CN106412690B - Video playing determination method and device - Google Patents
Video playing determination method and device Download PDFInfo
- Publication number
- CN106412690B CN106412690B CN201510438518.8A CN201510438518A CN106412690B CN 106412690 B CN106412690 B CN 106412690B CN 201510438518 A CN201510438518 A CN 201510438518A CN 106412690 B CN106412690 B CN 106412690B
- Authority
- CN
- China
- Prior art keywords
- target
- vector
- picture
- video
- detected
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 22
- 239000013598 vector Substances 0.000 claims abstract description 347
- 238000013139 quantization Methods 0.000 claims description 22
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 13
- 238000001514 detection method Methods 0.000 description 11
- 238000004590 computer program Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 4
- 230000003252 repetitive effect Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
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]
- H04N21/40—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 or rendering scenes according to encoded video stream scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream 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
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/454—Content or additional data filtering, e.g. blocking advertisements
- H04N21/4545—Input to filtering algorithms, e.g. filtering a region of the image
- H04N21/45457—Input to filtering algorithms, e.g. filtering a region of the image applied to a time segment
-
- 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
- H04N21/47—End-user applications
- H04N21/472—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content
- H04N21/47202—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content for requesting content on demand, e.g. video on demand
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method and a device for determining video playing. The method comprises the following steps: extracting a target template picture of a target video in a template video library; sequentially acquiring target pictures to be detected corresponding to the target template pictures from the real-time video stream according to the time sequence; calculating a vector distance between a first target characteristic vector of the target template picture and a second target characteristic vector of the target picture to be detected; when the vector distance is smaller than or equal to the preset vector distance, judging whether the vector distances between the first target feature vectors of other target template pictures in the target video and the second target feature vectors of corresponding other target pictures to be detected are smaller than the preset vector distance; and determining whether the target video starts to be played in the real-time video stream according to the judgment result. By the technical scheme, whether the target video is played in the real-time video stream can be accurately determined, so that the video played in the real-time video stream can be accurately predicted according to the target video.
Description
Technical Field
The present invention relates to the field of video processing technologies, and in particular, to a method and an apparatus for determining video playing.
Background
Currently, in an Electronic Program Guide (EPG) processing system, real-time prediction of a Program that is broadcast recently is required. And the predicted program is actually subjected to video repeatability detection. However, the task amount of manually performing the repetitive detection is very large, the efficiency is low, and the accuracy and precision of the repetitive detection are low, so that the real-time program prediction cannot be accurately performed, which brings great inconvenience to users.
Disclosure of Invention
The invention provides a method and a device for determining video playing, which are used for predicting programs through the repeatability detection of videos such as programs and the like.
The invention provides a method for determining video playing, which comprises the following steps: extracting the starting playing time of a target video in a template video library and a target template picture corresponding to the starting playing time;
sequentially acquiring a target picture to be detected with the most advanced time in a target playing time period corresponding to the starting playing time of the target template picture from the real-time video stream according to the time sequence;
calculating a vector distance between a first target characteristic vector of the target template picture and a second target characteristic vector of the target picture to be detected;
when the vector distance is smaller than or equal to a preset vector distance, sequentially judging whether the vector distances between first target feature vectors of other target template pictures in the target video and second target feature vectors of corresponding other target pictures to be detected in a preset time period are smaller than the preset vector distance according to the time sequence, wherein the preset time period comprises the play starting time;
and determining whether the target video in the template video library is started to be played in the real-time video stream according to a judgment result.
In one embodiment, the determining whether the target video in the template video library has started to be played in the real-time video stream according to the determination result includes:
when the vector distance is smaller than or equal to the preset vector distance, when the vector distances between the first target feature vectors of other target template pictures in the target video and the second target feature vectors of corresponding other target pictures to be detected are smaller than the preset vector distance, determining that the target video starts to be played in the real-time video stream, and sending a video playing prompt signal; otherwise, determining that the target video does not start to be played in the real-time video stream.
In one embodiment, the method further comprises:
when the vector distance is larger than the preset vector distance, acquiring a picture to be detected with the most forward time in an adjacent playing time period adjacent to the target playing time period from a real-time video stream;
judging whether the vector distance between the first target characteristic vector of the target template picture and the second target characteristic vector of the picture to be detected is smaller than or equal to the preset vector distance;
when the vector distance between the first target characteristic vector of the target template picture and the second target characteristic vector of the picture to be detected is smaller than or equal to the preset vector distance, whether the target video in the template video library is started to be played in the real-time video stream is determined continuously according to the judgment result;
and when the vector distance between the first target characteristic vector of the target template picture and the second target characteristic vector of the picture to be detected is greater than the preset vector distance, directly determining that the target video does not start to be played in the real-time video stream.
In one embodiment, before calculating the vector distance, vector quantization is respectively performed on a first target feature vector of the target template picture and a second target feature vector of the target picture to be detected; and
the calculating a vector distance between a first target feature vector of the target template picture and a second target feature vector of the target picture to be detected includes:
and calculating the vector distance between the first target characteristic vector of the target template picture and the second target characteristic vector of the target picture to be detected according to the first target characteristic vector of the target template picture after vector quantization and the second target characteristic vector of the target picture to be detected after vector quantization.
In one embodiment, the calculating a first target feature vector of the target template picture includes:
acquiring an integral histogram of the target template picture;
dividing the target template picture into M image blocks;
acquiring a local histogram of each of the M image blocks;
and determining a first target feature vector of the target template picture according to the overall histogram and the M local histograms.
The invention also provides a device for determining video playing, which comprises: the extraction module is used for extracting the starting playing time of the target video in the template video library and a target template picture corresponding to the starting playing time;
the first acquisition module is used for sequentially acquiring a target picture to be detected with the most advanced time in a target playing time period corresponding to the starting playing time of the target template picture from the real-time video stream according to the time sequence;
the calculation module is used for calculating the vector distance between a first target characteristic vector of the target template picture and a second target characteristic vector of the target picture to be detected;
the first judging module is used for sequentially judging whether the vector distances between the first target feature vectors of other target template pictures in the target video and the second target feature vectors of corresponding other target pictures to be detected in a preset time period are smaller than the preset vector distance according to the time sequence when the vector distance is smaller than or equal to the preset vector distance, wherein the preset time period comprises the playing starting time;
and the determining module is used for determining whether the target video in the template video library starts to be played in the real-time video stream according to the judgment result.
In one embodiment, the determining module comprises:
the first determining sub-module is used for determining that the target video starts to be played in the real-time video stream and sending a video playing prompt signal when the vector distance is smaller than or equal to the preset vector distance and the vector distances between the first target feature vectors of other target template pictures in the target video and the second target feature vectors of corresponding other target pictures to be detected are smaller than the preset vector distance; otherwise, determining that the target video does not start to be played in the real-time video stream.
In one embodiment, the apparatus further comprises:
the second acquisition module is used for acquiring a picture to be detected which is most advanced in time in an adjacent playing time period adjacent to the target playing time period from a real-time video stream when the vector distance is greater than the preset vector distance;
the second judgment module is used for judging whether the vector distance between the first target characteristic vector of the target template picture and the second target characteristic vector of the picture to be detected is smaller than or equal to the preset vector distance or not;
the determining module further comprises:
a second determining submodule, configured to, when a vector distance between a first target feature vector of the target template picture and a second target feature vector of the picture to be detected is smaller than or equal to the preset vector distance, continue to determine, according to the determination result, whether the target video in the template video library has started to be played in the real-time video stream;
and the third determining submodule is used for directly determining that the target video does not start to be played in the real-time video stream when the vector distance between the first target characteristic vector of the target template picture and the second target characteristic vector of the picture to be detected is greater than the preset vector distance.
In one embodiment, the apparatus further comprises:
the vector quantization module is used for respectively carrying out vector quantization on a first target characteristic vector of the target template picture and a second target characteristic vector of the target picture to be detected before calculating the vector distance; and
the calculation module comprises:
and the calculating submodule is used for calculating the vector distance between the first target characteristic vector of the target template picture and the second target characteristic vector of the target picture to be detected according to the first target characteristic vector of the target template picture after vector quantization and the second target characteristic vector of the target picture to be detected after vector quantization.
In one embodiment, the calculation module further comprises:
the first obtaining sub-module is used for obtaining an overall histogram of the target template picture;
the dividing submodule is used for dividing the target template picture into M image blocks;
the second obtaining sub-module is used for obtaining a local histogram of each image block in the M image blocks;
and the fourth determining submodule is used for determining a first target feature vector of the target template picture according to the overall histogram and the M local histograms.
The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:
by calculating the vector distance between the first target feature vector of each target template picture of the target video in the template video library and the second target feature vector of the target to-be-detected picture in the corresponding real-time video stream, whether the target to-be-detected picture in the real-time video stream is matched with the corresponding target template picture in the target video can be accurately determined according to the vector distance, and whether the target video is played in the real-time video stream is further accurately determined, so that the video played in the real-time video stream can be accurately predicted according to the target video.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
fig. 1 is a flow chart illustrating a method of determining video playback according to an exemplary embodiment.
Fig. 2 is a flow chart illustrating another method of determining video playback according to an example embodiment.
Fig. 3 is a flow chart illustrating yet another method of determining video playback in accordance with an exemplary embodiment.
Fig. 4 is a block diagram illustrating a video play determination apparatus according to an example embodiment.
Fig. 5 is a block diagram illustrating another apparatus for determining video playback according to an example embodiment.
Fig. 6 is a block diagram illustrating yet another apparatus for determining video playback according to an example embodiment.
Fig. 7 is a block diagram illustrating still another apparatus for determining video playback according to an example embodiment.
Fig. 8 is a block diagram illustrating still another apparatus for determining video playback according to an example embodiment.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
In the related art, in an Electronic Program Guide (EPG) processing system, a Program to be recently broadcast needs to be predicted in real time. And the predicted program is actually subjected to video repeatability detection. However, the task amount of manually performing the repetitive detection is very large, the efficiency is low, and the accuracy and precision of the repetitive detection are low, so that the real-time program prediction cannot be accurately performed, which brings great inconvenience to users.
In order to solve the above technical problem, an embodiment of the present disclosure provides a method for determining video playing, where the method is applied to a determination program, system or device for video playing, as shown in fig. 1, in step S101, a start playing time of a target video in a template video library and a target template picture corresponding to the start playing time are extracted; the template video library may store different programs (perhaps different sets and different periods) which are broadcast at the same time and occur at a near time (e.g., a certain almost fixed time of yesterday and the last day) derived from the EPG system, and the target video is a certain program or a program header of a certain program which is broadcast at the same time in the template video library, so as to detect whether the program is broadcast again at the same time in the real-time video stream, thereby accurately realizing video repeatability detection and program prediction. Of course, the invention is limited to the detection of identical video content when performing video repeatability detection (i.e. matching detection), and does not involve the deformation of pictures, the change of colors, and the like. And the target template picture is a first frame target shot in the target video.
Step S102, sequentially acquiring a target picture to be detected with the most advanced time in a target playing time period corresponding to the starting playing time of the target template picture from the real-time video stream according to the time sequence; after the first frame target shot in the target video is acquired, the first frame to-be-measured shot corresponding to the target template picture can be acquired in the real-time video stream in time sequence, and the broadcast of the program usually has time errors, so that the first frame to-be-measured picture is the target to-be-measured picture with the most advanced time in the target broadcast time period [ T1, T2] corresponding to the broadcast starting time T1, wherein T1< T1< T2.
Step S103, calculating a vector distance between a first target characteristic vector of the target template picture and a second target characteristic vector of the target picture to be detected; the first target feature vector is used for uniquely identifying the target template picture and is a fingerprint, namely a video fingerprint, of the target template picture; the second target feature vector is used for uniquely identifying the target picture to be detected, and is a finger print of the target picture to be detected, namely a video fingerprint. The smaller the vector distance is, the higher the matching degree of the first target feature vector of the target template picture and the second target feature vector of the target picture to be detected is, and the higher the similarity between the target template picture and the target picture to be detected is.
Step S104, when the vector distance is smaller than or equal to a preset vector distance, sequentially judging whether the vector distances between first target feature vectors of other target template pictures in the target video and second target feature vectors of corresponding other target pictures to be detected in a preset time period are smaller than the preset vector distance according to the time sequence, wherein the preset time period comprises the playing starting time; when the vector distance between the first target feature vector of the first frame of target shot (i.e., the target template picture) and the second target feature vector of the first frame of shot to be tested (i.e., the target picture to be tested) is smaller than the preset vector distance, it is described that the first frame of target shot is matched with the first frame of shot to be tested, whether the vector distances between the first target feature vectors of other template pictures and the second target feature vectors of corresponding other target pictures to be tested in a preset time period are all smaller than the preset vector distance may be sequentially calculated according to a time sequence, and if both are smaller than the preset vector distance, it is described that the other template pictures in the preset time period are matched with the other target pictures to be tested, where the preset time period is a time period corresponding to a playing time period of the target video.
Step S105, determining whether the target video in the template video library is started to be played in the real-time video stream according to the judgment result. According to the judgment result, the fact that the real-time video stream in the preset time period starts to play the target video can be determined, and therefore program prediction is accurately carried out.
Of course, if the target video is a program broadcast in the recent EPG in the same time slot or a program header of the program and the real-time video stream is a program broadcast in the EPG today, then by the above scheme, the present invention completes the real-time prediction of the EPG program, and meanwhile, when it is determined that the vector distance between the second target feature vector of the image or images to be detected of some target acquired in time sequence and the first target feature vector of the corresponding target template image acquired from the target video is greater than the preset vector distance, i.e. not completely matched one by one, it indicates that the target video is not broadcast and other new programs are broadcast, and the template video library may be updated by using the other new programs to complete the correction of the EPG, for example: the new program is used for replacing the target program in the template video library and the target program in the historical EPG, and various information such as program types, names, playing time, broadcasting stations and the like is marked on the new program, so that the template video library is updated, the program in the EPG system is corrected, and the program in the EPG system is always the latest program.
In one embodiment, the step S105 may be performed as:
when the vector distance is smaller than or equal to the preset vector distance, when the vector distances between the first target feature vectors of other target template pictures in the target video and the second target feature vectors of corresponding other target pictures to be detected are smaller than the preset vector distance, determining that the target video starts to be played in the real-time video stream, and sending a video playing prompt signal; otherwise, determining that the target video does not start to be played in the real-time video stream.
When the vector distance between a first target feature vector of a first frame of target shot (namely, the target template picture) and a second target feature vector of a first frame of shot to be detected (namely, the target picture to be detected) in a preset time period is smaller than the preset vector distance, if the vector distance between a first target feature vector of other template pictures in the preset time period and a second target feature vector of corresponding other target pictures to be detected is also smaller than the preset vector distance, all the target template pictures and all the target pictures to be detected in the preset time period are matched, and then the target video can be determined to be played by a video stream within the time period, so that accurate program prediction is realized, and at the moment, a user can be prompted so that the user can watch the program in time; of course, when it is determined that the vector distance between the second target feature vector of the other target to-be-detected picture and the first target feature vector of the other target template picture is greater than the preset vector distance within the preset time period, it may be determined that the target video is not started to be played by the real-time video stream within the time period, which also means that the video played in the time period in the real-time video stream is a new video rather than a target video, and the template video library may be updated by using the new video without prompting the user that the program corresponding to the target video is played at the same time.
As shown in fig. 2, in one embodiment, the method may further comprise:
step S201, when the vector distance is larger than the preset vector distance, acquiring a picture to be tested which is most advanced in time in an adjacent playing time period adjacent to the target playing time period from a real-time video stream; when the vector distance between the first target feature vector of the first frame of target shot (i.e. the target template picture) and the second target feature vector of the first frame of shot to be tested (i.e. the target picture to be tested) is greater than the preset vector distance, it is indicated that the first frame of target shots is not matched with the first frame of shots to be tested, i.e. the first frame of shots to be tested is not the first shot corresponding to the first frame of target shots, possibly due to the play-out time error of the target video, the first shot corresponding to the target shot of the first frame, i.e. the picture to be tested which is the most advanced in time, can be searched again in the adjacent play time adjacent to the target play time period T1, T2, so as to further accurately judge whether the target video is played at the same time, of course, the adjacent playing time period is the time period closest to the target playing time period, such as: t-1, T1 or T2, T3, so that the number of searching times and the number of matching times can be reduced.
Step S202, judging whether the vector distance between the first target characteristic vector of the target template picture and the second target characteristic vector of the picture to be detected is smaller than or equal to the preset vector distance; when the vector distance between the first target feature vector of the first frame target lens and the second target feature vector of the newly determined first frame lens to be detected (namely, the picture to be detected) is smaller than or equal to the preset vector distance, it is described that the first frame target lens is matched with the first frame lens to be detected, whether the vector distances between the first target feature vectors of other template pictures in a preset time period and the second target feature vectors of corresponding other target pictures to be detected are smaller than the preset vector distance or not can be sequentially calculated according to the time sequence, and if the vector distances are smaller than the preset vector distance, it is described that the other template pictures in the preset time period are matched with the other target pictures to be detected.
Step S203, when the vector distance between the first target feature vector of the target template picture and the second target feature vector of the picture to be detected is smaller than or equal to the preset vector distance, whether the target video in the template video library is started to be played in the real-time video stream is determined continuously according to the judgment result;
step S204, when the vector distance between the first target characteristic vector of the target template picture and the second target characteristic vector of the picture to be detected is larger than the preset vector distance, directly determining that the target video does not start to be played in the real-time video stream.
When the vector distance between the first target feature vector of the first frame of target shot and the newly determined second target feature vector of the first frame of shot to be detected is smaller than or equal to the preset vector distance, if the vector distance between the first target feature vector of other template pictures in a preset time period and the corresponding second target feature vector of other target pictures to be detected is smaller than the preset vector distance, all target template pictures and all target pictures to be detected in the preset time period are matched, and then it can be determined that the video stream starts to play the target video in real time within the time period; when the vector distance between the first target feature vector of the target template picture and the corresponding newly determined second target feature vector of the picture to be detected is greater than the preset vector distance, it is indicated that the target template picture is not matched with the picture to be detected due to the broadcasting time error, but the target video is not started to be played in the real-time video stream, and it can be directly determined that the target video is not started to be played in the real-time video stream within the preset time period, and other programs are played.
In one embodiment, before calculating the vector distance, vector quantization is respectively performed on a first target feature vector of the target template picture and a second target feature vector of the target picture to be detected; and
the above step S103 may be performed as:
and calculating the vector distance between the first target characteristic vector of the target template picture and the second target characteristic vector of the target picture to be detected according to the first target characteristic vector of the target template picture after vector quantization and the second target characteristic vector of the target picture to be detected after vector quantization.
Since the number of vector digits in the first target feature vector of the target template picture may be M, the number of vector digits in the second target feature vector of the target picture to be detected may be N, and M and N may be unequal, directly calculating the vector distance between the first target feature vector and the second target feature vector with different number of vector digits increases the calculation burden of the system, slows down the calculation rate of the vector distance, and cannot ensure the real-time performance of the calculated vector distance, therefore, vector quantization is performed through the first target feature vector of the target template picture and the second target feature vector of the target picture to be detected, so that the number of digits in the first target feature vector of each target template picture and the second target feature vector of the corresponding target picture to be detected are equal, which effectively reduces the burden of calculating the vector distance in the system, the calculation speed of the vector distance is accelerated, so that the real-time performance of the calculated vector distance is ensured to the maximum extent, and the speed for judging whether each target picture to be detected is matched with the corresponding target template picture is increased.
As shown in fig. 3, in one embodiment, the step S103 may be performed as:
step A1, acquiring an integral histogram of the target template picture;
step A2, dividing the target template picture into M image blocks;
step A3, obtaining a local histogram of each of M image blocks;
step A4, determining a first target feature vector of the target template picture according to the overall histogram and the M local histograms.
In order to more accurately obtain the first target feature vector of each target template picture, the overall histogram of the target template picture can be obtained to obtain the global features of the target template picture, meanwhile, the target template picture is divided into M regions to obtain the local histogram of the image block of each region so as to obtain the local features of each image block, and finally, the global features and the M local features are used to obtain the first target feature vector of the target template picture with higher accuracy; of course, this scheme may also be used when obtaining the second target feature vector of each target picture to be measured, which is beneficial to improve the accuracy of video program prediction, where M is preferably 4.
As shown in fig. 4, the present invention further provides a device for determining video playing, including: the extracting module 401 is configured to extract a starting playing time of a target video in a template video library and a target template picture corresponding to the starting playing time;
a first obtaining module 402, configured to sequentially obtain, according to a time sequence, a target to-be-detected picture with a most advanced time within a target playing time period corresponding to a starting playing time of a target template picture from a real-time video stream;
a calculating module 403, configured to calculate a vector distance between a first target feature vector of the target template picture and a second target feature vector of the target picture to be detected;
a first determining module 404, configured to sequentially determine, according to the time sequence, whether vector distances between first target feature vectors of other target template pictures in the target video and second target feature vectors of corresponding other target pictures to be detected in a preset time period are both smaller than a preset vector distance when the vector distance is smaller than or equal to the preset vector distance, where the preset time period includes the play start time;
a determining module 405, configured to determine, according to a determination result, whether the target video in the template video library has started to be played in the real-time video stream.
As shown in fig. 5, in one embodiment, the determining module 405 includes:
a first determining sub-module 4051, configured to determine that the target video has started to be played in the real-time video stream when the vector distance is smaller than or equal to the preset vector distance, and when the vector distances between the first target feature vectors of other target template pictures in the target video and the second target feature vectors of corresponding other target pictures to be detected are both smaller than the preset vector distance, and send a video play prompt signal; otherwise, determining that the target video does not start to be played in the real-time video stream.
As shown in fig. 6, in one embodiment, the apparatus further comprises:
a second obtaining module 601, configured to obtain, from the real-time video stream, a to-be-detected picture that is closest to the target playing time period and is in the adjacent playing time period adjacent to the target playing time period when the vector distance is greater than the preset vector distance;
a second determining module 602, configured to determine whether a vector distance between the first target feature vector of the target template picture and the second target feature vector of the picture to be detected is smaller than or equal to the preset vector distance;
the determining module 405 further comprises:
a second determining sub-module 4052, configured to, when a vector distance between the first target feature vector of the target template picture and the second target feature vector of the picture to be detected is smaller than or equal to the preset vector distance, continue to determine, according to the determination result, whether the target video in the template video library has started to be played in the real-time video stream;
a third determining sub-module 4053, configured to directly determine that the target video does not start to be played in the real-time video stream when a vector distance between the first target feature vector of the target template picture and the second target feature vector of the picture to be detected is greater than the preset vector distance.
As shown in fig. 7, in one embodiment, the apparatus further comprises:
a vector quantization module 701, configured to perform vector quantization on the first target feature vector of the target template picture and the second target feature vector of the target picture to be detected before calculating the vector distance; and
the calculation module 403 includes:
the calculating submodule 4031 is configured to calculate a vector distance between the first target feature vector of the target template picture and the second target feature vector of the target picture to be detected according to the first target feature vector of the target template picture after vector quantization and the second target feature vector of the target picture to be detected after vector quantization.
As shown in fig. 8, in one embodiment, the calculation module 403 further includes:
a first obtaining sub-module 4032, configured to obtain an overall histogram of the target template picture;
a dividing submodule 4033, configured to divide the target template picture into M image blocks;
a second obtaining sub-module 4034, configured to obtain a local histogram of each of the M image blocks;
a fourth determining submodule 4035, configured to determine a first target feature vector of the target template picture according to the overall histogram and the M local histograms.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Finally, the video playing determination device is suitable for the terminal equipment. For example, it may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, etc.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (6)
1. A method for determining video playback, comprising:
extracting the starting playing time of a target video in a template video library and a target template picture corresponding to the starting playing time;
sequentially acquiring a target picture to be detected with the most advanced time in a target playing time period corresponding to the starting playing time of the target template picture from the real-time video stream according to the time sequence;
calculating a vector distance between a first target characteristic vector of the target template picture and a second target characteristic vector of the target picture to be detected;
when the vector distance is smaller than or equal to a preset vector distance, sequentially judging whether the vector distances between first target feature vectors of other target template pictures in the target video and second target feature vectors of corresponding other target pictures to be detected in a preset time period are smaller than the preset vector distance according to the time sequence, wherein the preset time period comprises the play starting time;
determining whether the target video in the template video library is started to be played in the real-time video stream according to a judgment result;
determining whether the target video in the template video library has started to be played in the real-time video stream according to the judgment result, including:
when the vector distance is smaller than or equal to the preset vector distance, when the vector distances between the first target feature vectors of other target template pictures in the target video and the second target feature vectors of corresponding other target pictures to be detected are smaller than the preset vector distance, determining that the target video starts to be played in the real-time video stream, and sending a video playing prompt signal; otherwise, determining that the target video does not start to be played in the real-time video stream;
the method further comprises the following steps:
when the vector distance is larger than the preset vector distance, acquiring a picture to be detected with the most forward time in an adjacent playing time period adjacent to the target playing time period from a real-time video stream;
judging whether the vector distance between the first target characteristic vector of the target template picture and the second target characteristic vector of the picture to be detected is smaller than or equal to the preset vector distance;
when the vector distance between the first target characteristic vector of the target template picture and the second target characteristic vector of the picture to be detected is smaller than or equal to the preset vector distance, whether the target video in the template video library is started to be played in the real-time video stream is determined continuously according to the judgment result;
and when the vector distance between the first target characteristic vector of the target template picture and the second target characteristic vector of the picture to be detected is greater than the preset vector distance, directly determining that the target video does not start to be played in the real-time video stream.
2. The method of claim 1,
before calculating the vector distance, respectively carrying out vector quantization on a first target characteristic vector of the target template picture and a second target characteristic vector of the target picture to be detected; and
the calculating a vector distance between a first target feature vector of the target template picture and a second target feature vector of the target picture to be detected includes:
and calculating the vector distance between the first target characteristic vector of the target template picture and the second target characteristic vector of the target picture to be detected according to the first target characteristic vector of the target template picture after vector quantization and the second target characteristic vector of the target picture to be detected after vector quantization.
3. The method according to claim 1 or 2,
the calculating a first target feature vector of the target template picture includes:
acquiring an integral histogram of the target template picture;
dividing the target template picture into M image blocks;
acquiring a local histogram of each of the M image blocks;
and determining a first target feature vector of the target template picture according to the overall histogram and the M local histograms.
4. An apparatus for determining video playback, comprising:
the extraction module is used for extracting the starting playing time of the target video in the template video library and a target template picture corresponding to the starting playing time;
the first acquisition module is used for sequentially acquiring a target picture to be detected with the most advanced time in a target playing time period corresponding to the starting playing time of the target template picture from the real-time video stream according to the time sequence;
the calculation module is used for calculating the vector distance between a first target characteristic vector of the target template picture and a second target characteristic vector of the target picture to be detected;
the first judging module is used for sequentially judging whether the vector distances between the first target feature vectors of other target template pictures in the target video and the second target feature vectors of corresponding other target pictures to be detected in a preset time period are smaller than the preset vector distance according to the time sequence when the vector distance is smaller than or equal to the preset vector distance, wherein the preset time period comprises the playing starting time;
the determining module is used for determining whether the target video in the template video library starts to be played in the real-time video stream according to the judgment result;
the determining module comprises:
the first determining sub-module is used for determining that the target video starts to be played in the real-time video stream and sending a video playing prompt signal when the vector distance is smaller than or equal to the preset vector distance and the vector distances between the first target feature vectors of other target template pictures in the target video and the second target feature vectors of corresponding other target pictures to be detected are smaller than the preset vector distance; otherwise, determining that the target video does not start to be played in the real-time video stream;
the device further comprises:
the second acquisition module is used for acquiring a picture to be detected which is most advanced in time in an adjacent playing time period adjacent to the target playing time period from a real-time video stream when the vector distance is greater than the preset vector distance;
the second judgment module is used for judging whether the vector distance between the first target characteristic vector of the target template picture and the second target characteristic vector of the picture to be detected is smaller than or equal to the preset vector distance or not;
the determining module further comprises:
a second determining submodule, configured to, when a vector distance between a first target feature vector of the target template picture and a second target feature vector of the picture to be detected is smaller than or equal to the preset vector distance, continue to determine, according to the determination result, whether the target video in the template video library has started to be played in the real-time video stream;
and the third determining submodule is used for directly determining that the target video does not start to be played in the real-time video stream when the vector distance between the first target characteristic vector of the target template picture and the second target characteristic vector of the picture to be detected is greater than the preset vector distance.
5. The apparatus of claim 4, further comprising:
the vector quantization module is used for respectively carrying out vector quantization on a first target characteristic vector of the target template picture and a second target characteristic vector of the target picture to be detected before calculating the vector distance; and
the calculation module comprises:
and the calculating submodule is used for calculating the vector distance between the first target characteristic vector of the target template picture and the second target characteristic vector of the target picture to be detected according to the first target characteristic vector of the target template picture after vector quantization and the second target characteristic vector of the target picture to be detected after vector quantization.
6. The apparatus according to claim 4 or 5,
the calculation module further comprises:
the first obtaining sub-module is used for obtaining an overall histogram of the target template picture;
the dividing submodule is used for dividing the target template picture into M image blocks;
the second obtaining sub-module is used for obtaining a local histogram of each image block in the M image blocks;
and the fourth determining submodule is used for determining a first target feature vector of the target template picture according to the overall histogram and the M local histograms.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510438518.8A CN106412690B (en) | 2015-07-23 | 2015-07-23 | Video playing determination method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510438518.8A CN106412690B (en) | 2015-07-23 | 2015-07-23 | Video playing determination method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106412690A CN106412690A (en) | 2017-02-15 |
| CN106412690B true CN106412690B (en) | 2020-01-10 |
Family
ID=58008521
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510438518.8A Expired - Fee Related CN106412690B (en) | 2015-07-23 | 2015-07-23 | Video playing determination method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106412690B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109740530B (en) * | 2018-12-29 | 2022-05-03 | 深圳Tcl新技术有限公司 | Video segment extraction method, device, equipment and computer-readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103152639A (en) * | 2013-03-25 | 2013-06-12 | 天脉聚源(北京)传媒科技有限公司 | Method and device for correcting television program list |
| CN103514293A (en) * | 2013-10-09 | 2014-01-15 | 北京中科模识科技有限公司 | Method for video matching in video template library |
| CN103581705A (en) * | 2012-11-07 | 2014-02-12 | 深圳新感易搜网络科技有限公司 | Method and system for recognizing video program |
| CN104636505A (en) * | 2015-03-13 | 2015-05-20 | 北京世纪互联宽带数据中心有限公司 | Video retrieval method and video retrieval device |
| CN105451068A (en) * | 2015-11-24 | 2016-03-30 | 华数传媒网络有限公司 | Electronic program list generation method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101833650A (en) * | 2009-03-13 | 2010-09-15 | 清华大学 | Video copy detection method based on contents |
-
2015
- 2015-07-23 CN CN201510438518.8A patent/CN106412690B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103581705A (en) * | 2012-11-07 | 2014-02-12 | 深圳新感易搜网络科技有限公司 | Method and system for recognizing video program |
| CN103152639A (en) * | 2013-03-25 | 2013-06-12 | 天脉聚源(北京)传媒科技有限公司 | Method and device for correcting television program list |
| CN103514293A (en) * | 2013-10-09 | 2014-01-15 | 北京中科模识科技有限公司 | Method for video matching in video template library |
| CN104636505A (en) * | 2015-03-13 | 2015-05-20 | 北京世纪互联宽带数据中心有限公司 | Video retrieval method and video retrieval device |
| CN105451068A (en) * | 2015-11-24 | 2016-03-30 | 华数传媒网络有限公司 | Electronic program list generation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106412690A (en) | 2017-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230077355A1 (en) | Tracker assisted image capture | |
| CN107707931B (en) | Method and device for generating interpretation data according to video data, method and device for synthesizing data and electronic equipment | |
| US9852511B2 (en) | Systems and methods for tracking and detecting a target object | |
| CN110691259B (en) | Video playing method, system, device, electronic equipment and storage medium | |
| CN109376256B (en) | Image searching method and device | |
| US9224048B2 (en) | Scene-based people metering for audience measurement | |
| CN108989875B (en) | Method and device for generating bullet screen file | |
| CN106375781B (en) | A kind of judgment method and device repeating video | |
| CN110335313B (en) | Audio acquisition equipment positioning method and device and speaker identification method and system | |
| CN111401238B (en) | Method and device for detecting character close-up fragments in video | |
| CN103763480A (en) | Method and equipment for obtaining video dubbing | |
| CN106375849B (en) | A kind of method, apparatus, the update method of video and device generating template | |
| CN106412690B (en) | Video playing determination method and device | |
| US20070248243A1 (en) | Device and method of detecting gradual shot transition in moving picture | |
| US20200092444A1 (en) | Playback method, playback device and computer-readable storage medium | |
| CN104170367A (en) | Virtual shutter image capture | |
| CN110430424B (en) | FOV testing method and device, storage medium and electronic equipment | |
| CN112287771A (en) | Method, apparatus, server and medium for detecting video event | |
| CN106375850B (en) | A kind of judgment method and device matching video | |
| US20230224528A1 (en) | Method of processing video stream, computer device, and medium | |
| CN109040774B (en) | Program information extraction method, terminal equipment, server and storage medium | |
| CN112380938A (en) | Face recognition and temperature measurement method, device, equipment and medium | |
| CN106375848A (en) | Video playback prompting method and video playback prompting device | |
| CN112069331A (en) | Data processing method, data retrieval method, data processing device, data retrieval device, data processing equipment and storage medium | |
| CN115442656B (en) | Video head and tail automatic detection method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A method and device for determining video playing Effective date of registration: 20210104 Granted publication date: 20200110 Pledgee: Inner Mongolia Huipu Energy Co.,Ltd. Pledgor: WUXI TVMINING MEDIA SCIENCE & TECHNOLOGY Co.,Ltd. Registration number: Y2020990001517 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200110 Termination date: 20210723 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |