 3, second video frame image 4, second video frame image 5, and second video frame image 6, wherein second video frame image 1 includes first feature object 1, first feature object 2, first feature object 3, and first feature object 4; second video frame image 2 includes first feature object 1, first feature object 2, and first feature object 3; second video frame image 3 includes first feature object 4, first feature object 5, and first feature object 6; second video frame image 4 includes first feature object 4, first feature object 5, and first feature object 6; second video frame image 5 includes first feature object 3, first feature object 4, and first feature object 5; second video frame image 6 includes first feature object 8. Determine one or more object combinations that appear simultaneously in multiple frames of the second video frame image, for example, first feature object 1, first feature object 2, and first feature object 3 appear simultaneously in second video frame image 1 and second video frame image 2; first feature object 4, first feature object 5, and first feature object 6 appear simultaneously in second video frame image 3, second video frame image 4, and second video frame image 5. Determine the first feature combination according to the number of times each object combination in the one or more object combinations appears, for example, determine a group of object combinations with a larger number of appearances as the first feature combination of the second video information (for example, the first feature object 3, the first feature object 4, and the first feature object 5).

[0049] In some embodiments, step S152 includes step S1521 (not shown) and step S1522. In step S1521, one or more object combinations that appear simultaneously in multiple frames of the second video frame image are determined, wherein each of the object combinations includes at least three candidate objects; in step S1522, the at least three first feature objects are determined based on the position information between the at least three candidate objects. In some embodiments, the first feature object in each object combination is determined from the candidate objects. For example, one or more object combinations that appear simultaneously in multiple frames of the second video frame image are determined, wherein at least three objects in each object combination are used as candidate objects, and at least three first feature objects are determined from the candidate objects based on the position information between the candidate objects to ensure that the at least three first feature objects determined can enclose a feature area.

[0050] In some embodiments, the step S1522 includes: if the number of the at least three candidate objects is greater than three, and at least one of the at least three candidate objects is not on the same straight line as the other candidate objects, then the at least three candidate objects are used as the at least three first feature objects of the object combination. In some embodiments, the number of the first feature objects is not limited. If the number of at least three candidate objects in the same object combination is greater than three (for example, 4, 5, etc.), as long as there is one candidate object that is not on the same straight line as the other candidate objects, the at least three candidate objects can be used as the at least three first feature objects to ensure that the determined at least three first feature objects can enclose a feature area.

[0051] In some embodiments, step S1522 includes: determining three first feature objects from the at least three candidate objects, wherein the position information between the three first feature objects satisfies the target condition. In other embodiments, three candidate objects may be selected from the at least three candidate objects as the first feature objects, and the position information of the three first feature objects needs to meet the target condition. For example, the target condition includes but is not limited to that the three first feature objects are not on the same straight line; the distance between the three first feature objects is equal to or greater than the distance threshold. This ensures that the three first feature objects can form a feature area well.

[0052] In some embodiments, step S153 includes: sorting the one or more object combinations in descending order according to the number of occurrences of each object combination in the one or more object combinations; determining the object combination ranked in the top N as the first feature combination, wherein N is a positive integer. In some embodiments, N includes but is not limited to positive integers such as 1 and 2. For example, the second video information includes one or more groups of first feature combinations. In some embodiments, the number of occurrences of each group of object combinations is sorted, and the object combination ranked in the top N is determined as the first feature combination of the second video information. In some embodiments, although the second video information includes N groups of first feature combinations, in actual applications, one group of first feature combinations can be selected, and the video repetition is detected according to the first feature combination (for example, the target video frame image is determined frame by frame from the one or more frames of the first video frame image according to the first feature combination). In order to improve the accuracy of the detection, one first feature combination can be selected from the N groups of first feature combinations to detect the video repetition (for example, the target video frame image is determined frame by frame from the one or more frames of the first video frame image according to the first feature combination).

[0053] In some embodiments, the method further includes step S16 (not shown). In step S16, a second feature combination corresponding to the first feature combination is determined. In some embodiments, the second feature combination is in a corresponding relationship with the first feature combination. In some embodiments, since the first feature combination is a group of object combinations that appear simultaneously in multiple frames of the second video frame image and appear a large number of times, the first feature combination in each frame of the second video frame image can determine a feature area, and a second feature object can be identified in each feature area. Therefore, a first feature combination may correspond to multiple second feature combinations. In some embodiments, the second feature combination used to identify the target detection area can be a second feature combination determined randomly.

[0054] In some embodiments, the determining of the second feature combination corresponding to the first feature combination includes: for each of the first feature combinations, in each frame of the second video frame image where at least three first feature objects of the first feature combination appear simultaneously, using the at least three first feature objects appearing in the second video frame image as connection endpoints to determine a feature region in the second video frame image where the at least three first feature objects are located; identifying one or more objects in the feature region, and determining the one or more objects as the second feature objects of the second feature combination. For example, in multiple frames of the second video frame image of the second video information A, a group of object combinations that appear simultaneously in the same frame of the second video frame image and appear more times include: a cup, a notebook, a pencil, and a tissue, then it is determined that the first feature combination of the second video information includes the first feature objects of the cup, the notebook, the pencil, and the tissue. In some embodiments, in each frame of the second video frame image including the first feature combination, a feature region can be determined based on the at least three first feature objects of the first feature combination, and the second feature object is an object in the feature region. In some embodiments, since the first feature combination is a group of object combinations that appear simultaneously in multiple frames of the second video frame image and appear a large number of times, the first feature combination in each frame of the second video frame image can determine a feature area, and the second feature object can be identified in each feature area. Therefore, one first feature combination may correspond to multiple second feature combinations. In some embodiments, the second feature combination used to identify the target detection area can be a second feature combination determined randomly.

[0055] In some embodiments, the step S13 includes: for each frame of the target video frame image, according to the ratio of the number of second target objects appearing in the target detection area of ​​the target video frame image to the total number of objects appearing in the target detection area, and in combination with the first ratio and the first weight of the number of first target objects to the total number of objects in the target video frame image, determine the single frame repetition of the target video frame image, wherein the first weight corresponds to the first ratio. In some embodiments, in order to further improve the accuracy of detection, the single frame repetition of the target video frame image is calculated in combination with the number of the first target objects and the total number of objects in the target video frame image. For example, the single frame repetition r = (d / K) * (b / M * 0.1), wherein d is the number of second target objects, K is the total number of objects appearing in the target detection area, b is the number of first target objects, M is the total number of objects in the target video frame image, and 0.1 is the first weight.

[0056] In some embodiments, the step S13 includes: for each frame of the target video frame image, according to the ratio of the number of second target objects appearing in the target detection area of ​​the target video frame image to the total number of objects appearing in the target detection area, and in combination with the first ratio of the number of first target objects to the total number of objects in the target video frame image, the first weight, the second ratio of the area of ​​the target detection area to the total area of ​​the target video frame image, and the second weight, the video frame matching degree of the target video frame image is determined, wherein the first weight corresponds to the first ratio, and the second weight corresponds to the second ratio. In some embodiments, in order to further improve the accuracy of detection, in addition to combining the first target object number with the total number of objects in the target video frame image, the single-frame repetition degree of the target video frame image is also calculated in combination with the area of ​​the target detection area and the total area of ​​the target video frame image. For example, the single-frame repetition rate r = (d / K)*(b / M*0.1)*(c / J*0.5), wherein d is the number of second target objects, K is the total number of objects appearing in the target detection area, b is the number of first target objects, M is the total number of objects in the target video frame image, 0.1 is the first weight, c is the area of ​​the target detection area, J is the total area of ​​the target video frame image, and 0.5 is the second weight.

[0057] In some embodiments, the S14 includes: determining a third ratio of the number of frames of the one or more first video frame images to the total number of frames of the first video frame information; determining the video matching degree of the first video information and the second video information according to the single frame repetition of each frame of the target video frame image in the one or more target video frame images and the third ratio. In some embodiments, the one or more first video frame images obtained are partial video frame images of the first video information (for example, partial video frame images extracted from the first video information). When calculating the video repetition of the first video information and the second video information, it is necessary to combine the number of frames of the extracted first video frame image with the total number of frames of the first video information for calculation. For example, the total number of frames of the first video information is N, the number of frames of the one or more first video frame images extracted is n, and the video repetition R = (∑r) / (n / N).

[0058] Figure 2A flow chart of extracting the first feature combination and the second feature combination of the second video information according to an embodiment of the present application is shown. Video 1 is scanned frame by frame (for example, the second video information), items (for example, the object) are identified, temporarily stored, several item combinations with the highest frequency of occurrence (for example, the first feature combination) are selected, the enclosed range (for example, the feature area) is determined, and items within the identification range (for example, the second feature object) and the general orientation relationship (for example, the position information) are stored. The video feature library (for example, the feature library) is stored. After subsequently acquiring one or more first video frame images of the first video information, the video repetition is detected based on the feature information of the second video information recorded in the feature library (for example, the first feature combination and the second feature combination).

[0059] Figure 3 A device structure diagram of a device for detecting video repetition according to an embodiment of the present application is shown, and the device includes a module 11, a module 12, a module 13, and a module 14. Specifically, module 11 is used to obtain one or more frames of first video frame images of the first video information. Module 12 is used to detect frame by frame whether there is a target video frame image that meets the repetition detection condition in the one or more frames of the first video frame images according to the first feature combination of the second video information. Module 13 is used to determine the single-frame repetition of the target video frame image according to the ratio of the number of second target objects appearing in the target detection area of ​​the target video frame image to the total number of all objects appearing in the target detection area for each frame of the target video frame image that meets the repetition detection condition. Module 14 is used to determine the video repetition of the first video information and the second video information according to the single-frame repetition of each frame of the target video frame image in the one or more frames of the target video frame images that are finally determined.

[0060] Specifically, a module is used to obtain one or more first video frame images of the first video information. In some embodiments, the first video information includes video information to be detected. In some embodiments, the video information includes one or more video frame images arranged in a time sequence. In some embodiments, the one or more first video frame images are all video frame images of the first video information; in other embodiments, the one or more first video frame images are partial video frame images extracted from the first video information (for example, one or more first video frame images of the first video information are extracted for detection).

[0061] Module one and module two are used to detect frame by frame whether there is a target video frame image that meets the repetition detection condition in the one or more frames of the first video frame image according to the first feature combination of the second video information. In some embodiments, the second video information includes the video information to be compared, for example, it is necessary to detect the video repetition between the first video information and the second video information. In some embodiments, in order to improve detection efficiency and save computing resources, the target video frame image that meets the repetition detection condition is determined from the acquired one or more frames of the first video frame image, and then the single-frame repetition of the target video frame image is further detected. For the first video frame image that does not meet the repetition detection condition, it is discarded and the single-frame repetition of the first video frame image is no longer calculated. For example, the acquired one or more first video frame images include: first video frame image 1, first video frame image 2, first video frame image 3, first video frame image 4, first video frame image 5 (in some embodiments, the first video frame image 1, first video frame image 2, first video frame image 3, first video frame image 4, first video frame image 5 are partial video frame images extracted from the first video information, wherein the 1, 2, 3, 4, 5 are only used to indicate the order of the video frame images, but do not represent the specific number of frames, for example, the first video frame image 2 is located after the first video frame image 1), if the first video frame image 1 meets the repetition detection condition, the first video frame 1 is determined as the target video frame image. If the first video frame 1 does not meet the repetition detection condition, the first video frame image 2 is sequentially detected to see if it meets the repetition detection condition. If the first video frame image 2 meets the repetition detection condition, the first video frame image 2 is determined as the target video frame image, and so on, the detection is performed frame by frame in the order of the one or more first video frame images. In some embodiments, a first video frame image having a higher matching degree with the first feature combination is searched in the one or more frames of the first video image according to the first feature combination, and the first video frame image is determined as the target video frame image that meets the repetition detection condition. For example, the first feature combination includes one or more first feature objects, and the one or more frames of the first video frame image are detected frame by frame according to the one or more first feature objects to determine whether there is an object matching the one or more first feature objects. If so, it is determined that the first video frame image meets the repetition detection condition. In some embodiments, a feature database is established in the network device (for example, when the execution subject is a network device) or the user device (for example, when the execution subject is a user device), and the network device or the user device can obtain the first feature combination of the second video information from the feature database.

[0062] A module 13 is used to determine the single-frame repetition of the target video frame image according to the ratio of the number of second target objects appearing in the target detection area of ​​the target video frame image to the total number of all objects appearing in the target detection area for each frame of the target video frame image that meets the repetition detection condition. In some embodiments, in order to further improve the detection efficiency and save computing resources, when calculating the single-frame repetition of the target video frame image, it is necessary to determine the target detection area of ​​the target video frame image, and then further identify the second target object in the target detection area, and determine the single-frame repetition of the target video frame image by calculating the ratio of the number of the second target object to the total number of all objects in the target detection area. In some embodiments, the target detection area is determined based on the first target object. For the determination process of the target detection area, please refer to the following embodiments, which will not be repeated here. In some embodiments, the second target object is identified based on the second feature combination corresponding to the first feature combination. For the identification process of the second target object, please refer to the following embodiments, which will not be repeated here. For example, the number of the second target objects appearing in the target detection area is 2, and the total number of all objects appearing in the target detection area is 5, then the single-frame repetition degree of the target video frame image is 0.4.

[0063] A module 14 is used to determine the video repetition of the first video information and the second video information according to the single-frame repetition of each target video frame image in the one or more target video frame images. In some embodiments, the determination of the video repetition of the first video information and the second video information is based on the single-frame repetition of each target video frame image. For example, for one or more first video frame images of the first video information, a total of three target video frame images are determined, wherein the single-frame repetition of target video frame image 1 is 0.4, the single-frame repetition of target video frame image 2 is 0.2, and the single-frame repetition of target video frame image 3 is 0.1, then the video repetition of the first video information and the second video information is 0.4+0.2+0.1=0.7. Further, the video repetition can be compared with a preset video repetition threshold. If the calculated video repetition is greater than or equal to the video repetition threshold, it can be determined that the first video information has the possibility of plagiarizing the second video information, or the second video information has the possibility of plagiarizing the first video information.

[0064] In some embodiments, the first feature combination includes at least three first feature objects, and the one-two module is used to: detect frame by frame whether there are at least three first target objects in each first video frame image of the one or more first video frame images according to the at least three first feature objects, wherein the at least three first target objects match the at least three first feature objects; if so, determine the first video frame image as the target video frame image that meets the repetition detection condition; the device also includes a four-module (not shown), the one-four-module being used to determine, for each frame of the target video frame image, a target detection area of ​​the target video frame image according to the at least three first target objects present in the target video frame image.

[0065] Here, the specific implementation methods corresponding to the one and two modules are the same as or similar to the specific implementation example of step S12, and thus will not be described in detail and are included herein by reference.

[0066] In some embodiments, the at least three first target objects match the at least three first feature objects, including: the content information of the at least three first target objects matches the content information of the at least three first feature objects, and the position information of the at least three first target objects matches the position information of the at least three first feature objects. In some embodiments, the content information matching includes but is not limited to matching size, color, image content, etc. For example, the first feature combination includes 5 first feature objects (for example, a cup, a notebook, a pencil, a tissue, and a school bag), and the first video frame image is detected frame by frame based on image recognition technology to see whether there is a cup, notebook, pencil, tissue, or school bag similar to the cup, notebook, pencil, tissue, or school bag. In some embodiments, the position information matching includes but is not limited to: similar coordinates (for example, the first feature combination also records the specific coordinates of each first feature object, and the coordinates of the object matched with the first feature object are compared with the coordinates of the first feature object. If the difference is equal to or less than the difference threshold, it is determined that the position information is matched), or the orientation between the objects is the same (for example, the orientation between the first feature objects is recorded in the first feature combination, for example, the first feature object 1 is at the lower left of the first feature object 2... If the orientation between the object 1 matched with the first feature object 1 and the first feature object 2 and the object 2 is also object 1 at the lower left of object 2, it is determined that the position information is matched). If it is detected that there is a cup, notebook, pencil, tissue, or schoolbag in the first video frame image that matches the content information and position information of the cup, notebook, pencil, tissue, or schoolbag, it is determined that the first video frame image is a target video frame image that meets the repetition detection condition, and the cup, notebook, pencil, tissue, or schoolbag in the first video frame image is used as the first target object.

[0067] In some embodiments, the target detection area of ​​the target video frame image is determined based on the at least three first target objects present in the target video frame image, including: using the at least three first target objects as connection endpoints to determine the target detection area of ​​the target video frame image. For example, the first feature combination includes: first feature object 1, first feature object 2, first feature object 3, and the first feature object 1 is at the lower left of the first feature object 2, and the first feature object 3 is at the lower right of the first feature object 2, then the target detection area composed of the first feature object 1, the first feature object 2, and the first feature object 3 as connection endpoints is a triangle. In some embodiments, the target detection area is determined based on the first target object so as to identify the second target object in the target detection area.

[0068] In some embodiments, the module 13 includes a module 131 (not shown) and a module 132. The module 131 is used to identify, for each frame of the target video frame image, a second target object appearing in a target detection area of ​​the target video image according to a second feature combination corresponding to the first feature combination; the module 132 is used to determine a single-frame repetition degree of the target video frame image according to a ratio of the number of the second target objects to the total number of all objects appearing in the target detection area.

[0069] Here, the specific implementation corresponding to the one-three modules is the same as or similar to the specific implementation of step S13, and is therefore not repeated here and is included here by reference.

[0070] In some embodiments, the second feature combination includes a second feature object, and the one-three-one module: for each frame of the target video frame image, identifies a second target object appearing in the target detection area of ​​the target video frame image according to the second feature object, wherein the content information of the second target object matches the content information of the second feature object, and the position information of the second target object matches the position information of the second feature object.

[0071] Here, the specific implementation corresponding to the one-three-one module is the same as or similar to the specific implementation example of step S131, and is therefore not repeated here and is included here by reference.

[0072] In some embodiments, the first feature combination includes at least three first feature objects, the second feature combination includes a second feature object, and the at least three first feature objects and the second feature object exist in the same frame of the second video frame image of the second video information. In some embodiments, the correspondence between the first feature combination and the second feature combination is reflected in that the first feature combination and the second feature combination are determined based on the same frame of the second video frame image of the second video information. In some embodiments, at least three first feature objects in the first feature combination include a group that appears in the same second video frame image at the same time and appears more times. For the case where there are several groups of object combinations that appear more times, the largest group can be selected as the first feature combination, or a group can be randomly selected from the top N groups of object combinations as the first feature combination. For example, in multiple frames of the second video frame images of the second video information A, a group of object combinations that appear in the same frame of the second video frame image at the same time and appear more times include: cup, notebook, pencil, tissue, and it is determined that the first feature combination of the second video information includes the first feature objects of the cup, notebook, pencil, and tissue. In some embodiments, in each frame of the second video frame image including the first feature combination, a feature area can be determined based on at least three first feature objects of the first feature combination, and the second feature object is an object within the feature area. Since the first feature combination is a group of object combinations that appear simultaneously in multiple frames of the second video frame image and appear a large number of times, the first feature combination in each frame of the second video frame image can determine a feature area, and the second feature object can be identified in each feature area. Therefore, one first feature combination may correspond to multiple second feature combinations. In some embodiments, the second feature combination used to identify the target detection area can be a second feature combination determined randomly.

[0073] In some embodiments, the device further comprises a module (not shown) configured to determine the first feature combination of the second video information.

[0074] Here, the specific implementation corresponding to the one-five modules is the same as or similar to the specific implementation of step S15, and is therefore not repeated here and is included here by reference.

[0075] In some embodiments, the second video information includes one or more frames of second video frame images, and the one-five modules include a one-five-one module (not shown), a one-five-two module, and a one-five-three module. The one-five-one module is used to identify objects that appear in each of the one or more frames of the second video frame images; the one-five-two module is used to determine one or more object combinations that appear simultaneously in multiple frames of the second video frame images, wherein each of the object combinations includes at least three first feature objects; and the one-five-three module is used to determine the first feature combination according to the number of times each of the one or more object combinations appears.

[0076] Here, the specific implementation corresponding to the one-five modules is the same as or similar to the specific implementation of step S15, and is therefore not repeated here and is included here by reference.

[0077] In some embodiments, the 152 module includes a 1521 module (not shown) and a 1522 module, wherein the 1521 module is used to determine one or more object combinations that appear simultaneously in multiple frames of second video frame images, wherein each of the object combinations includes at least three candidate objects; and the 1522 module is used to determine the at least three first feature objects based on position information between the at least three candidate objects.

[0078] Here, the specific implementation corresponding to the 152 module is the same as or similar to the specific implementation of step S152, and is therefore not repeated here and is included here by reference.

[0079] In some embodiments, the 1522 module is used to: if the number of the at least three candidate objects is greater than three, and at least one of the at least three candidate objects is not on the same straight line as the other candidate objects, then the at least three candidate objects are used as the at least three first feature objects of the object combination.

[0080] Here, the specific implementation corresponding to the 1522 module is the same as or similar to the specific implementation of step S1522, and is therefore not repeated here and is included here by reference.

[0081] In some embodiments, the one-five-two-two module: determines three first feature objects from the at least three candidate objects, wherein position information between the three first feature objects satisfies the target condition.

[0082] Here, the specific implementation corresponding to the 1522 module is the same as or similar to the specific implementation of step S1522, and is therefore not repeated here and is included here by reference.

[0083] In some embodiments, the one-five-three module: sorts the one or more object combinations in descending order according to the number of occurrences of each object combination in the one or more object combinations; determines the object combinations ranked in the top N positions as the first feature combination, wherein N is a positive integer.

[0084] Here, the specific implementation corresponding to the 153 module is the same as or similar to the specific implementation of step S153, and is therefore not repeated here and is included here by reference.

[0085] In some embodiments, the device further includes a module (not shown) configured to determine a second feature combination corresponding to the first feature combination.

[0086] Here, the specific implementation corresponding to the one-six modules is the same as or similar to the specific implementation of step S16, and thus will not be described in detail and is included herein by reference.

[0087] In some embodiments, the determining of the second feature combination corresponding to the first feature combination includes: for each of the first feature combinations, in each frame of the second video frame image where at least three first feature objects of the first feature combination appear simultaneously, using the at least three first feature objects appearing in the second video frame image as connection endpoints to determine a feature region in the second video frame image where the at least three first feature objects are located; identifying one or more objects in the feature region, and determining the one or more objects as the second feature objects of the second feature combination. For example, in multiple frames of the second video frame image of the second video information A, a group of object combinations that appear simultaneously in the same frame of the second video frame image and appear more times include: a cup, a notebook, a pencil, and a tissue, then it is determined that the first feature combination of the second video information includes the first feature objects of the cup, the notebook, the pencil, and the tissue. In some embodiments, in each frame of the second video frame image including the first feature combination, a feature region can be determined based on the at least three first feature objects of the first feature combination, and the second feature object is an object in the feature region. In some embodiments, since the first feature combination is a group of object combinations that appear simultaneously in multiple frames of the second video frame image and appear a large number of times, the first feature combination in each frame of the second video frame image can determine a feature area, and the second feature object can be identified in each feature area. Therefore, one first feature combination may correspond to multiple second feature combinations. In some embodiments, the second feature combination used to identify the target detection area can be a second feature combination determined randomly.

[0088] In some embodiments, the one-three modules are used to: for each frame of the target video frame image, determine the single-frame repetition of the target video frame image based on the ratio of the number of second target objects appearing in the target detection area of ​​the target video frame image to the total number of objects appearing in the target detection area, and in combination with a first ratio and a first weight of the number of first target objects to the total number of objects in the target video frame image, wherein the first weight corresponds to the first ratio.

[0089] Here, the specific implementation corresponding to the one-three modules is the same as or similar to the specific implementation of step S13, and is therefore not repeated here and is included here by reference.

[0090] In some embodiments, the one-three modules are used to: for each frame of the target video frame image, determine the video frame matching degree of the target video frame image based on the ratio of the number of second target objects appearing in the target detection area of ​​the target video frame image to the total number of objects appearing in the target detection area, and in combination with a first ratio of the number of first target objects to the total number of objects in the target video frame image, a first weight, a second ratio of the area of ​​the target detection area to the total area of ​​the target video frame image, and a second weight, wherein the first weight corresponds to the first ratio, and the second weight corresponds to the second ratio.

[0091] Here, the specific implementation corresponding to the one-three modules is the same as or similar to the specific implementation of step S13, and is therefore not repeated here and is included here by reference.

[0092] In some embodiments, the one-four modules are used to: determine a third ratio of the number of frames of the one or more frames of the first video frame image to the total number of frames of the first video frame information; determine the video matching degree between the first video information and the second video information based on the single-frame repetition of each frame of the target video frame image in the one or more frames of the target video frame image and the third ratio.

[0093] Here, the specific implementation corresponding to the one-fourth module is the same as or similar to the specific implementation of step S14, and thus will not be described in detail and is included herein by reference.

[0094] In addition to the methods and devices described in the above embodiments, the present application also provides a computer-readable storage medium, which stores computer code. When the computer code is executed, the method described in any of the preceding items is executed.

[0095] The present application also provides a computer program product. When the computer program product is executed by a computer device, the method described in any of the preceding items is executed.

[0096] The present application also provides a computer device, the computer device comprising:

[0097] one or more processors;

[0098] a memory for storing one or more computer programs;

[0099] When the one or more computer programs are executed by the one or more processors, the one or more processors are caused to implement the method as described in any of the preceding items.

[0100] Figure 4 An exemplary system that can be used to implement various embodiments described in this application is shown;

[0101] like Figure 4 In some embodiments shown, the system 300 can be used as any of the devices in the various described embodiments. In some embodiments, the system 300 may include one or more computer-readable media (e.g., system memory or NVM / storage device 320) with instructions and one or more processors (e.g., (one or more) processors 305) coupled to the one or more computer-readable media and configured to execute instructions to implement modules to perform the actions described in this application.

[0102] For one embodiment, system control module 310 may include any suitable interface controller to provide any suitable interface to at least one of processor(s) 305 and / or any suitable device or component in communication with system control module 310 .

[0103] The system control module 310 may include a memory controller module 330 to provide an interface to the system memory 315. The memory controller module 330 may be a hardware module, a software module, and / or a firmware module.

[0104] The system memory 315 may be used, for example, to load and store data and / or instructions for the system 300. For one embodiment, the system memory 315 may include any suitable volatile memory, such as a suitable DRAM. In some embodiments, the system memory 315 may include double data rate type four synchronous dynamic random access memory (DDR4 SDRAM).

[0105] For one embodiment, system control module 310 may include one or more input / output (I / O) controllers to provide interfaces to NVM / storage device 320 and communication interface(s) 325 .

[0106] For example, NVM / storage device 320 may be used to store data and / or instructions. NVM / storage device 320 may include any suitable non-volatile memory (e.g., flash memory) and / or may include any suitable non-volatile storage device(s) (e.g., one or more hard disk drives (HDDs), one or more compact disk (CD) drives, and / or one or more digital versatile disk (DVD) drives).

[0107] NVM / storage device 320 may include storage resources that are physically part of the device on which system 300 is installed, or it may be accessible to the device without being part of the device. For example, NVM / storage device 320 may be accessed over a network via communication interface(s) 325.

[0108] Communication interface(s) 325 may provide an interface for system 300 to communicate over one or more networks and / or with any other suitable devices. System 300 may wirelessly communicate with one or more components of a wireless network in accordance with any of one or more wireless network standards and / or protocols.

[0109] For one embodiment, at least one of the processor(s) 305 may be packaged together with the logic of one or more controllers of the system control module 310 (e.g., the memory controller module 330). For one embodiment, at least one of the processor(s) 305 may be packaged together with the logic of one or more controllers of the system control module 310 to form a system-in-package (SiP). For one embodiment, at least one of the processor(s) 305 may be integrated on the same die with the logic of one or more controllers of the system control module 310. For one embodiment, at least one of the processor(s) 305 may be integrated on the same die with the logic of one or more controllers of the system control module 310 to form a system on chip (SoC).

[0110] In various embodiments, the system 300 may be, but is not limited to: a server, a workstation, a desktop computing device, or a mobile computing device (e.g., a laptop computing device, a handheld computing device, a tablet computer, a netbook, etc.). In various embodiments, the system 300 may have more or fewer components and / or a different architecture. For example, in some embodiments, the system 300 includes one or more cameras, a keyboard, a liquid crystal display (LCD) screen (including a touch screen display), a non-volatile memory port, multiple antennas, a graphics chip, an application specific integrated circuit (ASIC), and a speaker.

[0111] It should be noted that the present application can be implemented in software and / or a combination of software and hardware, for example, can be implemented using an application specific integrated circuit (ASIC), a general purpose computer or any other similar hardware device. In one embodiment, the software program of the present application can be executed by a processor to implement the steps or functions described above. Similarly, the software program of the present application (including relevant data structures) can be stored in a computer-readable recording medium, for example, a RAM memory, a magnetic or optical drive or a floppy disk and similar devices. In addition, some steps or functions of the present application can be implemented using hardware, for example, as a circuit that cooperates with a processor to perform each step or function.

[0112] In addition, a part of the present application may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present application through the operation of the computer. Those skilled in the art should understand that the existence of computer program instructions in computer-readable media includes but is not limited to source files, executable files, installation package files, etc., and accordingly, the way in which computer program instructions are executed by a computer includes but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to the computer.

[0113] Communication media include media by which communication signals containing, for example, computer readable instructions, data structures, program modules, or other data are transmitted from one system to another. Communication media may include guided transmission media such as cables and wires (e.g., fiber optic, coaxial, etc.) and wireless (unguided transmission) media that can propagate energy waves, such as acoustic, electromagnetic, RF, microwave, and infrared. Computer readable instructions, data structures, program modules, or other data may be embodied as a modulated data signal in, for example, a wireless medium such as a carrier wave or similar mechanism such as embodied as part of spread spectrum technology. The term "modulated data signal" refers to a signal whose one or more characteristics are changed or set in such a manner as to encode information in the signal. Modulation may be analog, digital, or a hybrid modulation technique.

[0114] By way of example and not limitation, computer-readable storage media may include volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. For example, computer-readable storage media include, but are not limited to, volatile memory, such as random access memory (RAM, DRAM, SRAM); and non-volatile memory, such as flash memory, various read-only memories (ROM, PROM, EPROM, EEPROM), magnetic and ferromagnetic / ferroelectric memories (MRAM, FeRAM); and magnetic and optical storage devices (hard disks, magnetic tapes, CDs, DVDs); or other media now known or later developed that can store computer-readable information / data for use by a computer system.

[0115] Here, according to an embodiment of the present application, a device is included, which includes a memory for storing computer program instructions and a processor for executing the program instructions, wherein, when the computer program instructions are executed by the processor, the device is triggered to run the methods and / or technical solutions based on the aforementioned multiple embodiments of the present application.

[0116] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the spirit or basic features of the present application. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present application is limited by the attached claims rather than the above description, so it is intended to include all changes that fall within the meaning and scope of the equivalent elements of the claims in the present application. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

Claims

1. A method for detecting video repetition, wherein: The method includes: Acquire one or more first video frame images of first video information; Detecting, frame by frame, whether there is a target video frame image that meets a repetition detection condition in the one or more first video frame images according to the first feature combination of the second video information; For each frame of the target video frame image that is detected to meet the repetition detection condition, the single-frame repetition of the target video frame image is determined according to the ratio of the number of second target objects appearing in the target detection area of ​​the target video frame image to the total number of all objects appearing in the target detection area, wherein, for each frame of the target video frame image that is detected to meet the repetition detection condition, the single-frame repetition of the target video frame image is determined according to the ratio of the number of second target objects appearing in the target detection area of ​​the target video frame image to the total number of all objects appearing in the target detection area, including: for each frame of the target video frame image, identifying the second target object appearing in the target detection area of ​​the target video image according to the second feature combination corresponding to the first feature combination, wherein the first feature combination and the second feature combination are determined based on the same frame of the second video frame image of the second video information; determining the single-frame repetition of the target video frame image according to the ratio of the number of the second target objects to the total number of all objects appearing in the target detection area; The video repetition degree of the first video information and the second video information is determined according to the single frame repetition degree of each target video frame image in the one or more target video frame images that are finally determined.

2. The method according to claim 1, wherein: The first feature combination includes at least three first feature objects, and the first feature combination based on the second video information detects frame by frame whether there is a target video frame image that meets the repetition detection condition in the one or more first video frame images, including: Detecting, frame by frame, whether there are at least three first target objects in each of the one or more first video frame images according to the at least three first feature objects, wherein the at least three first target objects match the at least three first feature objects; If so, determining the first video frame image as the target video frame image that meets the repetition detection condition; The method, for each target video frame image that meets the repetition detection condition, determines the single-frame repetition of the target video frame image according to the ratio of the number of second target objects appearing in the target detection area of ​​the target video frame image to the total number of all objects appearing in the target detection area, and before that also includes: For each frame of the target video frame image, a target detection area of ​​the target video frame image is determined according to the at least three first target objects existing in the target video frame image.

3. The method according to claim 2, wherein: The at least three first target objects are matched with the at least three first feature objects, including: The content information of the at least three first target objects matches the content information of the at least three first feature objects, and the position information of the at least three first target objects matches the position information of the at least three first feature objects.

4. The method according to claim 2, wherein: The step of determining the target detection area of ​​the target video frame image according to the at least three first target objects existing in the target video frame image comprises: The at least three first target objects are used as connection endpoints to determine a target detection area of ​​the target video frame image.

5. The method according to claim 1, wherein: The second feature combination includes a second feature object, and for each frame of the target video frame image, identifying a second target object appearing in a target detection area of ​​the target video image according to the second feature combination corresponding to the first feature combination includes: For each frame of the target video frame image, a second target object appearing in the target detection area of ​​the target video frame image is identified according to the second feature object, wherein content information of the second target object matches content information of the second feature object, and position information of the second target object matches position information of the second feature object.

6. The method according to claim 1 or 5, wherein: The first feature combination includes at least three first feature objects, the second feature combination includes a second feature object, and the at least three first feature objects and the second feature object exist in a same frame of second video frame image of the second video information.

7. The method according to claim 1, wherein: The method further comprises: Determine the first feature combination of the second video information.

8. The method according to claim 7, wherein: The second video information includes one or more second video frame images, and determining the first feature combination of the second video information includes: Identify an object appearing in each of the one or more second video frame images; Determine one or more object combinations that appear simultaneously in multiple frames of second video frame images, wherein each of the object combinations includes at least three first feature objects; The first feature combination is determined according to the number of occurrences of each object combination in the one or more object combinations.

9. The method according to claim 8, wherein: The determining of one or more object combinations that appear simultaneously in multiple frames of second video frame images, wherein each of the object combinations includes at least three first feature objects, comprises: Determine one or more object combinations that appear simultaneously in multiple frames of second video frame images, wherein each of the object combinations includes at least three candidate objects; The at least three first feature objects are determined according to position information between the at least three candidate objects.

10. The method according to claim 9, wherein: The determining the at least three first feature objects according to the position information between the at least three candidate objects includes: If the number of the at least three candidate objects is greater than three, and at least one of the at least three candidate objects is not on the same straight line as the other candidate objects, the at least three candidate objects are used as the at least three first feature objects of the object combination.

11. The method according to claim 9, wherein: The determining the at least three first feature objects according to the position information between the at least three candidate objects includes: Three first feature objects are determined from the at least three candidate objects, wherein position information between the three first feature objects meets a target condition.

12. The method according to claim 8, wherein: The determining the first feature combination according to the number of occurrences of each object combination in the one or more object combinations includes: sorting the one or more object combinations in descending order according to the number of occurrences of each object combination in the one or more object combinations; The object combinations ranked in the top N positions are determined as the first feature combinations, where N is a positive integer.

13. The method according to claim 11, wherein: The method further comprises: A second feature combination corresponding to the first feature combination is determined.

14. The method according to claim 13, wherein: The determining a second feature combination corresponding to the first feature combination includes: For each of the first feature combinations, in each frame of the second video frame image in which at least three first feature objects of the first feature combination appear simultaneously, the at least three first feature objects appearing in the second video frame image are used as connection endpoints to determine a feature region in the second video frame image where the at least three first feature objects are located; One or more objects in the feature area are identified, and the one or more objects are determined as second feature objects of the second feature combination.

15. The method according to claim 2, wherein: The method of determining the single-frame repetition degree of the target video frame image according to the ratio of the number of second target objects appearing in the target detection area of ​​the target video frame image to the total number of all objects appearing in the target detection area for each frame of the target video frame image that meets the repetition detection condition comprises: For each frame of the target video frame image, the single-frame repetition degree of the target video frame image is determined according to the ratio of the number of second target objects appearing in the target detection area of ​​the target video frame image to the total number of objects appearing in the target detection area, and in combination with a first ratio and a first weight of the number of first target objects to the total number of objects in the target video frame image, wherein the first weight corresponds to the first ratio.

16. The method according to claim 15, wherein: For each frame of the target video frame image, the single-frame repetition degree of the target video frame image is determined according to the ratio of the number of second target objects appearing in the target detection area of ​​the target video frame image to the total number of objects appearing in the target detection area, and in combination with a first ratio of the number of first target objects to the total number of objects in the target video frame image and a first weight, wherein the first weight corresponds to the first ratio, including: For each frame of the target video frame image, the video frame matching degree of the target video frame image is determined according to the ratio of the number of second target objects appearing in the target detection area of ​​the target video frame image to the total number of objects appearing in the target detection area, and in combination with a first ratio of the number of first target objects to the total number of objects in the target video frame image, a first weight, a second ratio of the area of ​​the target detection area to the total area of ​​the target video frame image, and a second weight, wherein the first weight corresponds to the first ratio, and the second weight corresponds to the second ratio.

17. The method according to claim 1, wherein: The determining the video repetition degree of the first video information and the second video information according to the single frame repetition degree of each target video frame image in the one or more target video frame images finally determined includes: Determine a third ratio of the number of frames of the one or more first video frame images to the total number of frames of the first video frame information; The video matching degree between the first video information and the second video information is determined according to the single-frame repetition degree of each target video frame image in the one or more target video frame images and the third ratio.

18. A device for detecting video repetition, wherein: The equipment includes: Processor; and A memory arranged to store computer executable instructions which, when executed, cause the processor to perform the operations of the method as claimed in any one of claims 1 to 17.

19. A computer-readable medium storing instructions which, when executed, cause a computer to perform the operations of the method of any one of claims 1 to 17.

20. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 17 are implemented.