CN106375781B - A kind of judgment method and device repeating video - Google Patents
A kind of judgment method and device repeating video Download PDFInfo
- Publication number
- CN106375781B CN106375781B CN201510438517.3A CN201510438517A CN106375781B CN 106375781 B CN106375781 B CN 106375781B CN 201510438517 A CN201510438517 A CN 201510438517A CN 106375781 B CN106375781 B CN 106375781B
- Authority
- CN
- China
- Prior art keywords
- video
- template
- section
- measured
- target
- 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
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]
- H04N21/40—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
Abstract
The invention discloses a kind of judgment methods and device for repeating video.Method includes: to obtain multistage video to be measured from live video stream；Obtain the target feature vector of every section of video to be measured in multistage video to be measured；Multistage template video is extracted from template video library；M template pictures are synthesized into a Target Photo；The feature vector of Target Photo is obtained, and using the feature vector of Target Photo as the template characteristic vector of every section of template video；Calculate the vector distance between the target feature vector of every section of video to be measured and the template characteristic vector of every section of template video；When the vector distance between the target feature vector of one section of video to be measured and the template characteristic vector of one section of template video is less than or equal to default vector distance, at least partly video and one section of template video repetition in one section of video to be measured are determined.According to the technical solution of the present invention, video repeatability detection can be accurately carried out, programming predictions are accurately carried out.
Description
Technical field
The present invention relates to technical field of video processing, in particular to a kind of judgment method and device for repeating video.
Background technique
Currently, needing to carry out in electronic program guide (EPG, Electronic Program Guide) processing system
Program is predicted in real time.And predicting program is actually to carry out video repeatability detection.But the artificial repeated detection of progress
Task amount is very big, and efficiency is lower, and the accuracy rate of repeatability detection and precision are all relatively low, therefore, it is impossible to accurately carry out
Program predicts that this brings very big inconvenience to user in real time.
Summary of the invention
The present invention provides a kind of judgment method and device for repeating video, to use template video accurately to carry out video
Repeatability detection, and ensure the precision and efficiency of video repeatability detection, to realize to the program played in live video stream
Carry out accurate programming predictions.
The present invention provides a kind of judgment method for repeating video, comprising: from live video stream, obtains multistage view to be measured
Frequently；
Obtain the target feature vector of every section of video to be measured in multistage video to be measured, wherein the target feature vector
For every section of the unique identification video to be measured；
Multistage template video is extracted from template video library, wherein have M in every section of template video in multistage template video
Open template picture；
The pixel value of the target pixel points of same position in M in every section of template video template pictures is carried out
The M template pictures are synthesized a Target Photo, wherein the target picture of every template picture by weighted sum
The pixel value of vegetarian refreshments in the pixel value of the target pixel points of the Target Photo shared weight and be equal to 1；
The feature vector of the Target Photo is obtained, and using the feature vector of the Target Photo as template described in every section
The template characteristic vector of video；
Calculate every section of video to be measured target feature vector and every section of template video template characteristic vector it
Between vector distance；
When the vector between the target feature vector of one section of video to be measured and the template characteristic vector of one section of template video away from
When from being less than or equal to default vector distance, at least partly video and one section of template in one section of video to be measured are determined
Video repeats；Otherwise, it is determined that one section of video to be measured does not repeat completely with one section of template video.
In one embodiment, in the target feature vector and every section of template video for calculating every section of video to be measured
Template characteristic vector between vector distance before, the method also includes:
The template characteristic vector of template video described in multistage is clustered, to obtain multiclass template characteristic vector；
Determining at least partly video and one section of template video repetition in one section of video to be measured；Otherwise, sentence
Before fixed one section of video to be measured and one section of template video do not repeat completely, the method also includes:
When the vector distance between the target feature vector and a kind of template characteristic vector of one section of video to be measured is less than
Or when being equal to default vector distance, determine at least partly video in one section of video to be measured and a kind of template characteristic to
Corresponding target template video is measured to repeat, and start to judge at least partly video in one section of video to be measured whether with it is described
One section of template video repeats；Otherwise, it is determined that one section of video to be measured does not repeat completely with the target template video, and no longer
Judge whether at least partly video in one section of video to be measured repeats with one section of template video.
In one embodiment, determining at least partly video and class template spy in one section of video to be measured
Before levying the corresponding target template video repetition of vector, the method also includes:
Vector distance between the target feature vector and a kind of template characteristic vector of one section of video to be measured
When less than or equal to the default vector distance, by each of one section of video to be measured picture to be measured and the target template
Each target template picture in video is successively matched；
The vector distance when between the target feature vector and a kind of template characteristic vector of one section of video to be measured
When less than or equal to default vector distance, at least partly video and class template spy in one section of video to be measured are determined
The corresponding target template video of vector is levied to repeat；Otherwise, it is determined that one section of video to be measured and the target template video are complete
It does not repeat, comprising:
When the vector distance between the target feature vector and a kind of template characteristic vector of one section of video to be measured is less than
Or be equal to default vector distance, the vector distance closest in the default vector distance and one section of video to be measured with
When the number for the picture to be measured that target template picture in the target template video matches is higher than preset number, described in judgement
At least partly video and the target template video in one section of video to be measured repeat；Otherwise, it is determined that one section of video to be measured
In at least partly video do not repeated completely with the target template video；
The method also includes:
After determining that at least partly video in one section of video to be measured does not repeat completely with the target template video,
The vector distance between the target feature vector of one section of video to be measured is successively being found in multiclass template characteristic vector most
Close to other class template feature vectors of the default vector distance；
Judge in one section of video to be measured in target template video corresponding with other described class template feature vectors
Whether the number for the picture to be measured that target template picture matches is higher than the preset number, and circuits sequentially, until described one
Target Photo in section video to be measured in target template video corresponding with other described class template feature vectors match to
The number of mapping piece is higher than in every section of video to be measured in the preset number or multistage video to be measured and other described class templates
The number for the picture to be measured that target template picture in the corresponding target template video of feature vector matches is below described pre-
If number.
In one embodiment, in the feature vector for obtaining the Target Photo, and by the feature of the Target Photo to
Before amount is as the template characteristic vector of template video described in every section, the method also includes:
The target icon is subjected to DCT conversion, obtains the lateral coefficient of pixel coordinate and longitudinal system after DCT is converted
Number；
And
The feature vector for obtaining the Target Photo, and using the feature vector of the Target Photo as described in every section
The template characteristic vector of template video, comprising:
The preceding Q2 potential coefficient in the preceding Q1 potential coefficient and longitudinal coefficient in the lateral coefficient is chosen, before described
Q1 potential coefficient and the preceding Q2 potential coefficient generate the template characteristic vector of every section of template video.
In one embodiment, in the target that the M in every section of template video is opened to the same position in template pictures
The pixel value of pixel is weighted summation, when the M template pictures are synthesized a target icon, the M moulds
Pixel value of the pixel value of the target pixel points of kth model picture in block picture in the target pixel points of the Target Photo
In shared weight αk=γ∧k, wherein γ is the constant less than 1.
The present invention also provides a kind of judgment means for repeating video, comprising: first obtains module, is used for from live video stream
In, obtain multistage video to be measured；
Second obtains module, for obtaining the target feature vector of every section of video to be measured in multistage video to be measured, wherein
The target feature vector is used for every section of the unique identification video to be measured；
Processing module, for extracting multistage template video from template video library, wherein every section in multistage template video
There are M template pictures in template video；
Summation module, for the M in every section of template video to be opened to the object pixel of the same position in template pictures
The pixel value of point is weighted summation, the M template pictures is synthesized a Target Photo, wherein every mould
The pixel value of the target pixel points of plate picture in the pixel value of the target pixel points of the Target Photo shared weight and it is small
In or equal to 1；
Third obtains module, for obtaining the feature vector of the Target Photo, and by the feature of the Target Photo to
Measure the template characteristic vector as template video described in every section；
Computing module, for calculating the target feature vector of every section of video to be measured and the mould of every section of template video
Vector distance between plate features vector；
Determination module, for working as the target feature vector of one section of video to be measured and the template characteristic vector of one section of template video
Between vector distance when being less than or equal to default vector distance, determine at least partly video in one section of video to be measured with
One section of template video repeats；Otherwise, it is determined that one section of video to be measured does not repeat completely with one section of template video.
In one embodiment, described device further include:
Cluster module, in the target feature vector for calculating every section of video to be measured and every section of template video
Before vector distance between template characteristic vector, the template characteristic vector of template video described in multistage is clustered, with
To multiclass template characteristic vector；
The determination module includes:
Decision sub-module, for determining at least partly video and one section of template view in one section of video to be measured
Frequency repeats；Otherwise, it is determined that before one section of video to be measured and one section of template video do not repeat completely, when described one section to
When the vector distance surveyed between the target feature vector of video and a kind of template characteristic vector is less than or equal to default vector distance,
Determine at least partly video target template video corresponding with one kind template characteristic vector in one section of video to be measured
It repeats, and starts to judge whether at least partly video in one section of video to be measured repeats with one section of template video；It is no
Then, determine that one section of video to be measured does not repeat completely with the target template video, and no longer judge in one section of video to be measured
At least partly video whether with one section of template video repeat.
In one embodiment, described device further include:
Matching module, for determining at least partly video and a kind of template characteristic in one section of video to be measured
Before the corresponding target template video of vector repeats, when the target feature vector and a class template of one section of video to be measured
When vector distance between feature vector is less than or equal to the default vector distance, by each of described one section of video to be measured
Picture to be measured is successively matched with each target template picture in the target template video；
The decision sub-module is also used to:
When the vector distance between the target feature vector and a kind of template characteristic vector of one section of video to be measured is less than
Or be equal to default vector distance, the vector distance closest in the default vector distance and one section of video to be measured with
When the number for the picture to be measured that target template picture in the target template video matches is higher than preset number, described in judgement
At least partly video and the target template video in one section of video to be measured repeat；Otherwise, it is determined that one section of video to be measured
In at least partly video do not repeated completely with the target template video；
Described device further include:
Module is found, for determining at least partly video and the target template video in one section of video to be measured
After not repeating completely, successively found between the target feature vector of one section of video to be measured in multiclass template characteristic vector
Vector distance closest to the default vector distance other class template feature vectors；
Judgment module, for judging target corresponding with other described class template feature vectors in one section of video to be measured
Whether the number for the picture to be measured that the target template picture in template video matches is higher than the preset number, and successively follows
Ring, the target figure in target template video corresponding with other described class template feature vectors in one section of video to be measured
The number for the picture to be measured that piece matches is higher than in every section of video to be measured in the preset number or multistage video to be measured and institute
State the number for the picture to be measured that the target template picture in the corresponding target template video of other class template feature vectors matches
It is below the preset number.
In one embodiment, described device further include:
Conversion module, in the feature vector for obtaining the Target Photo, and by the feature vector of the Target Photo
Before the template characteristic vector of template video described in every section, the target icon is subjected to DCT conversion, obtains DCT conversion
The lateral coefficient of pixel coordinate and longitudinal coefficient afterwards；
The third obtains module
Submodule is generated, for choosing preceding Q2 in preceding Q1 potential coefficient and longitudinal coefficient in the lateral coefficient
Coefficient generates the template characteristic vector of every section of template video according to the preceding Q1 potential coefficient and the preceding Q2 potential coefficient.
In one embodiment, in the target that the M in every section of template video is opened to the same position in template pictures
The pixel value of pixel is weighted summation, when the M template pictures are synthesized a target icon, the M moulds
Pixel value of the pixel value of the target pixel points of kth model picture in block picture in the target pixel points of the Target Photo
In shared weight αk=γ∧k, wherein γ is the constant less than 1.
The technical scheme provided by this disclosed embodiment can include the following benefits:
It can be according between the target feature vector of every section of video to be measured and the template characteristic vector of every section of template video
Vector distance determines the similarity of every section of video to be measured and every section of template video, and then determines in this section of video to be measured at least
Whether partial video repeats with this section of template video, and then realization can accurately carry out video repeatability detection, and ensure video
The precision and efficiency of repeatability detection, and finally realize that accurately determine template video specifically starts to play in video to be measured
Time accurately carries out programming predictions to realize.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification
It obtains it is clear that understand through the implementation of the invention.The objectives and other advantages of the invention can be by written explanation
Specifically noted structure is achieved and obtained in book, claims and attached drawing.
Below by drawings and examples, technical scheme of the present invention will be described in further detail.
Detailed description of the invention
Attached drawing is used to provide further understanding of the present invention, and constitutes part of specification, with reality of the invention
It applies example to be used to explain the present invention together, not be construed as limiting the invention.In the accompanying drawings:
Fig. 1 is a kind of flow chart of judgment method for repeating video shown according to an exemplary embodiment.
Fig. 2 is a kind of block diagram of judgment means for repeating video shown according to an exemplary embodiment.
Fig. 3 is the block diagram of another judgment means for repeating video shown according to an exemplary embodiment.
Fig. 4 is the block diagram of the judgment means of another repetition video shown according to an exemplary embodiment.
Fig. 5 is the block diagram of the judgment means of another repetition video shown according to an exemplary embodiment.
Specific embodiment
Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings, it should be understood that preferred reality described herein
Apply example only for the purpose of illustrating and explaining the present invention and is not intended to limit the present invention.
In the related technology, it in electronic program guide (EPG, Electronic Program Guide) processing system, needs
Program is carried out to predict in real time.And predicting program is actually to carry out video repeatability detection.But it is artificial to carry out repeatability
The task amount of detection is very big, and efficiency is lower, and the accuracy rate of repeatability detection and precision are all relatively low, therefore, it is impossible to accurately
Ground carries out program and predicts that this brings very big inconvenience to user in real time.
In order to solve the above-mentioned technical problem, the embodiment of the present disclosure provides a kind of judgment method for repeating video, this method
Suitable for the determining program, system or the device that repeat video, as shown in Figure 1,
In step s101, from live video stream, when obtaining multistage video to be measured, it is preferable that make the two of arbitrary neighborhood
There is the matched video frame in part between section video to be measured, such as: there is 50% weight between two sections of videos to be measured of arbitrary neighborhood
Conjunction rate, such as: one whole section of live video stream is mnpqrsdpddqc, can intercept into mnpqrs, tri- sections of qrsdpd, dpddqc to
Video is surveyed, two sections can be divided into avoid video to be measured identical with template video in this way and to compare with template video respectively, from
And ensure the continuity of video to be measured, certainly, every section of video to be measured can include an independent program or advertisement.
In step s 102, the target feature vector of every section of video to be measured in multistage video to be measured is obtained, wherein target
Feature vector is used for every section of unique identification video to be measured；Target feature vector is used for every section of unique identification video to be measured, is every section
The video finger print of the video to be measured of the fingerprint of video to be measured, that is, every section.
In step s 103, multistage template video is extracted from template video library, wherein every section in multistage template video
There are M template pictures in template video；
Template video library can be several derived customized channels, the i.e. view such as most interior in a couple of days history program, advertisement
Frequency evidence is stored in video template library, such as: can be most in a couple of days in several customized channels program, wide
The video datas such as announcement, specifically: therefore the pictures such as all programs, advertisement from program start time to finish time use this
Known template video library (it can be multiple programs or advertisement, and every section of template video can include an independent advertisement
Or program) this program or advertisement can be searched in the real time programme stream of all channels, and searched in real time programme stream
When the program or advertisement, that is, it can determine the specific time started of the program or advertisement in real time programme stream being played on, from
And realize programming predictions.
Secondly, can be regarded from every section of template in template video library when obtaining the M in every section of template video template picture
It is extracted once using down-sampled mode every 5 (or 2) pictures in all template pictures of frequency, both reduces identical molds in this way
The processing of plate picture, and reduce the data processing amount of template picture, reasonable sample rate will not cause losing for important information
It loses.
In addition, smooth treatment can be carried out using Gaussian function to every template picture when extracting M template pictures,
And it is W*H=720*480 that picture is uniformly reduced into size, to be uniformly processed, furthermore it is preferred that multistage template regards
There is 50% coincidence factor in frequency between two sections of template videos of arbitrary neighborhood, such as: template video library is abcdefghigklmn, can
To intercept into abcdef, defghi, ghigkl, tetra- sections of template videos of gklmn, in order to ensure that video and template video to be measured exist
Continuity when comparing, certainly, since every section of video represents a program or advertisement, and the duration of different program or advertisement is not
Together, so the possibility for the template picture for including in every section of template video is different namely the corresponding M of every section of template video is different；And
If predicting programme information, every section of template video can be the video-frequency band of program head；If predicting advertising information, every section of template view
Frequency can choose the video-frequency band of advertisement.
In step S104, by the target pixel points of the same position in the M in every section of template video template pictures
Pixel value is weighted summation, M template pictures is synthesized a Target Photo, wherein the target of every template picture
The pixel value of pixel in the pixel value of the target pixel points of Target Photo shared weight and be equal to 1；
By the way that the pixel value of the target pixel points of the same position in the M in every section of template video template pictures is carried out
M template pictures can be synthesized a representative Target Photo, so that the feature of the Target Photo by weighted sum
The feature of M picture is combined, so that the template that the feature vector of the Target Photo can represent this section of template video is special
Levy vector；And the pixel value of the target pixel points of every template picture is shared in the pixel value of the target pixel points of Target Photo
Weight and be equal to 1, then be to ensure that the M template picture can synthesize the necessary condition of a picture, so that after synthesis
The pixel value of each target pixel points be still no more than every template picture in M template picture the target pixel points most
Big pixel value, wherein weighted sum is exactly that the weight number adduction of M picture is equal to 1, a1*p1+a2*p2 ...=p, wherein p1,
P2 ... is the pixel value of the target pixel points of every figure in M figures, and p is the pixel of the target pixel points in the Target Photo
Value, it is Fig. 1 in M picture that a1, a2, a3 ... be corresponding, and the pixel value of 2,3 ... some target pixel points accounts for the Target Photo
In the target pixel points weight, weighted value is all nonnegative number, a1+a2+ ...=1.
In step s105, the feature vector of Target Photo is obtained, and using the feature vector of Target Photo as every section of mould
The template characteristic vector of plate video；Template characteristic vector is used for every section of template video of unique identification, is every section of template video
The video finger print of the template video of fingerprint, that is, every section.
In step s 106, calculate every section of video to be measured target feature vector and every section of template video template characteristic to
Vector distance between amount；
Wherein, vector distance is used to characterize similarity between every section of video to be measured and every section of template video, and vector away from
From smaller, similarity is higher；By successively calculating the target feature vector of every section of video to be measured and the template of every section of template video
Vector distance between feature vector can accurately determine the similarity between every section of video to be measured and every section of template video,
Accurately locking and the highest video-frequency band to be measured of every section of template video repetitive rate, it is ensured that the precision and effect of video repeatability detection
Rate, and prevent detection and omit, and vector distance is smaller, similarity is higher, illustrates that this section of video to be measured is regarded with this section of template
The repetitive rate of frequency is higher.
In step s 107, when the template characteristic vector of the target feature vector of one section of video to be measured and one section of template video
Between vector distance when being less than or equal to default vector distance, determine at least partly video in one section of video to be measured and one section
Template video repeats；Otherwise, it is determined that one section of video to be measured does not repeat completely with one section of template video.
When the vector between the target feature vector of this section of video to be measured and the template characteristic vector of this section of template video away from
When from being less than or equal to default vector distance, illustrate that the similarity of this section of video to be measured and this section of template video is high, and then say
The repetitive rate of bright this section of video to be measured and this section of template video is high, it may be considered that at least partly view in this section of video to be measured
Frequency is repeated with this section of template video, i.e. at least partly video in this section of video to be measured is the data in this section of template video, into
And convenient for determining starting position of this section of template video in this section of video to be measured, thus accurately in real-time stream
The program (i.e. the template video) of broadcasting is predicted.Certainly, when the vector distance is greater than generally default vector distance, illustrate this
Section video to be measured and the similarity of this section of template video are extremely low, and then the repetitive rate pole of this section of video to be measured and this section of template video
It is low, it may be considered that this section of video to be measured does not repeat completely with this section of template video；In addition, in determining this section of video to be measured
After at least partly video is repeated with this section of template video, in order to further accurately determine which in this section of video to be measured to mapping
Piece match and (is repeated) with which picture in this section of template video, or determines repetitive rate in order to further accurate, can be by
Every picture to be measured in this section of video to be measured matches one by one with every picture in this section of template video.
In one embodiment, special in the template of the target feature vector and every section of template video that calculate every section of video to be measured
Before levying the vector distance between vector, method further include:
The template characteristic vector of multistage template video is clustered, with obtain the multiclass template characteristic in template video library to
Amount, wherein every class template feature vector is a cluster centre；
Since every section of template video corresponds to a template characteristic vector, and when the number of segment that template video includes is excessive,
The number of template characteristic vector will be excessive, or even has many incoherent template characteristic vectors, therefore, if directly calculated
Vector distance between every section of video object feature vector to be measured and the template characteristic vector of every section of template video, will necessarily make
Since template characteristic vector is excessive, and the computation rate of impact vector distance, increase the computation burden of system, therefore, pass through by
The template characteristic vector of the essentially identical template video of similarity is clustered, the template characteristic vector after can making cluster
Number of vectors significantly reduce (such as: the quantity of the vector in template characteristic vector after cluster be cluster before 5%).
Determining at least partly video and one section of template video repetition in one section of video to be measured；Otherwise, it is determined that one section to
Before survey video and one section of template video do not repeat completely, method further include:
When between the target feature vector and a kind of template characteristic vector (i.e. a certain class cluster centre) of one section of video to be measured
Vector distance when being less than or equal to default vector distance, determine at least partly video and a class template in one section of video to be measured
Whether the corresponding target template video of feature vector repeats, and start to judge at least partly video in one section of video to be measured with one
Section template video repeats；Otherwise, it is determined that one section of video to be measured does not repeat completely with target template video, and no longer judge one section to
Whether at least partly video surveyed in video repeats with one section of template video, wherein the corresponding target template of every class cluster centre
Video is made of the higher several segments template video of similarity, i.e., every class cluster centre has several higher moulds of similarity
Plate features vector composition, wherein several corresponding videos of template characteristic vector are the several segments template video, and this section
Video to be measured is one section of video to be measured in the corresponding target template video of one kind template characteristic vector.
Due to judge one by one at least partly video in every section of video to be measured whether with the duplicate work of every section of template video
Measure it is very big, the processing load of system is very heavy, therefore, by the template characteristic of the essentially identical template video of similarity to
After amount is clustered, the arrow between the target feature vector of every section of video to be measured and every class template feature vector can be first calculated
Span is from if the vector distance illustrates the phase of this section of video to be measured and the target template video less than default vector distance
It is high like spending, and then can tentatively judge that at least partly video in this section of video to be measured is corresponding with such template characteristic vector
Target template video repeats, and for the specific airtime in template video library in further accurate lock live video stream, it can
Further to judge the target template whether corresponding with such template characteristic vector of at least partly video in this section of video to be measured
A certain section of template video in video repeats, and then convenient for accurately locking every section of template video in template video library real-time
Specific location namely specific airtime in video flowing；Certainly, if the vector distance is greater than or equal to default vector distance,
Then illustrate that the similarity of this section of video to be measured and the target template video is extremely low, it is basic it is considered that not repeating completely, then completely
It is not necessary to further judge at least partly video in this section of video to be measured whether with certain section of mould in the target template video
Plate video repeats, so that the video for alleviating system repeats the burden for detecting and predicting.In addition, K- can be used when cluster
Means clustering algorithm.
In one embodiment, determining at least partly video and a kind of template characteristic vector pair in one section of video to be measured
Before the target template video answered repeats, method further include:
When the vector distance between the target feature vector and a kind of template characteristic vector of one section of video to be measured is less than or waits
When default vector distance, by each target template in each of one section of video to be measured picture to be measured and target template video
Picture is successively matched；
If the vector distance is less than default vector distance, at least partly view in this section of video to be measured can only be tentatively judged
Frequency target template video corresponding with such template characteristic vector repeats, and in order to further be accurately determined this section of video to be measured
In the similarity of at least partly video target template video corresponding with such template characteristic vector whether really repeat, need
Whether deeply compare each target template picture in each of this section of video to be measured picture to be measured and the target template video
Matching to ensure that video repeats the precision of detection, and then ensures the programming predictions precision in live video stream.
When the vector distance between the target feature vector and a kind of template characteristic vector of one section of video to be measured is less than or waits
When default vector distance, at least partly video target corresponding with a kind of template characteristic vector in one section of video to be measured is determined
Template video repeats；Otherwise, it is determined that one section of video to be measured does not repeat completely with target template video, comprising:
When the vector distance between the target feature vector and a kind of template characteristic vector of one section of video to be measured is less than or waits
In default vector distance, the vector distance, closest to the default vector distance, (i.e. one kind template characteristic vector is most to connect
Close cluster centre) and one section of video to be measured in the picture to be measured that matches with the target template picture in target template video
Number be higher than preset number when, determine one section of video to be measured at least partly video and target template video repeat；Otherwise,
Determine that at least partly video in one section of video to be measured does not repeat completely with target template video；
When the vector distance between the target feature vector and such template characteristic vector of this section of video to be measured is less than or waits
In default vector distance and such template characteristic vector closest to this section of video to be measured target feature vector when, if this section is to be measured
When picture to be measured matches number higher than preset number with corresponding target template picture in video, illustrate this section of video to be measured with
The similarity of target template video is higher, and then can be determined that at least partly video in the video to be measured and the target template regard
Frequency repeats, and otherwise, illustrates that the similarity of this section of video to be measured and the target template video is lower, and then can be determined that the view to be measured
At least partly video in frequency does not repeat completely with the target template video, certainly, in the target for determining a certain section of video to be measured
Vector distance between feature vector and a certain class template feature vector whether most the proximity default vector distance when, need to calculate
The vector between every class template feature vector in the target feature vector and multiclass template characteristic vector of this section of video to be measured away from
From then each vector distance being compared therefrom to select with the default vector distance and presets vector distance most with this
Close vector distance is regarded from determining with the target template of the default immediate a certain class template feature vector of vector distance
Frequently.
Method further include:
After determining that at least partly video in one section of video to be measured does not repeat completely with target template video, successively more
It is found in class template feature vector and the closest default vector of vector distance between the target feature vector of one section of video to be measured
Other class template feature vectors (i.e. other nearly cluster centre) of distance；
After determining that at least partly video in this section of video to be measured does not repeat completely with the target template video, Ke Yi
It finds in multiclass template characteristic vector and is sweared the vector distance between the target feature vector of this section of video to be measured closest to default
Span from other nearly class template feature vectors, with judge time corresponding target template video of near-lying mode plate features vector whether with
This section of video to be measured repeats.
Judge the target template in one section of video to be measured in target template video corresponding with other class template feature vectors
Whether the number for the picture to be measured that picture matches is higher than preset number, and circuits sequentially, until in one section of video to be measured with its
The number for the picture to be measured that Target Photo in the corresponding target template video of his class template feature vector matches is higher than default
In every section of video to be measured in number or multistage video to be measured in target template video corresponding with other class template feature vectors
The number of picture to be measured that matches of target template picture be below preset number.
Vector distance between the target feature vector and some other secondary near-lying mode plate features vector of this section of video to be measured
Less than or equal to default vector distance, if picture to be measured is corresponding with other secondary near-lying mode plate features vectors in this section of video to be measured
When target template picture matches number higher than preset number, illustrate this section of video to be measured and other secondary near-lying mode plate features vectors
The similarity of corresponding target template video is higher, and then can be determined that at least partly video in the video to be measured and other times
Near-lying mode plate features vector corresponds to the repetition of target template video, otherwise, illustrates this section of video to be measured and other secondary near-lying mode plate features
The similarity that vector corresponds to target template video is lower, and then can determine at least partly video in the video to be measured and this its
His time near-lying mode plate features vector corresponds to target template video and does not repeat completely；Certainly, if in this section of video to be measured with it is all its
The number for the picture to be measured that target template picture in his time corresponding target template video of near-lying mode plate features vector matches is equal
Lower than preset number, then illustrates that this section of video to be measured and entire template video library do not repeat, then can jump out circulation, reselection
The video to be measured of other sections is matched with target template video, accurately to determine whether played the mould in the live video stream
Plate video library, and if playing has the template video library, specifically play the time of the template video.
In one embodiment, in the feature vector for obtaining Target Photo, and using the feature vector of Target Photo as every
Before the template characteristic vector of section template video, method further include:
Target icon is subjected to DCT conversion, obtains the lateral coefficient and longitudinal coefficient of pixel coordinate after DCT conversion；
Above-mentioned steps S105 can be performed as:
The preceding Q2 potential coefficient in the preceding Q1 potential coefficient and longitudinal coefficient in lateral coefficient is chosen, according to preceding Q1 potential coefficient with before
Q2 potential coefficient generates the template characteristic vector of every section of template video.
When generating template characteristic vector, more forward several potential coefficients are characterizing the target in lateral coefficient and longitudinal coefficient
Shared weight is bigger when picture, the template characteristic vector of generation more can accurately indicate the Target Photo, and if selection
Coefficient digit is more, and the calculation amount of system will be bigger, and the computation burden of system will be heavier, calculated Target Photo feature
The real-time of vector will be lower, therefore, when generating Target Photo feature vector, can be wanted with integration objective picture feature vector
The computing capability of the precision, system asked and the requirement of real-time of feature vector choose preceding Q1 potential coefficient and longitudinal direction in lateral coefficient
Preceding Q2 potential coefficient in coefficient, to meet required precision, the computing capability of system and the reality of feature vector of feature vector simultaneously
When property requirement, wherein Q1 and Q2 is preset value, it is preferable that the value of Q1 and Q2 is 1.
In one embodiment, in the object pixel that the M in every section of template video is opened to the same position in template pictures
The pixel value of point is weighted summation, kth when M template pictures are synthesized a target icon, in M model pictures
Open the pixel value of the target pixel points of model picture weight α shared in the pixel value of the target pixel points of Target Photok=
γ∧k, wherein γ is the constant less than 1.
When M template pictures are synthesized a target icon, the kth in the M model pictures opens model picture
The pixel value of each target pixel points power shared in the pixel value of the target pixel points of the corresponding position in the Target Photo
Weight αk=γ∧k, wherein γ be preferably 0.65, certainly, for some target pixel points, every template picture
The pixel value of target pixel points weight α shared in the pixel value of the target pixel points of the Target PhotokAnd should
Less than or equal to 1, certainly, due to
αkIt is an exponential form, therefore, the M corresponding α of template picturekBe likely larger than 1, only need in this case
To each weight αkIt is normalized.
As shown in Fig. 2, the present invention also provides a kind of judgment means for repeating video, comprising: first obtains module 201, quilt
It is configured to from live video stream, obtains multistage video to be measured；
Second obtain module 202, be configured as obtain multistage video to be measured in every section of video to be measured target signature to
Amount, wherein the target feature vector is configured as every section of the unique identification video to be measured；
Processing module 203 is configured as extracting multistage template video from template video library, wherein multistage template video
In every section of template video in have M template pictures；
Summation module 204 is configured as the mesh of the same position in the M in every section of template video template pictures
The pixel value of mark pixel is weighted summation, the M template pictures is synthesized a Target Photo, wherein every
The pixel value of the target pixel points of the template picture shared weight in the pixel value of the target pixel points of the Target Photo
And be equal to 1；
Third obtains module 205, is configured as obtaining the feature vector of the Target Photo, and by the Target Photo
Template characteristic vector of the feature vector as template video described in every section；
Computing module 206 is configured as calculating the target feature vector and every section of template of every section of video to be measured
Vector distance between the template characteristic vector of video；
Determination module 207 is configured as working as the target feature vector of one section of video to be measured and the template of one section of template video
When vector distance between feature vector is less than or equal to default vector distance, at least portion in one section of video to be measured is determined
Video and one section of template video is divided to repeat；Otherwise, it is determined that one section of video to be measured and one section of template video are complete
It does not repeat.
As shown in figure 3, in one embodiment, described device further include:
Cluster module 301 is configured as in the target feature vector and every section of mould for calculating every section of video to be measured
Before vector distance between the template characteristic vector of plate video, the template characteristic vector of template video described in multistage is gathered
Class, to obtain multiclass template characteristic vector；
The determination module 207 includes:
Decision sub-module 2071 is configured as determining at least partly video and described one in one section of video to be measured
Section template video repeats；Otherwise, it is determined that working as institute before one section of video to be measured and one section of template video do not repeat completely
It states the vector distance between the target feature vector of one section of video to be measured and a kind of template characteristic vector and is less than or equal to default arrow
Span from when, determine at least partly video target corresponding with one kind template characteristic vector in one section of video to be measured
Template video repeat, and start to judge at least partly video in one section of video to be measured whether with one section of template video
It repeats；Otherwise, it is determined that one section of video to be measured does not repeat completely with the target template video, and no longer judge described one section
Whether at least partly video in video to be measured repeats with one section of template video.
As shown in figure 4, in one embodiment, described device further include:
Matching module 401 is configured as determining at least partly video and described one kind in one section of video to be measured
Before the corresponding target template video of template characteristic vector repeats, when one section of video to be measured target feature vector with it is described
When vector distance between a kind of template characteristic vector is less than or equal to the default vector distance, by one section of video to be measured
Each of picture to be measured successively matched with each target template picture in the target template video；
The decision sub-module 207 is also configured to
When the vector distance between the target feature vector and a kind of template characteristic vector of one section of video to be measured is less than
Or be equal to default vector distance, the vector distance closest in the default vector distance and one section of video to be measured with
When the number for the picture to be measured that target template picture in the target template video matches is higher than preset number, described in judgement
At least partly video and the target template video in one section of video to be measured repeat；Otherwise, it is determined that one section of video to be measured
In at least partly video do not repeated completely with the target template video；
Described device further include:
Module 402 is found, is configured as determining at least partly video and the target in one section of video to be measured
After template video does not repeat completely, the target signature with one section of video to be measured is successively found in multiclass template characteristic vector
Other class template feature vectors of vector distance between vector closest to the default vector distance；
Judgment module 403 is configured as judging in one section of video to be measured and other described class template feature vectors pair
Whether the number for the picture to be measured that the target template picture in target template video answered matches is higher than the preset number, and
It circuits sequentially, until in target template video corresponding with other described class template feature vectors in one section of video to be measured
The number for the picture to be measured that Target Photo matches is higher than every section of video to be measured in the preset number or multistage video to be measured
In the picture to be measured that matches of target template picture in target template video corresponding with other described class template feature vectors
Number be below the preset number.
As shown in figure 5, in one embodiment, described device further include:
Conversion module 501 is configured as in the feature vector for obtaining the Target Photo, and by the spy of the Target Photo
Before vector is levied as the template characteristic vector of template video described in every section, the target icon is subjected to DCT conversion, is obtained
The lateral coefficient of pixel coordinate and longitudinal coefficient after DCT conversion；
Third obtains module 205
Submodule 2051 is generated, is configured as choosing in the preceding Q1 potential coefficient and longitudinal coefficient in the lateral coefficient
Preceding Q2 potential coefficient, the template characteristic of every section of template video is generated according to the preceding Q1 potential coefficient and the preceding Q2 potential coefficient
Vector.
In one embodiment, in the target that the M in every section of template video is opened to the same position in template pictures
The pixel value of pixel is weighted summation, when the M template pictures are synthesized a target icon, the M moulds
Pixel value of the pixel value of the target pixel points of kth model picture in block picture in the target pixel points of the Target Photo
In shared weight αk=γ∧k, wherein γ is the constant less than 1.
About the device in above-described embodiment, wherein each unit executes the concrete mode of operation in related this method
Embodiment in be described in detail, no detailed explanation will be given here.
Finally, the judgment means of the repetition video in the present invention are suitable for terminal device.For example, it may be mobile phone,
Computer, digital broadcasting terminal, messaging device, game console, tablet device, Medical Devices, body-building equipment, a number
Word assistant etc..
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The shape for the computer program product implemented in usable storage medium (including but not limited to magnetic disk storage and optical memory etc.)
Formula.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (6)
1. a kind of judgment method for repeating video characterized by comprising
From live video stream, multistage video to be measured is obtained；
Obtain the target feature vector of every section of video to be measured in multistage video to be measured, wherein the target feature vector is used for
Every section of the unique identification video to be measured；
Multistage template video is extracted from template video library, wherein there are M moulds in every section of template video in multistage template video
Plate picture；
The pixel value of the target pixel points of same position in M in every section of template video template pictures is weighted
The M template pictures are synthesized a Target Photo, wherein the target pixel points of every template picture by summation
Pixel value in the pixel value of the target pixel points of the Target Photo shared weight and be equal to 1；
The feature vector of the Target Photo is obtained, and using the feature vector of the Target Photo as template video described in every section
Template characteristic vector；
It calculates between the target feature vector of every section of video to be measured and the template characteristic vector of every section of template video
Vector distance；
When the vector distance between the target feature vector of one section of video to be measured and the template characteristic vector of one section of template video is small
When the first default vector distance, at least partly video and one section of template in one section of video to be measured are determined
Video repeats；Otherwise, it is determined that one section of video to be measured does not repeat completely with one section of template video；
Between the template characteristic vector of target feature vector and every section of template video for calculating every section of video to be measured
Vector distance before, the method also includes:
The template characteristic vector of template video described in multistage is clustered, to obtain multiclass template characteristic vector；
Determining at least partly video and one section of template video repetition in one section of video to be measured；Otherwise, it is determined that institute
It states before one section of video to be measured and one section of template video do not repeat completely, the method also includes:
When the vector distance between the target feature vector and a kind of template characteristic vector of one section of video to be measured is less than or waits
When the second default vector distance, determine at least partly video in one section of video to be measured and a kind of template characteristic to
Corresponding target template video is measured to repeat, and start to judge at least partly video in one section of video to be measured whether with it is described
One section of template video repeats；Otherwise, it is determined that one section of video to be measured does not repeat completely with the target template video, and no longer
Judge whether at least partly video in one section of video to be measured repeats with one section of template video；
Determining the target mould corresponding with one kind template characteristic vector of at least partly video in one section of video to be measured
Before plate video repeats, the method also includes:
When the vector distance between the target feature vector and a kind of template characteristic vector of one section of video to be measured is less than
Or when being equal to the second default vector distance, by each of one section of video to be measured picture to be measured and the target template
Each target template picture in video is successively matched；
The vector distance when between the target feature vector and a kind of template characteristic vector of one section of video to be measured is less than
Or when being equal to the second default vector distance, at least partly video and class template spy in one section of video to be measured are determined
The corresponding target template video of vector is levied to repeat；Otherwise, it is determined that one section of video to be measured and the target template video are complete
It does not repeat, comprising:
When the vector distance between the target feature vector and a kind of template characteristic vector of one section of video to be measured is less than or waits
Vector between the second default vector distance, the target feature vector of one section of video to be measured and one kind template characteristic vector
Distance closest to the described second default vector distance and in one section of video to be measured with the target in the target template video
When the number for the picture to be measured that template picture matches is higher than preset number, determine in one section of video to be measured at least partly
Video and the target template video repeat；Otherwise, it is determined that at least partly video and the mesh in one section of video to be measured
Mark template video does not repeat completely；
The method also includes:
After determining that at least partly video in one section of video to be measured does not repeat completely with the target template video, successively
Finding in multiclass template characteristic vector, the vector distance between the target feature vector of one section of video to be measured is closest
Other class template feature vectors of the second default vector distance；
Judge the target in one section of video to be measured in target template video corresponding with other described class template feature vectors
Whether the number for the picture to be measured that template picture matches is higher than the preset number, and circuits sequentially, until described one section to
Survey that the Target Photo in video in target template video corresponding with other described class template feature vectors matches to mapping
The number of piece is higher than in every section of video to be measured in the preset number or multistage video to be measured and other described class template features
The number for the picture to be measured that target template picture in the corresponding target template video of vector matches is below the present count
Mesh.
2. the method according to claim 1, wherein in the feature vector for obtaining the Target Photo, and by institute
Before the feature vector of Target Photo is stated as the template characteristic vector of template video described in every section, the method also includes:
The Target Photo is subjected to DCT conversion, obtains the lateral coefficient and longitudinal coefficient of pixel coordinate after DCT conversion；With
And
The feature vector for obtaining the Target Photo, and using the feature vector of the Target Photo as template described in every section
The template characteristic vector of video, comprising:
The preceding Q2 potential coefficient in the preceding Q1 potential coefficient and longitudinal coefficient in the lateral coefficient is chosen, according to described Q1 first
Coefficient and the preceding Q2 potential coefficient generate the template characteristic vector of every section of template video.
3. method according to claim 1 or 2, which is characterized in that
Added by the pixel value of the target pixel points of the same position in the M in every section of template video template pictures
Power summation, the kth Prototype drawing when M template pictures are synthesized a Target Photo, in the M template pictures
The pixel value of the target pixel points of piece weight α shared in the pixel value of the target pixel points of the Target Photok=γ∧k,
Wherein, γ is the constant less than 1.
4. a kind of judgment means for repeating video characterized by comprising
First obtains module, for obtaining multistage video to be measured from live video stream；
Second obtains module, for obtaining the target feature vector of every section of video to be measured in multistage video to be measured, wherein described
Target feature vector is used for every section of the unique identification video to be measured；
Processing module, for extracting multistage template video from template video library, wherein every section of template in multistage template video
There are M template pictures in video；
Summation module, for by the target pixel points of the same position in the template pictures of the M in every section of template video
Pixel value is weighted summation, the M template pictures is synthesized a Target Photo, wherein every Prototype drawing
The pixel value of the target pixel points of piece sum of shared weight in the pixel value of the target pixel points of the Target Photo be less than or
Equal to 1；
Third obtains module, makees for obtaining the feature vector of the Target Photo, and by the feature vector of the Target Photo
For the template characteristic vector of template video described in every section；
Computing module, for calculating the target feature vector of every section of video to be measured and the template spy of every section of template video
Levy the vector distance between vector；
Determination module, for working as between the target feature vector of one section of video to be measured and the template characteristic vector of one section of template video
Vector distance when being less than or equal to the first default vector distance, determine at least partly video in one section of video to be measured with
One section of template video repeats；Otherwise, it is determined that one section of video to be measured does not repeat completely with one section of template video；
Described device further include:
Cluster module, for the template in the target feature vector and every section of template video for calculating every section of video to be measured
Before vector distance between feature vector, the template characteristic vector of template video described in multistage is clustered, it is more to obtain
Class template feature vector；
The determination module includes:
Decision sub-module, for determining at least partly video and one section of template video weight in one section of video to be measured
It is multiple；Otherwise, it is determined that before one section of video to be measured and one section of template video do not repeat completely, when one section of view to be measured
When vector distance between the target feature vector of frequency and a kind of template characteristic vector is less than or equal to the second default vector distance,
Determine at least partly video target template video corresponding with one kind template characteristic vector in one section of video to be measured
It repeats, and starts to judge whether at least partly video in one section of video to be measured repeats with one section of template video；It is no
Then, determine that one section of video to be measured does not repeat completely with the target template video, and no longer judge in one section of video to be measured
At least partly video whether with one section of template video repeat；
Described device further include:
Matching module, for determining at least partly video and a kind of template characteristic vector in one section of video to be measured
Target feature vector and a kind of template characteristic before corresponding target template video repeats, when one section of video to be measured
When vector distance between vector is less than or equal to the second default vector distance, by each of described one section of video to be measured
Picture to be measured is successively matched with each target template picture in the target template video；
The decision sub-module is also used to:
When the vector distance between the target feature vector and a kind of template characteristic vector of one section of video to be measured is less than or waits
Vector between the second default vector distance, the target feature vector of one section of video to be measured and a kind of template characteristic vector
Distance closest to the described second default vector distance and in one section of video to be measured with the target in the target template video
When the number for the picture to be measured that template picture matches is higher than preset number, determine in one section of video to be measured at least partly
Video and the target template video repeat；Otherwise, it is determined that at least partly video and the mesh in one section of video to be measured
Mark template video does not repeat completely；
Described device further include:
Module is found, for determining that at least partly video in one section of video to be measured and the target template video are complete
After not repeating, the arrow between the target feature vector of one section of video to be measured is successively being found in multiclass template characteristic vector
Span is from other class template feature vectors closest to the described second default vector distance；
Judgment module, for judging target template corresponding with other described class template feature vectors in one section of video to be measured
Whether the number for the picture to be measured that the target template picture in video matches is higher than the preset number, and circuits sequentially, directly
Target Photo phase into one section of video to be measured in target template video corresponding with other described class template feature vectors
The number of matched picture to be measured be higher than in every section of video to be measured in the preset number or multistage video to be measured with it is described its
The number for the picture to be measured that target template picture in the corresponding target template video of his class template feature vector matches is low
In the preset number.
5. device according to claim 4, which is characterized in that described device further include:
Conversion module, in the feature vector for obtaining the Target Photo, and using the feature vector of the Target Photo as
Before the template characteristic vector of every section of template video, the Target Photo is subjected to DCT conversion, obtains DCT conversion after image
The lateral coefficient of vegetarian refreshments coordinate and longitudinal coefficient；
The third obtains module
Submodule is generated, for choosing preceding Q2 systems in preceding Q1 potential coefficient and longitudinal coefficient in the lateral coefficient
Number, the template characteristic vector of every section of template video is generated according to the preceding Q1 potential coefficient and the preceding Q2 potential coefficient.
6. device according to claim 4 or 5, which is characterized in that
Added by the pixel value of the target pixel points of the same position in the M in every section of template video template pictures
Power summation, the kth Prototype drawing when M template pictures are synthesized a Target Photo, in the M template pictures
The pixel value of the target pixel points of piece weight α shared in the pixel value of the target pixel points of the Target Photok=γ∧k,
Wherein, γ is the constant less than 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510438517.3A CN106375781B (en) | 2015-07-23 | 2015-07-23 | A kind of judgment method and device repeating video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510438517.3A CN106375781B (en) | 2015-07-23 | 2015-07-23 | A kind of judgment method and device repeating video |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106375781A CN106375781A (en) | 2017-02-01 |
| CN106375781B true CN106375781B (en) | 2019-09-13 |
Family
ID=57880180
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510438517.3A Expired - Fee Related CN106375781B (en) | 2015-07-23 | 2015-07-23 | A kind of judgment method and device repeating video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106375781B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110324660B (en) * | 2018-03-29 | 2021-01-19 | 北京字节跳动网络技术有限公司 | Method and device for judging repeated video |
| CN108959492A (en) * | 2018-06-25 | 2018-12-07 | 江苏大学 | A kind of nearly repetition video detecting method based on Teoplitz core offset minimum binary |
| CN109934142B (en) * | 2019-03-04 | 2021-07-06 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating feature vectors of video |
| CN110413603B (en) * | 2019-08-06 | 2023-02-24 | 北京字节跳动网络技术有限公司 | Method and device for determining repeated data, electronic equipment and computer storage medium |
| CN111426693A (en) * | 2020-04-26 | 2020-07-17 | 湖南恒岳重钢钢结构工程有限公司 | Quality defect detection system and detection method thereof |
| CN114422841B (en) * | 2021-12-17 | 2024-01-02 | 北京达佳互联信息技术有限公司 | Subtitle generation method and device, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1938714A (en) * | 2004-03-23 | 2007-03-28 | 英国电讯有限公司 | Method and system for semantically segmenting scenes of a video sequence |
| CN101359368A (en) * | 2008-09-09 | 2009-02-04 | 华为技术有限公司 | Video image clustering method and system |
| CN101833650A (en) * | 2009-03-13 | 2010-09-15 | 清华大学 | Video copy detection method based on contents |
| CN101853377A (en) * | 2010-05-13 | 2010-10-06 | 复旦大学 | Method for identifying content of digital video |
| CN101976258A (en) * | 2010-11-03 | 2011-02-16 | 上海交通大学 | Video semantic extraction method by combining object segmentation and feature weighing |
| CN102693299A (en) * | 2012-05-17 | 2012-09-26 | 西安交通大学 | System and method for parallel video copy detection |
| CN103593464A (en) * | 2013-11-25 | 2014-02-19 | 华中科技大学 | Video fingerprint detecting and video sequence matching method and system based on visual features |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8063295B2 (en) * | 2002-10-03 | 2011-11-22 | Polyphonic Human Media Interface, S.L. | Method and system for video and film recommendation |
| US8195689B2 (en) * | 2009-06-10 | 2012-06-05 | Zeitera, Llc | Media fingerprinting and identification system |
-
2015
- 2015-07-23 CN CN201510438517.3A patent/CN106375781B/en not_active Expired - Fee Related
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1938714A (en) * | 2004-03-23 | 2007-03-28 | 英国电讯有限公司 | Method and system for semantically segmenting scenes of a video sequence |
| CN101359368A (en) * | 2008-09-09 | 2009-02-04 | 华为技术有限公司 | Video image clustering method and system |
| CN101833650A (en) * | 2009-03-13 | 2010-09-15 | 清华大学 | Video copy detection method based on contents |
| CN101853377A (en) * | 2010-05-13 | 2010-10-06 | 复旦大学 | Method for identifying content of digital video |
| CN101976258A (en) * | 2010-11-03 | 2011-02-16 | 上海交通大学 | Video semantic extraction method by combining object segmentation and feature weighing |
| CN102693299A (en) * | 2012-05-17 | 2012-09-26 | 西安交通大学 | System and method for parallel video copy detection |
| CN103593464A (en) * | 2013-11-25 | 2014-02-19 | 华中科技大学 | Video fingerprint detecting and video sequence matching method and system based on visual features |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106375781A (en) | 2017-02-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106375781B (en) | A kind of judgment method and device repeating video | |
| CN109522843B (en) | Multi-target tracking method, device, equipment and storage medium | |
| CN108898086B (en) | Video image processing method and device, computer readable medium and electronic equipment | |
| CN108090470B (en) | Face alignment method and device | |
| CN108960114A (en) | Human body recognition method and device, computer readable storage medium and electronic equipment | |
| CN108875487B (en) | Training of pedestrian re-recognition network and pedestrian re-recognition based on training | |
| CN105931269A (en) | Tracking method for target in video and tracking device thereof | |
| CN109002784B (en) | Street view identification method and system | |
| CN111814846B (en) | Training method and recognition method of attribute recognition model and related equipment | |
| CN106375849B (en) | A kind of method, apparatus, the update method of video and device generating template | |
| CN115376047A (en) | Shooting identification method, device, equipment and storage medium | |
| CN109961103B (en) | Training method of feature extraction model, and image feature extraction method and device | |
| CN106375850B (en) | A kind of judgment method and device matching video | |
| KR20220130567A (en) | Methods, apparatuses, devices, and storage medium for detecting correlated objects included in an image | |
| US11244154B2 (en) | Target hand tracking method and apparatus, electronic device, and storage medium | |
| JP2016118971A (en) | Image feature amount registration device, method, and program | |
| US20190220670A1 (en) | Moving image processing apparatus, moving image processing method, and computer readable medium | |
| CN111428125B (en) | Ordering method, ordering device, electronic equipment and readable storage medium | |
| CN106354736A (en) | Judgment method and device of repetitive video | |
| Fiaz et al. | PS-ARM: an end-to-end attention-aware relation mixer network for person search | |
| CN105229700B (en) | Device and method for extracting peak figure picture from multiple continuously shot images | |
| CN112488062B (en) | Image identification method, device, equipment and medium | |
| CN114519520A (en) | Model evaluation method, model evaluation device and storage medium | |
| JP4997179B2 (en) | Image processing apparatus, method, and program | |
| CN110188809B (en) | Loop detection method based on image blocking |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A judgment method and device for repeated video Effective date of registration: 20210104 Granted publication date: 20190913 Pledgee: Inner Mongolia Huipu Energy Co.,Ltd. Pledgor: WUXI TVMINING MEDIA SCIENCE & TECHNOLOGY Co.,Ltd. Registration number: Y2020990001517 |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190913 Termination date: 20210723 |