CN112788363B - Method for identifying infringement video, device for identifying infringement video and electronic equipment - Google Patents
Method for identifying infringement video, device for identifying infringement video and electronic equipment Download PDFInfo
- Publication number
- CN112788363B CN112788363B CN202011631761.9A CN202011631761A CN112788363B CN 112788363 B CN112788363 B CN 112788363B CN 202011631761 A CN202011631761 A CN 202011631761A CN 112788363 B CN112788363 B CN 112788363B
- Authority
- CN
- China
- Prior art keywords
- video
- identified
- target account
- time range
- frames
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs
- H04N21/23418—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/24—Monitoring of processes or resources, e.g. monitoring of server load, available bandwidth, upstream requests
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/254—Management at additional data server, e.g. shopping server, rights management server
- H04N21/2541—Rights Management
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
Abstract
The embodiment of the invention provides a method for identifying infringement videos, a device for identifying infringement videos and electronic equipment. The method comprises the following steps: acquiring a video to be identified; determining whether the video to be identified contains a feature frame corresponding to a target account, wherein the feature frame corresponding to the target account is at least one video frame in a video file under the target account; and under the condition that the video to be identified contains the characteristic frames corresponding to the target account, comparing the video to be identified with the video file under the target account, and identifying whether the video to be identified is an infringement video. According to the embodiment of the invention, under the condition that the video to be identified is not likely to infringe the video file under the target account, the fine granularity comparison process with larger calculation amount is saved, so that the calculation amount of the whole infringe identification process is smaller, and the time consumption is shorter.
Description
Technical Field
The present invention relates to the field of video technologies, and in particular, to a method for identifying an infringement video, an apparatus for identifying an infringement video, and an electronic device.
Background
In the video self-media era, a plurality of people can realize wealth freedom by shooting videos, and more new self-media people are also led to the industry. However, many new people have chosen videos with large direct infringement V in order to get better exposure and attention.
To discover such infringement in time, infringement identification is typically performed on a newly uploaded video to determine whether the video is infringed. The current method for identifying video infringement generally comprises the steps of comparing all video frames in the video to be identified with all copyrighted videos frame by frame, so as to determine whether the video to be identified is an infringement video.
However, although the existing infringement judgment method can accurately identify the infringement video, the frame-by-frame comparison is large in calculated amount, long in time consumption and quite resource-consuming.
Disclosure of Invention
In view of the above problems, embodiments of the present invention provide a method for identifying an infringement video, an apparatus for identifying an infringement video, and an electronic device, so as to solve the problems in the prior art that an infringement identification process has a large calculation amount and consumes a long time.
In a first aspect, an embodiment of the present invention provides a method for identifying infringement videos, the method including:
acquiring a video to be identified;
determining whether the video to be identified contains a feature frame corresponding to a target account, wherein the feature frame corresponding to the target account is at least one video frame in a video file under the target account;
and under the condition that the video to be identified contains the characteristic frames corresponding to the target account, comparing the video to be identified with the video file under the target account, and identifying whether the video to be identified is an infringement video.
Optionally, the determining whether the video to be identified includes the feature frame corresponding to the target account includes:
acquiring a video frame combination in a preset time range in the video to be identified;
and determining whether the video frame combination in the preset time range contains the feature frame corresponding to the target account.
Optionally, the obtaining a video frame combination within a preset time range in the video to be identified includes:
acquiring a plurality of video frames which are associated with image content and are in a preset time range in the video to be identified;
and obtaining the video frame combination according to the plurality of acquired video frames.
Optionally, the obtaining a video frame combination within a preset time range in the video to be identified includes:
acquiring a plurality of key frames in a preset time range in the video to be identified;
and obtaining the video frame combination according to the acquired key frames.
Optionally, before the step of acquiring the video to be identified, the method further comprises:
acquiring a video frame combination in a preset time range in a video file under the target account;
under the condition that the target number is larger than a preset number threshold, determining the target video frames as feature frames corresponding to the target accounts; the target number is the number of video files of the target video frames in the video files under the target account.
Optionally, the preset time range includes at least one of:
a time range of a first preset duration starting at a starting playing time of the video file;
and ending the time range of the second preset duration at the ending playing time of the video file.
In a second aspect, an embodiment of the present invention further provides an apparatus for identifying infringement videos, where the apparatus includes:
the first acquisition module is used for acquiring the video to be identified;
the first identification module is used for determining whether the video to be identified contains a characteristic frame corresponding to a target account, wherein the characteristic frame corresponding to the target account is at least one video frame in a video file under the target account;
and the second identification module is used for comparing the video to be identified with the video file under the target account under the condition that the video to be identified contains the characteristic frame corresponding to the target account, and identifying whether the video to be identified is an infringement video.
Optionally, the first identification module includes:
the acquisition unit is used for acquiring a video frame combination in a preset time range in the video to be identified;
and the identification unit is used for determining whether the video frame combination in the preset time range contains the characteristic frame corresponding to the target account.
Optionally, the acquiring unit is specifically configured to acquire a plurality of video frames that are in a preset time range in the video to be identified and associated with image content; and obtaining the video frame combination according to the plurality of acquired video frames.
Optionally, the acquiring unit is specifically configured to acquire a plurality of key frames in a preset time range in the video to be identified; and obtaining the video frame combination according to the acquired key frames.
Optionally, the apparatus further comprises:
the second acquisition module is used for acquiring video frame combinations in a preset time range in each video file under the target account;
the determining module is used for determining the target video frames as the characteristic frames corresponding to the target accounts under the condition that the target number is larger than a preset number threshold; the target number is the number of video files of the target video frames in the video files under the target account.
In a third aspect, embodiments of the present invention also provide an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps in the method of identifying infringed videos as described above when the computer program is executed.
In a fourth aspect, embodiments of the present invention also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps in a method of identifying infringed videos as described above.
In the embodiment of the invention, the feature frame corresponding to the target account is at least one video frame in the video file under the target account, so that the feature frame is taken as a representative of the video file under the target account. When judging whether the video to be identified has infringement to the video file under the target account, firstly comparing the video to be identified with the characteristic frame, and carrying out a coarse-granularity screening process. If the video to be identified contains the characteristic frame corresponding to the target account, the probability that the video to be identified and the video file under the target account have the same video content is high, the video to be identified is determined to be a suspected infringement video, the suspected infringement video is further compared with the video file under the target account, and whether the video to be identified is the infringement video or not is finally identified through fine comparison. In the process of judging whether the video to be identified is the infringement video or not, firstly, through coarse granularity screening with smaller calculation amount, determining whether the video to be identified has possibility of infringing the video file under the target account, and adopting a fine granularity comparison method with larger calculation amount to compare the video to be identified with the video file under the target account only when the video to be identified has possibility of infringement to the video file under the target account, thereby saving the fine granularity comparison process with larger calculation amount and shortening the time consumption in the whole infringement identification process under the condition that the video to be identified does not have possibility of infringement to the video file under the target account.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments of the present invention will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of steps in a method for identifying infringement videos according to an embodiment of the present invention;
fig. 2 is a block diagram of an apparatus for identifying infringement videos according to an embodiment of the present invention;
fig. 3 is a block diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
In various embodiments of the present invention, it should be understood that the sequence numbers of the following processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
Referring to fig. 1, an embodiment of the present invention provides a method for identifying an infringement video, including:
step 101: and acquiring the video to be identified.
It should be noted that the video to be identified is an object for determining whether it is an infringement video. The video to be identified may be a file in any video format, which may be a video file uploaded by a user or a local video file.
Step 102: and determining whether the video to be identified contains the characteristic frame corresponding to the target account.
It should be noted that, the feature frame corresponding to the target account is at least one video frame in the video file under the target account. Here, the target account may be any one of all accounts that are successfully registered with an online platform that is provided with a large number of video files. Each account corresponds to a video file uploaded by a user to whom the account belongs. For example, a video website is registered with a large number of accounts, a user uploads a video file to the video website through the account, and a feature frame corresponding to the account is a video frame in the video file uploaded by the user to which the account belongs. Because the feature frames corresponding to the target account are video frames in the video file under the target account, the feature frames can be used as representatives of the video file under the target account.
Step 103: and under the condition that the video to be identified contains the characteristic frames corresponding to the target account, comparing the video to be identified with the video files under the target account, and identifying whether the video to be identified is an infringement video.
It should be noted that, when a feature frame is included in a video file as a representation of a video file under a target account, it is indicated that the video file may have the same video content as at least one video file under the target account, and then the video file may be determined to be a suspected infringement video file, that is, the probability that the video file is an infringement video file is higher. Here, in the case that the feature frame is a video frame, the video to be identified includes the feature frame corresponding to the target account, which may be understood that a certain frame in the video to be identified is the same as or similar to the feature frame. Wherein two video frames are identical or similar means that the similarity of the image contents of the two video frames exceeds a preset threshold. In the case that the feature frames are at least two video frames, the video to be identified contains the feature frames corresponding to the target account, which can be understood as at least one video frame in the feature frames corresponding to the target account contained in the video to be identified.
When the video to be identified is compared with the video files under the target account, the user to be identified can be respectively compared with each video file under the target account, and when the video files are compared, the video files can be compared frame by frame, but the method is not limited to the method. It should be noted that after the video to be identified is acquired, it may be first determined whether the account to which the video to be identified belongs is a target account, and if so, there is no infringement, without executing step 102 and step 103. If not, steps 102 and 103 are required.
The identification process is only used for identifying whether the video to be identified has infringement to the video file under the target account. The target account is any account of all accounts successfully registered on the online platform, after the steps are executed, the target account can be switched to be other accounts, the steps 102 and 103 are repeatedly executed, and whether the video to be identified has infringement to video files under other accounts or not is identified.
In the embodiment of the invention, the feature frame corresponding to the target account is at least one video frame in the video file under the target account, so that the feature frame is taken as a representative of the video file under the target account. When judging whether the video to be identified has infringement to the video file under the target account, firstly comparing the video to be identified with the characteristic frame, and carrying out a coarse-granularity screening process. If the video to be identified contains the characteristic frame corresponding to the target account, the probability that the video to be identified and the video file under the target account have the same video content is high, the video to be identified is determined to be a suspected infringement video, the suspected infringement video is further compared with the video file under the target account, and whether the video to be identified is the infringement video or not is finally identified through fine comparison. In the process of judging whether the video to be identified is the infringement video or not, firstly, through coarse granularity screening with smaller calculation amount, determining whether the video to be identified has possibility of infringing the video file under the target account, and adopting a fine granularity comparison method with larger calculation amount to compare the video to be identified with the video file under the target account only when the video to be identified has possibility of infringement to the video file under the target account, thereby saving the fine granularity comparison process with larger calculation amount and shortening the time consumption in the whole infringement identification process under the condition that the video to be identified does not have possibility of infringement to the video file under the target account.
Based on the above embodiment of the present invention, in the embodiment of the present invention, determining whether the video to be identified includes the feature frame corresponding to the target account includes:
and acquiring a video frame combination in a preset time range in the video to be identified.
In this step, the preset time range is a time range of a preset duration in the video to be identified, and a start time of the preset time range can be set arbitrarily according to requirements. Here, the number of video frames in the video frame combination is at least two. When the video frames in the video frame combination are acquired, the video frames can be acquired in any mode within a preset time range of the video to be identified. Preferably, the video frame combination can be obtained according to the video content of the video to be identified, so that the video frame combination can accurately represent the video content of the video to be identified.
And determining whether the video frame combination in the preset time range contains the characteristic frame corresponding to the target account.
In this step, when the feature frame is a video frame, the video frame combination includes the feature frame corresponding to the target account, which can be understood that a certain frame in the video frame combination is the same as or similar to the feature frame. In the case that the feature frames are at least two video frames, the video frame combination includes the feature frames corresponding to the target account, which can be understood as including at least one video frame in the feature frames corresponding to the target account in the video frame combination.
In the embodiment of the invention, whether the video to be identified contains the characteristic frame is determined according to whether the video frame combination of the video frame to be identified contains the characteristic frame or not, so that the frame-by-frame comparison of the video to be identified and the characteristic frame can be avoided, the calculated amount is reduced, and the calculation time is shortened.
Based on the above embodiment of the present invention, in the embodiment of the present invention, obtaining a video frame combination within a preset time range in a video to be identified includes:
and acquiring a plurality of video frames which are associated with the image content and are in a preset time range in the video to be identified.
In this step, the image content association may be understood as that the image content is continuous, for example, the image content in the same scene is the image content association, but is not limited thereto.
And obtaining a video frame combination according to the acquired multiple video frames.
In the embodiment of the invention, the plurality of video frames associated with the image content are extracted as the video frame combination, so that the video frame combination can more accurately represent the video content of the video to be identified, and the accuracy of infringement identification is improved.
Based on the above embodiment of the present invention, in the embodiment of the present invention, obtaining a video frame combination within a preset time range in a video to be identified includes:
and acquiring a plurality of key frames in a preset time range in the video to be identified.
In this step, the key frame refers to the frame in which the key action in the movement or change of the character or object is located.
And obtaining a video frame combination according to the acquired multiple key frames.
In the embodiment of the invention, the key frames in the video to be identified are extracted as the video frame combination, so that the video frame combination can more accurately represent the video content of the video to be identified, and the accuracy of infringement identification is improved.
Based on the above embodiment of the present invention, in the embodiment of the present invention, obtaining a video frame combination within a preset time range in a video to be identified includes:
and acquiring a plurality of video frames in a preset time range in the video to be identified according to a preset time interval.
In this step, the preset time interval is determined by a preset time range, and it is required to ensure that a plurality of video frames can be acquired within the preset time range. For example, the preset time range is 1 st second to 20 th second, and the preset time interval may be 1 second, 2 seconds … seconds, or the like. I.e. one video frame is acquired every 1 second, one video frame every 2 seconds, one video frame every 10 seconds.
And obtaining a video frame combination according to all the obtained video frames.
In the embodiment of the invention, the video frames in the video to be identified are extracted as the video frame combination according to the preset time interval, so that the video frame combination is conveniently obtained.
Based on the above embodiment of the present invention, in the embodiment of the present invention, obtaining a video frame combination within a preset time range in a video to be identified includes:
and acquiring a video frame of a preset position in a preset time range in the video to be identified.
In this step, the preset position may be a preset position. The preset position may also be a position corresponding to the target account, that is, a position of a video frame in the video file under the extracted target account when determining the feature frame corresponding to the target account.
And obtaining a video frame combination according to all the obtained video frames.
In the embodiment of the invention, the video frames in the video to be identified are extracted as the video frame combination according to the preset position, so that the video frame combination is conveniently obtained.
On the basis of the above embodiment of the present invention, before the step of acquiring the video to be identified, the method further includes:
and acquiring a video frame combination in a preset time range in the video file under the target account.
In this step, the starting time of the preset time range may be set arbitrarily according to the requirement. Here, the number of video frames in the video frame combination is at least two. When the video frames in the video frame combination are acquired, the acquisition can be performed in any mode within a preset time range of the video file. Preferably, the video frame combination may be obtained according to the video content of the video file, so that the video frame combination may accurately represent the video content of the video file. Here, a corresponding video frame combination is acquired for each video file.
And under the condition that the target number is larger than a preset number threshold, determining the target video frames as feature frames corresponding to the target accounts.
In this step, the target number is the number of video files in which the target video frame appears in the video files under the target account. That is, the target video frame is a common video frame in the target number video file. Wherein, different video frames with the same or similar image content can be used as the same video frame. The target number can be set according to the requirement, and of course, the target number can also be set according to the number of all video files under the target account, namely, the ratio of the target number to the number of all video files under the target account is a preset ratio. For example, the preset ratio is one half, and when the number of all video files under the target account is 100, the target number is 50. Preferably, its corresponding feature frame may be updated for the target user periodically.
In the embodiment of the invention, the public video frames in the video files under the target account are used as the feature frames corresponding to the target account, so that the feature frames can more accurately represent the video content of the video files under the target account, and the accuracy of infringement identification is improved.
On the basis of the above embodiment of the present invention, in the embodiment of the present invention, the preset time range includes at least one of the following:
a time range of a first preset duration starting at a starting playing time of the video file;
and ending the time range of the second preset duration at the ending playing time of the video file.
It should be noted that the head and tail portions of a video file are typically unique to the user's video content and are easily used directly by others. Here, the time range of the first preset duration, which starts at the start play time of the video file, may be understood as the title portion of the video file. The first preset duration may be determined according to a duration of a header in a plurality of video files, for example, the duration of the header in the plurality of video files is generally in a range of 20 seconds to 30 seconds, and then the first preset duration is any duration in a range of 20 seconds to 30 seconds. Similarly, the time range of the second preset duration ending at the ending playing time of the video file may be understood as the end portion of the video file, where the second preset duration may be determined according to the end durations in a large number of video files, for example, the end durations in a large number of video files are generally in the range of 20 seconds to 30 seconds, and then the second preset duration is any duration in the range of 20 seconds to 30 seconds. Of course, some users also set their own unique video content in the middle part of the video file, where the preset time range may be the time range of the middle part of the video file.
In the embodiment of the invention, the video frames are extracted from the head and the tail of the video file by utilizing the characteristics of the head and the tail, so that the extracted video frames can embody the unique characteristics of the video file and the accuracy of infringement identification is improved.
Optionally, in the case that the video to be identified is determined to be an infringement video, an infringement tag is added to the video to be identified. The infringement marks herein may be letters, numbers or special symbols, and the infringement marks of the video are used to characterize the video as infringement video. Preferably, the method further comprises: determining the proportion of infringed videos in video files under accounts to which videos to be identified belong; and adding an infringement user mark to the account to which the video to be identified belongs under the condition that the proportion exceeds a preset threshold value. It should be noted that the infringing user mark may be a number, a letter or a special symbol. Preferably, for users with infringement user tags, no recommendation is made to their account or video under the account.
Having described the method for identifying infringement videos provided by the embodiment of the present invention, the apparatus for identifying infringement videos provided by the embodiment of the present invention will be described with reference to the accompanying drawings.
Referring to fig. 2, the embodiment of the invention further provides an apparatus for identifying infringement videos, where the apparatus includes:
a first obtaining module 21, configured to obtain a video to be identified;
the first identifying module 22 is configured to determine whether the video to be identified includes a feature frame corresponding to the target account, where the feature frame corresponding to the target account is at least one video frame in the video file under the target account;
the second identifying module 23 is configured to, when the video to be identified includes a feature frame corresponding to the target account, compare the video to be identified with a video file under the target account, and identify whether the video to be identified is an infringement video.
Optionally, the first identification module 22 includes:
the acquisition unit is used for acquiring video frame combinations in a preset time range in the video to be identified;
and the identification unit is used for determining whether the video frame combination in the preset time range contains the characteristic frame corresponding to the target account.
Optionally, the acquiring unit is specifically configured to acquire a plurality of video frames in a preset time range in the video to be identified, where the video frames are associated with image content; and obtaining a video frame combination according to the acquired multiple video frames.
Optionally, the acquiring unit is specifically configured to acquire a plurality of key frames in a preset time range in the video to be identified; and obtaining a video frame combination according to the acquired multiple key frames.
Optionally, the apparatus further comprises:
the second acquisition module is used for acquiring video frame combinations in a preset time range in each video file under the target account;
the determining module is used for determining the target video frames as the feature frames corresponding to the target accounts under the condition that the target number is larger than a preset number threshold; the target number is the number of video files with target video frames in the video files under the target account.
Optionally, the preset time range includes at least one of:
a time range of a first preset duration starting at a starting playing time of the video file;
and ending the time range of the second preset duration at the ending playing time of the video file.
The device for identifying infringement videos provided by the embodiment of the present invention can implement each process implemented by the method for identifying infringement videos in the method embodiment of fig. 1, and in order to avoid repetition, the description is omitted here.
In the embodiment of the invention, the feature frame corresponding to the target account is at least one video frame in the video file under the target account, so that the feature frame is taken as a representative of the video file under the target account. When judging whether the video to be identified has infringement to the video file under the target account, firstly comparing the video to be identified with the characteristic frame, and carrying out a coarse-granularity screening process. If the video to be identified contains the characteristic frame corresponding to the target account, the probability that the video to be identified and the video file under the target account have the same video content is high, the video to be identified is determined to be a suspected infringement video, the suspected infringement video is further compared with the video file under the target account, and whether the video to be identified is the infringement video or not is finally identified through fine comparison. In the process of judging whether the video to be identified is the infringement video or not, firstly, through coarse granularity screening with smaller calculation amount, determining whether the video to be identified has possibility of infringing the video file under the target account, and adopting a fine granularity comparison method with larger calculation amount to compare the video to be identified with the video file under the target account only when the video to be identified has possibility of infringement to the video file under the target account, thereby saving the fine granularity comparison process with larger calculation amount and shortening the time consumption in the whole infringement identification process under the condition that the video to be identified does not have possibility of infringement to the video file under the target account.
In another aspect, an embodiment of the present invention further provides an electronic device, including a memory, a processor, a bus, and a computer program stored in the memory and capable of running on the processor, where the processor implements the steps in the method for identifying infringed videos described above when the processor executes the program.
For example, fig. 3 shows a schematic physical structure of an electronic device.
As shown in fig. 3, the electronic device may include: processor 310, communication interface (Communications Interface) 320, memory 330 and communication bus 340, wherein processor 310, communication interface 320, memory 330 accomplish communication with each other through communication bus 340. The processor 310 may call logic instructions in the memory 330 to perform the following method:
acquiring a video to be identified;
determining whether the video to be identified contains a feature frame corresponding to a target account, wherein the feature frame corresponding to the target account is at least one video frame in a video file under the target account;
and under the condition that the video to be identified contains the characteristic frames corresponding to the target account, comparing the video to be identified with the video file under the target account, and identifying whether the video to be identified is an infringement video.
Further, the logic instructions in the memory 330 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In still another aspect, an embodiment of the present invention further provides a computer readable storage medium having stored thereon a computer program, which when executed by a processor is implemented to perform the method for identifying infringed videos provided in the above embodiments, for example, including:
acquiring a video to be identified;
determining whether the video to be identified contains a feature frame corresponding to a target account, wherein the feature frame corresponding to the target account is at least one video frame in a video file under the target account;
and under the condition that the video to be identified contains the characteristic frames corresponding to the target account, comparing the video to be identified with the video file under the target account, and identifying whether the video to be identified is an infringement video.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. A method of identifying infringing videos, the method comprising:
acquiring a video to be identified;
determining whether the video to be identified contains a characteristic frame corresponding to a target account through coarse granularity screening, wherein the characteristic frame corresponding to the target account is at least one video frame in a video file under the target account;
under the condition that the video to be identified contains the characteristic frames corresponding to the target account, comparing the video to be identified with each video file under the target account by adopting a fine granularity comparison method, and identifying whether the video to be identified is an infringement video or not, wherein the characteristic frames corresponding to the target account are representative of all video files under the target account;
the determining whether the video to be identified contains the feature frame corresponding to the target account through coarse granularity screening comprises the following steps:
acquiring a video frame combination in a preset time range in the video to be identified;
and determining whether the video frame combination in the preset time range contains the feature frame corresponding to the target account.
2. The method according to claim 1, wherein the obtaining the video frame combination within the preset time range in the video to be identified includes:
acquiring a plurality of video frames which are associated with image content and are in a preset time range in the video to be identified;
and obtaining the video frame combination according to the plurality of acquired video frames.
3. The method according to claim 1, wherein the obtaining the video frame combination within the preset time range in the video to be identified includes:
acquiring a plurality of key frames in a preset time range in the video to be identified;
and obtaining the video frame combination according to the acquired key frames.
4. The method of claim 1, wherein prior to the step of capturing the video to be identified, the method further comprises:
acquiring a video frame combination in a preset time range in a video file under the target account;
under the condition that the target number is larger than a preset number threshold, determining the target video frames as feature frames corresponding to the target accounts; the target number is the number of video files of the target video frames in the video files under the target account.
5. The method according to claim 1 or 4, wherein the preset time range comprises at least one of:
a time range of a first preset duration starting at a starting playing time of the video file;
and ending the time range of the second preset duration at the ending playing time of the video file.
6. An apparatus for identifying infringing videos, the apparatus comprising:
the first acquisition module is used for acquiring the video to be identified;
the first identification module is used for determining whether the video to be identified contains a characteristic frame corresponding to a target account through coarse granularity screening, wherein the characteristic frame corresponding to the target account is at least one video frame in a video file under the target account;
the second identification module is used for comparing the video to be identified with each video file under the target account by adopting a fine granularity comparison method under the condition that the video to be identified contains the characteristic frames corresponding to the target account, and identifying whether the video to be identified is an infringement video or not, wherein the characteristic frames corresponding to the target account are representative of all video files under the target account;
the first identification module includes:
the acquisition unit is used for acquiring a video frame combination in a preset time range in the video to be identified;
and the identification unit is used for determining whether the video frame combination in the preset time range contains the characteristic frame corresponding to the target account.
7. An electronic device comprising a processor, a memory and a computer program stored on the memory and executable on the processor, wherein the computer program when executed by the processor implements the steps of the method of identifying infringed videos of any of claims 1-5.
8. A computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, implements the steps of the method of identifying infringing videos according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011631761.9A CN112788363B (en) | 2020-12-30 | 2020-12-30 | Method for identifying infringement video, device for identifying infringement video and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011631761.9A CN112788363B (en) | 2020-12-30 | 2020-12-30 | Method for identifying infringement video, device for identifying infringement video and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112788363A CN112788363A (en) | 2021-05-11 |
| CN112788363B true CN112788363B (en) | 2023-04-28 |
Family
ID=75754762
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011631761.9A Active CN112788363B (en) | 2020-12-30 | 2020-12-30 | Method for identifying infringement video, device for identifying infringement video and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112788363B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109299734A (en) * | 2018-09-13 | 2019-02-01 | 北京字节跳动网络技术有限公司 | Recognition methods, device and the computer readable storage medium of infringement picture |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2811416A1 (en) * | 2013-06-06 | 2014-12-10 | Vestel Elektronik Sanayi ve Ticaret A.S. | An identification method |
| CN104143055B (en) * | 2014-08-16 | 2017-02-15 | 合一网络技术(北京)有限公司 | Pirated video monitoring method and system |
| CN105681899B (en) * | 2015-12-31 | 2019-05-10 | 北京奇艺世纪科技有限公司 | A kind of detection method and device of similar video and pirate video |
| CN108881947B (en) * | 2017-05-15 | 2021-08-17 | 阿里巴巴集团控股有限公司 | Method and device for detecting infringement of live stream |
| CN109960746A (en) * | 2019-03-14 | 2019-07-02 | 佛山市摄时度文化传播有限公司 | Video infringement method for early warning and device |
| CN110324729B (en) * | 2019-07-18 | 2021-08-27 | 北京奇艺世纪科技有限公司 | Method, device, electronic equipment and medium for identifying infringement video link |
| CN111708988B (en) * | 2020-05-15 | 2023-05-30 | 北京奇艺世纪科技有限公司 | Infringement video identification method and device, electronic equipment and storage medium |
-
2020
- 2020-12-30 CN CN202011631761.9A patent/CN112788363B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109299734A (en) * | 2018-09-13 | 2019-02-01 | 北京字节跳动网络技术有限公司 | Recognition methods, device and the computer readable storage medium of infringement picture |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112788363A (en) | 2021-05-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107563500B (en) | Video recommendation method and system based on user head portrait | |
| CN110532369B (en) | Question and answer pair generation method and device and server | |
| CN108388591B (en) | Book recommendation method, device and system and readable storage medium | |
| CN105159913B (en) | Method and device for determining file to be cleaned | |
| US20170293759A1 (en) | Method, apparatus and computer device for scanning information to be scanned | |
| CN108066990B (en) | Method, device and server for selecting user from candidate user list | |
| CN112788363B (en) | Method for identifying infringement video, device for identifying infringement video and electronic equipment | |
| CN113032524A (en) | Trademark infringement identification method, terminal device and storage medium | |
| US9141818B2 (en) | Information providing apparatus and non-transitory computer readable medium having stored information for each marker image identification information | |
| EP3026671A1 (en) | Method and apparatus for detecting emotional key frame | |
| CN115269919A (en) | Method and device for determining quality of short video, electronic equipment and storage medium | |
| CN114530073B (en) | Training method and device based on virtual reality | |
| CN106202360A (en) | Examination question searching method and device | |
| CN114625909A (en) | Image text selection method and device, electronic equipment and storage medium | |
| CN111708988B (en) | Infringement video identification method and device, electronic equipment and storage medium | |
| CN110807179B (en) | User identification method, device, server and storage medium | |
| CN114220057A (en) | Video trailer identification method and device, electronic equipment and readable storage medium | |
| US11938407B2 (en) | Player identification system and method | |
| CN110458171B (en) | License plate recognition method and related device | |
| CN112149552A (en) | Intelligent monitoring method and device | |
| CN112347990A (en) | Multimode-based intelligent manuscript examining system and method | |
| KR100734845B1 (en) | Method for discriminating malicious video using image quality classification and apparatus thereof | |
| CN111191522A (en) | Image scene information storage method and system | |
| CN113365100B (en) | Video processing method and device | |
| CN110737802B (en) | Pirated video detection method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |