CN106412690A - Determination method and device of video playing - Google Patents
Determination method and device of video playing Download PDFInfo
- Publication number
- CN106412690A CN106412690A CN201510438518.8A CN201510438518A CN106412690A CN 106412690 A CN106412690 A CN 106412690A CN 201510438518 A CN201510438518 A CN 201510438518A CN 106412690 A CN106412690 A CN 106412690A
- Authority
- CN
- China
- Prior art keywords
- vector
- target
- picture
- template
- measured
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 239000013598 vector Substances 0.000 claims abstract description 334
- 238000013139 quantization Methods 0.000 claims description 21
- 238000013507 mapping Methods 0.000 claims description 13
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 9
- 238000004590 computer program Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000004048 modification Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004153 renaturation Methods 0.000 description 1
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 present invention discloses a determination method and device of video playing. The method comprises the steps of extracting the target template pictures of the target videos in a template video base; orderly obtaining the target to-be-measured pictures corresponding to the target template pictures from a real-time video stream according to the time sequence; calculating the vector distances between the first target feature vectors of the target template pictures and the second target feature vectors of the target to-be-measured pictures; when the vector distances are less than or equal to a preset vector distance, determining whether the vector distances between the first target feature vectors of the other target template pictures in the target video and the second target feature vectors of the corresponding other target to-be-measured pictures are all less than the preset vector distance, and determining whether the playing of the target videos in the real-time video stream begins according to a determination result. According to the technical scheme of the present invention, whether the playing of the target videos in the real-time video stream begins can be determined accurately, thereby accurately predicting the videos played in the real-time video stream according to the target videos.
Description
Technical field
The present invention relates to technical field of video processing, particularly to a kind of determination method and device of video playback.
Background technology
At present, in electric program menu (EPG, Electronic Program Guide) processing system,
Need to carry out program real-time estimate to the recent program broadcasting.And predict program video actually to be carried out
Repeatability detection.But the task amount manually carrying out repeatability detection is very big, less efficient, and repeatability inspection
The accuracy rate surveyed and precision all ratios are relatively low, therefore, it is impossible to carry out program real-time estimate exactly, this gives user
Bring very big inconvenience.
Content of the invention
The present invention provides a kind of determination method and device of video playback, in order to the repetition by videos such as programs
Property detection carrying out programming predictions.
The present invention provides a kind of determination method of video playback, including：Extract target video in template video storehouse
Broadcast start time and broadcast start time corresponding To Template picture；
The broadcast start time with To Template picture is obtained sequentially in time successively from live video stream
Time in corresponding target reproduction time section the most forward target picture to be measured；
Calculate the first object characteristic vector and the second of described target picture to be measured of described To Template picture
Vector distance between target feature vector；
When described vector distance is less than or equal to default vector distance, judge successively according to described time sequencing
The first object characteristic vector of other To Template pictures in described target video in preset time period with
Whether the vector distance between the second target feature vector of corresponding other targets picture to be measured is respectively less than institute
State default vector distance, wherein, described preset time period includes described broadcast start time；
According to judged result, determine whether have started in described live video stream play in described template video storehouse
Described target video.
In one embodiment, described according to judged result, determine in described live video stream whether have started to
Play the described target video in described template video storehouse, including：
When described vector distance is less than or equal to described default vector distance, when its in described target video
Second target of the first object characteristic vector of his To Template picture and other targets corresponding picture to be measured
When vector distance between characteristic vector is respectively less than described default vector distance, determine in described live video stream
Have started to play described target video, and send video playback cue；Otherwise, it determines described regard in real time
Frequency does not commence play out described target video in flowing.
In one embodiment, methods described also includes：
When described vector distance is more than described default vector distance, obtain and described mesh from live video stream
Time in the mark adjacent neighbouring reproduction time section of reproduction time section the most forward picture to be measured；
Judge the first object characteristic vector of described To Template picture and the second target of described picture to be measured
Whether the vector distance between characteristic vector is less than or equal to described default vector distance；
When the first object characteristic vector of described To Template picture and the second target of described picture to be measured are special
When levying vector distance between vector and being less than or equal to described default vector distance, continue to judge knot according to described
Really, determine that the described target whether having started in described live video stream play in described template video storehouse regards
Frequently；
When the first object characteristic vector of described To Template picture and the second target of described picture to be measured are special
When levying vector distance between vector and being more than described default vector distance, directly in the described live video stream of determination
Do not commence play out described target video.
In one embodiment, before calculating described vector distance, respectively by described To Template picture
Second target feature vector of first object characteristic vector and described target picture to be measured carries out vector quantization；With
And
The described first object characteristic vector calculating described To Template picture and described target picture to be measured
Vector distance between second target feature vector, including：
After first object characteristic vector according to the described To Template picture after vector quantization and vector quantization
Described target picture to be measured second target feature vector calculate described To Template picture first object
Vector distance between second target feature vector of characteristic vector and described target picture to be measured.
In one embodiment, the described first object characteristic vector calculating described To Template picture, including：
Obtain the overall rectangular histogram of described To Template picture；
Described To Template picture is divided into M image block；
Obtain the local histogram of each the described image block in M described image block；
Determine the of described To Template picture according to described overall rectangular histogram and M described local histogram
One target feature vector.
The present invention also provides a kind of determination device of video playback, including：Extraction module, for extracting template
The broadcast start time of target video and broadcast start time corresponding To Template picture in video library；
First acquisition module, for obtaining and To Template figure successively sequentially in time from live video stream
Time in the corresponding target reproduction time section of the broadcast start time of piece the most forward target picture to be measured；
Computing module, the first object characteristic vector for calculating described To Template picture is treated with described target
Vector distance between second target feature vector of mapping piece；
First judge module, for being less than or equal to default vector distance when described vector distance, according to described
Time sequencing judges other To Template pictures in the described target video in preset time period successively
Arrow between first object characteristic vector and the second target feature vector of other targets corresponding picture to be measured
Span is respectively less than described default vector distance from whether, and wherein, described preset time period includes described starting to broadcast
Put the time；
Determining module, for according to judged result, determining whether have started in described live video stream play institute
State the described target video in template video storehouse.
In one embodiment, described determining module includes：
First determination sub-module, for described vector distance be less than or equal to described default vector distance when,
First object characteristic vector and other mesh corresponding when other To Template pictures in described target video
When marking vector distance between the second target feature vector of picture to be measured and being respectively less than described default vector distance,
Determine and have started in described live video stream play described target video, and send video playback cue；
Otherwise, it determines not commencing play out described target video in described live video stream.
In one embodiment, described device also includes：
Second acquisition module, for when described vector distance is more than described default vector distance, regarding from real time
The time that frequency obtains in the neighbouring reproduction time section adjacent with described target reproduction time section in flowing is the most forward
Picture to be measured；
Second judge module, the first object characteristic vector for judging described To Template picture is treated with described
Vector distance between second target feature vector of mapping piece whether less than or equal to described default vector away from
From；
Described determining module also includes：
Second determination sub-module, for treating with described when the first object characteristic vector of described To Template picture
When vector distance between second target feature vector of mapping piece is less than or equal to described default vector distance,
Continue according to described judged result, determine whether have started in described live video stream play described template video
Described target video in storehouse；
3rd determination sub-module, for treating with described when the first object characteristic vector of described To Template picture
When vector distance between second target feature vector of mapping piece is more than described default vector distance, directly really
Described target video is not commenced play out in fixed described live video stream.
In one embodiment, described device also includes：
Vector Quantization Module, for before calculating described vector distance, respectively by described To Template picture
First object characteristic vector and the second target feature vector of described target picture to be measured carry out vector quantization；
And
Described computing module includes：
Calculating sub module, for the first object feature according to the described To Template picture after vector quantization to
Second target feature vector of the described target picture to be measured after amount and vector quantization calculates described To Template
Arrow between second target feature vector of the first object characteristic vector of picture and described target picture to be measured
Span from.
In one embodiment, described computing module also includes：
First acquisition submodule, for obtaining the overall rectangular histogram of described To Template picture；
Divide submodule, for described To Template picture is divided into M image block；
Second acquisition submodule, for obtaining the local of each the described image block in M described image block
Rectangular histogram；
4th determination sub-module, for determining according to described overall rectangular histogram and M described local histogram
The first object characteristic vector of described To Template picture.
The technical scheme that embodiment of the disclosure provides can include following beneficial effect：
By the first object feature of each To Template picture of target video in calculation template video library to
Amount and corresponding live video stream in the second target feature vector of target picture to be measured between vector away from
From the target picture to be measured that specifically can be accurately determined according to vector distance in live video stream is regarded with target
In frequency, whether corresponding To Template picture all mates, so accurate determine in live video stream whether
Start broadcasting this target video, thus realizing carrying out standard according to this target video to the video play in live video stream
Really predict.
Other features and advantages of the present invention will illustrate in the following description, and, partly from explanation
Become apparent in book, or understood by implementing the present invention.The purpose of the present invention and other advantages can
Realized by specifically noted structure in the description write, claims and accompanying drawing and obtain
?.
Below by drawings and Examples, technical scheme is described in further detail.
Brief description
Accompanying drawing is used for providing a further understanding of the present invention, and constitutes a part for description, with this
Bright embodiment is used for explaining the present invention together, is not construed as limiting the invention.In the accompanying drawings：
Fig. 1 is a kind of flow chart of the determination method of the video playback according to an exemplary embodiment.
Fig. 2 is the flow chart of the determination method of another kind of video playback according to an exemplary embodiment.
Fig. 3 is the flow chart of the determination method of another video playback according to an exemplary embodiment.
Fig. 4 is a kind of block diagram of the determination device of the video playback according to an exemplary embodiment.
Fig. 5 is the block diagram of the determination device of another kind of video playback according to an exemplary embodiment.
Fig. 6 is the block diagram of the determination device of another video playback according to an exemplary embodiment.
Fig. 7 is the block diagram of the determination device of another video playback according to an exemplary embodiment.
Fig. 8 is the block diagram of the determination device of another video playback according to an exemplary embodiment.
Specific embodiment
Below in conjunction with accompanying drawing, the preferred embodiments of the present invention are illustrated it will be appreciated that described herein
Preferred embodiment is merely to illustrate and explains the present invention, is not intended to limit the present invention.
In correlation technique, in electric program menu (EPG, Electronic Program Guide) processing system
In system, need to carry out program real-time estimate to the recent program broadcasting.And predict that program actually will enter
The repeatability detection of row video.But the task amount manually carrying out repeatability detection is very big, less efficient, and weight
The accuracy rate of renaturation detection and precision all ratios are relatively low, therefore, it is impossible to carry out program real-time estimate exactly, this
Bring very big inconvenience to user.
In order to solve above-mentioned technical problem, the embodiment of the present disclosure provides a kind of determination method of video playback,
The method is be applied to the determination program of video playback, system or device, as shown in figure 1, step S101,
Extract the broadcast start time of target video and the corresponding To Template of broadcast start time in template video storehouse
Picture；Wherein, template video storehouse can in be stored with derive in EPG system close on the time (for example,
The moment that certain of yesterday and the day before yesterday is almost fixed) the different programs that broadcast of same time of occurring are (perhaps
Different collection numbers, the not same period), and target video is exactly a certain in the broadcast of same time in template video storehouse
Whether the program head of individual program or some program, play for the same time in detection live video stream again
This program, thus realize video repeatability detection and programming predictions exactly.Certainly, entering in the present invention
It is only limited to identical video content detection during row video repeatability detection (i.e. matching detection), be not related to
To the deformation of picture, change of color etc..Wherein, To Template picture is the first frame in target video
Target camera lens.
Step S102, sequentially in time successively from live video stream obtain with To Template picture from the beginning of
Time in the corresponding target reproduction time section of reproduction time the most forward target picture to be measured；Getting
After the first frame target camera lens in target video, can obtain in live video stream sequentially in time and be somebody's turn to do
Corresponding the first frame camera lens to be measured of To Template picture, and the broadcast of program generally also has time error, because
This, this first frame picture to be measured is the target reproduction time section corresponding with broadcast start time t1【T1,
T2】The most forward target picture to be measured of interior time, wherein, T1<t1<T2.
Step S103, calculates the first object characteristic vector of described To Template picture and described target treats mapping
Vector distance between second target feature vector of piece；First object characteristic vector is used for this mesh of unique mark
Mark template picture, the fingerprint for this To Template picture is video finger print；Second target feature vector
For this target of unique mark picture to be measured, the fingerprint for this target picture to be measured is video finger print.
Wherein, vector distance is less, illustrates that the first object characteristic vector of this To Template picture is to be measured with this target
The matching degree of the second target feature vector of picture is higher, further relates to this To Template picture and treats with this target
The similarity of mapping piece is higher.
Step S104, when described vector distance is less than or equal to default vector distance, according to described time sequencing
Judge the first object of other To Template pictures in the described target video in preset time period successively
Vector distance between characteristic vector and the second target feature vector of other targets corresponding picture to be measured is
No respectively less than described default vector distance, wherein, described preset time period includes described broadcast start time；
To be measured with the first frame in the first object characteristic vector of the first frame target camera lens (i.e. above-mentioned To Template picture)
The vector distance of the second target feature vector of camera lens (i.e. above-mentioned target to be measured picture) is less than this default vector
Apart from when, illustrate that this first frame target camera lens is matched with this first frame camera lens to be measured, then can be according to the time
Order successively calculate preset time period in the first object characteristic vector of other template picture with corresponding its
Whether the vector distance between the second target feature vector of his target picture to be measured is respectively less than this default vector
Distance, if being respectively less than this default vector distance, illustrates other template picture in preset time period and other mesh
Mark picture to be measured all to mate, wherein, preset time period is the time corresponding to broadcast time section of target video
Section.
Step S105, according to judged result, determines whether have started in described live video stream play described mould
Described target video in plate video library.According to above-mentioned judged result it may be determined that in this preset time period
Live video stream have started to play this target video, thus realize carried out programming predictions exactly.
Certainly, if target video is the program or this program broadcasting in the same time period in recent EPG
Program head, and live video stream be in EPG today broadcast program, then pass through such scheme, this
Invention just completes real-time estimate to EPG program, meanwhile, when judging certain that obtain sequentially in time
Second target feature vector of individual or some target picture to be measured and the corresponding mesh obtaining from target video
The vector distance of the first object characteristic vector of mark template picture is incomplete one more than this default vector distance
During one coupling, illustrate not play this target video, and broadcast is other new programs, can also pass through
Using this other new program, template video storehouse is updated completing the correction to EPG, for example：Make
Replace this target program in this target program and history EPG in this template video storehouse with this new program,
And the various information such as program category, name, reproduction time, broadcast station is marked on new program, from
And not only realize the renewal to template video storehouse, also complete the correction to the program in EPG system, make
Up-to-date program is always according to the program in EPG system.
In one embodiment, above-mentioned steps S105 can be performed as：
When described vector distance is less than or equal to described default vector distance, when its in described target video
Second target of the first object characteristic vector of his To Template picture and other targets corresponding picture to be measured
When vector distance between characteristic vector is respectively less than described default vector distance, determine in described live video stream
Have started to play described target video, and send video playback cue；Otherwise, it determines described regard in real time
Frequency does not commence play out described target video in flowing.
The first object of the first frame target camera lens (i.e. above-mentioned To Template picture) in preset time period is special
Levy the vector of vector and the second target feature vector of the first frame camera lens to be measured (i.e. above-mentioned target to be measured picture)
When distance is less than this default vector distance, if the first object feature of other template picture in preset time period
Vector distance between second target feature vector of vectorial and corresponding other targets picture to be measured is also all little
In this default vector distance, then all To Template pictures in explanation preset time period are to be measured with all targets
Picture all mates, and then can determine that live video stream has started to play this target video within this time,
Thus realize having carried out programming predictions exactly, at this point it is possible to prompting user is so that user can see in time
See this program；Certainly, when the second target characteristic that there is other targets picture to be measured in judgement preset time period
Vector distance between vector and the first object characteristic vector of other To Template pictures is more than default vector
Apart from when, then can determine that live video stream does not commence play out this target video within this time, also mean
The video broadcasting in this time in this live video stream is new video, rather than target video, then may be used
To be updated to this template video storehouse using this new video, simultaneously without prompting this target video of user
Corresponding program broadcasts in the same time again.
As shown in Fig. 2 in one embodiment, method may also include：
Step S201, when described vector distance is more than described default vector distance, obtains from live video stream
Take the picture to be measured that the time in the neighbouring reproduction time section adjacent with described target reproduction time section is the most forward；
To be measured with the first frame in the first object characteristic vector of the first frame target camera lens (i.e. above-mentioned To Template picture)
The vector distance of the second target feature vector of camera lens (i.e. above-mentioned target to be measured picture) is more than this default vector
Apart from when, illustrate that this first frame target camera lens and this first frame camera lens to be measured mismatch, namely this first frame treated
Surveying camera lens is not first camera lens corresponding with this first frame target camera lens it is likely that being because target
Caused by the broadcast time error of video, then can broadcast with target reproduction time section [T1, T2] adjacent closing on
Put in the time that again to find first camera lens corresponding with this first frame target camera lens be that the time is the most forward
Picture to be measured, in order to accurately judge whether further to have play target video in the same time, certainly, should
Neighbouring reproduction time section be closest to this target reproduction time section time period such as：[T-1, T1] or [T2, T3],
So searching number of times can be reduced, and then reduce matching times.
Step S202, judges the first object characteristic vector of described To Template picture and described picture to be measured
Whether the vector distance between the second target feature vector is less than or equal to described default vector distance；First
The first frame camera lens to be measured that the first object characteristic vector of frame target camera lens is determined with new (i.e. above-mentioned treats mapping
Piece) the vector distance of the second target feature vector when being less than or equal to this default vector distance, illustrate this
One frame target camera lens is matched with this first frame camera lens to be measured, then can calculate default sequentially in time successively
The first object characteristic vector of other template picture in the time period and other targets corresponding picture to be measured
Whether the vector distance between the second target feature vector is respectively less than this default vector distance, if it is pre- to be respectively less than this
If vector distance, illustrate that the picture to be measured with other targets of other template picture in preset time period all mates.
Step S203, when the of first object characteristic vector and the described picture to be measured of described To Template picture
When vector distance between two target feature vectors is less than or equal to described default vector distance, continue according to institute
State judged result, determine whether have started in described live video stream to play described in described template video storehouse
Target video；
Step S204, when the of first object characteristic vector and the described picture to be measured of described To Template picture
When vector distance between two target feature vectors is more than described default vector distance, directly determine described real-time
Described target video is not commenced play out in video flowing.
In first object characteristic vector and new the first frame camera lens to be measured determining of the first frame target camera lens the
When the vector distance of two target feature vectors is less than or equal to this default vector distance, if in preset time period
The first object characteristic vector of other template picture is special with the second target of other targets corresponding picture to be measured
Levy the vector distance between vector and be also respectively less than this default vector distance, then all in explanation preset time period
To Template picture picture to be measured with all targets all mates, and then can determine and regard in real time within this time
Frequency stream has started to play this target video；When the first object characteristic vector of To Template picture is new with corresponding
When vector distance between the second target feature vector of picture to be measured determining is more than this default vector distance,
To Template picture caused by explanation is not broadcast time error is mismatched with picture to be measured, but regards in real time
Frequency does not commence play out this target video in flowing, then can directly determine in this live video stream in preset time period
Inside do not commence play out this target video, and broadcast other programs.
In one embodiment, before calculating described vector distance, respectively by described To Template picture
Second target feature vector of first object characteristic vector and described target picture to be measured carries out vector quantization；With
And
Above-mentioned steps S103 can be performed as：
After first object characteristic vector according to the described To Template picture after vector quantization and vector quantization
Described target picture to be measured second target feature vector calculate described To Template picture first object
Vector distance between second target feature vector of characteristic vector and described target picture to be measured.
Because the vectorial digit in the first object characteristic vector of To Template picture may be M, and mesh
It may be N number of for marking the vectorial digit in the second target feature vector of picture to be measured, and M and N is probably
Unequal, thus directly calculate the different first object characteristic vector of vectorial digit and the second target spy
Levy the computation burden that the vector distance between vector can increase system, slow down the computation rate of vector distance, no
Method guarantees to calculate the real-time of vector distance, therefore, by the first object characteristic vector of To Template picture
Carry out vector quantization with the second target feature vector of target picture to be measured, each To Template picture can be made
First object characteristic vector and corresponding target picture to be measured the second target feature vector in digit order number
Number is equal, and this will be effectively reduced the burden calculating vector distance in system, accelerates the calculating of vector distance
Speed, thus farthest guaranteeing to calculate the real-time of vector distance, and then increase judges that each target is treated
The speed whether mated of mapping piece and corresponding To Template picture.
As shown in figure 3, in one embodiment, above-mentioned steps S103 can be performed as：
Step A1, obtains the overall rectangular histogram of described To Template picture；
Step A2, described To Template picture is divided into M image block；
Step A3, obtains the local histogram of each the described image block in M described image block；
Step A4, determines described To Template according to described overall rectangular histogram and M described local histogram
The first object characteristic vector of picture.
In order to the first object characteristic vector of each To Template picture more can be accurately acquired, can obtain
The overall rectangular histogram of this To Template picture, to obtain the global characteristics of this To Template picture, should simultaneously
To Template picture is divided into the region of M, with obtain each region image block local histogram thus
Get the local feature of each image block, and finally obtained using this global characteristics and M local feature
The first object characteristic vector of this higher To Template picture of accuracy；Certainly, treat in every target of acquisition
During the second target feature vector of mapping piece, it is possible to use the program, this is conducive to raising video frequency program pre-
The precision surveyed, wherein, M is preferably 4.
As shown in figure 4, the present invention also provides a kind of determination device of video playback, including：Extraction module 401,
For extracting the broadcast start time of target video and the corresponding target of broadcast start time in template video storehouse
Template picture；
First acquisition module 402, for obtaining and target mould successively sequentially in time from live video stream
Time in the corresponding target reproduction time section of the broadcast start time of plate picture the most forward target is to be measured
Picture；
Computing module 403, for calculating the first object characteristic vector of described To Template picture and described mesh
Mark the vector distance between the second target feature vector of picture to be measured；
First judge module 404, for being less than or equal to default vector distance when described vector distance, according to
Described time sequencing judges other To Template figures in the described target video in preset time period successively
Between the first object characteristic vector of piece and the second target feature vector of other targets corresponding picture to be measured
Vector distance whether be respectively less than described default vector distance, wherein, described preset time period include described in open
Beginning reproduction time；
Determining module 405, for according to judged result, determining whether have started in described live video stream broadcast
Put the described target video in described template video storehouse.
As shown in figure 5, in one embodiment, described determining module 405 includes：
First determination sub-module 4051, for being less than or equal to described default vector distance in described vector distance
When, when other To Template pictures in described target video first object characteristic vector with corresponding other
Vector distance between second target feature vector of target picture to be measured is respectively less than described default vector distance
When, determine and have started in described live video stream play described target video, and send video playback prompting letter
Number；Otherwise, it determines not commencing play out described target video in described live video stream.
As shown in fig. 6, in one embodiment, described device also includes：
Second acquisition module 601, for when described vector distance is more than described default vector distance, from reality
When video flowing in time of obtaining in the neighbouring reproduction time section adjacent with described target reproduction time section lean on most
Front picture to be measured；
Second judge module 602, for judging first object characteristic vector and the institute of described To Template picture
State whether the vector distance between the second target feature vector of picture to be measured is less than or equal to described default arrow
Span from；
Described determining module 405 also includes：
Second determination sub-module 4052, for when the first object characteristic vector of described To Template picture and institute
State vector distance between the second target feature vector of picture to be measured be less than or equal to described default vector away from
From when, continue according to described judged result, determine whether have started in described live video stream play described mould
Described target video in plate video library；
3rd determination sub-module 4053, for when the first object characteristic vector of described To Template picture and institute
When stating vector distance between the second target feature vector of picture to be measured and being more than described default vector distance, directly
Connect in the described live video stream of determination and do not commence play out described target video.
As shown in fig. 7, in one embodiment, described device also includes：
Vector Quantization Module 701, for before calculating described vector distance, respectively by described To Template
Second target feature vector of the first object characteristic vector of picture and described target picture to be measured carries out vector
Quantify；And
Described computing module 403 includes：
Calculating sub module 4031, special for the first object according to the described To Template picture after vector quantization
The second target feature vector levying the described target picture to be measured after vector sum vector quantization calculates described target
Between second target feature vector of the first object characteristic vector of template picture and described target picture to be measured
Vector distance.
As shown in figure 8, in one embodiment, described computing module 403 also includes：
First acquisition submodule 4032, for obtaining the overall rectangular histogram of described To Template picture；
Divide submodule 4033, for described To Template picture is divided into M image block；
Second acquisition submodule 4034, for obtaining each described image block in M described image block
Local histogram；
4th determination sub-module 4035, for according to described overall rectangular histogram and M described local histogram
Determine the first object characteristic vector of described To Template picture.
With regard to the device in above-described embodiment, wherein the concrete mode of modules execution operation is relevant
It has been described in detail in the embodiment of the method, explanation will be not set forth in detail herein.
Finally, the determination device of the video playback in the present invention is applied to terminal unit.For example, it may be moving
Mobile phone, computer, digital broadcast terminal, messaging devices, game console, tablet device, doctor
Treatment equipment, body-building equipment, personal digital assistant etc..
Those skilled in the art are it should be appreciated that embodiments of the invention can be provided as method, system or meter
Calculation machine program product.Therefore, the present invention can be using complete hardware embodiment, complete software embodiment or knot
Close the form of the embodiment of software and hardware aspect.And, the present invention can adopt and wherein wrap one or more
Computer-usable storage medium containing computer usable program code (including but not limited to disk memory and
Optical memory etc.) the upper computer program implemented form.
The present invention is to produce with reference to method according to embodiments of the present invention, equipment (system) and computer program
The flow chart of product and/or block diagram are describing.It should be understood that can by computer program instructions flowchart and
/ or block diagram in each flow process and/or the flow process in square frame and flow chart and/or block diagram and/
Or the combination of square frame.These computer program instructions can be provided to general purpose computer, special-purpose computer, embed
The processor of formula datatron or other programmable data processing device is to produce a machine so that passing through to calculate
The instruction of the computing device of machine or other programmable data processing device produces for realizing in flow chart one
The device of the function of specifying in individual flow process or multiple flow process and/or one square frame of block diagram or multiple square frame.
These computer program instructions may be alternatively stored in and computer or other programmable datas can be guided to process and set
So that being stored in this computer-readable memory in the standby computer-readable memory working in a specific way
Instruction produce and include the manufacture of command device, the realization of this command device is in one flow process or multiple of flow chart
The function of specifying in flow process and/or one square frame of block diagram or multiple square frame.
These computer program instructions also can be loaded in computer or other programmable data processing device, makes
Obtain and series of operation steps is executed on computer or other programmable devices to produce computer implemented place
Reason, thus the instruction of execution is provided for realizing in flow chart one on computer or other programmable devices
The step of the function of specifying in flow process or multiple flow process and/or one square frame of block diagram or multiple square frame.
Obviously, those skilled in the art can carry out various changes and modification without deviating from this to the present invention
Bright spirit and scope.So, if the present invention these modification and modification belong to the claims in the present invention and
Within the scope of its equivalent technologies, then the present invention is also intended to comprise these changes and modification.
Claims (10)
1. a kind of determination method of video playback is it is characterised in that include：
Extract the broadcast start time of target video and the corresponding target of broadcast start time in template video storehouse
Template picture；
The broadcast start time with To Template picture is obtained sequentially in time successively from live video stream
Time in corresponding target reproduction time section the most forward target picture to be measured；
Calculate the first object characteristic vector and the second of described target picture to be measured of described To Template picture
Vector distance between target feature vector；
When described vector distance is less than or equal to default vector distance, judge successively according to described time sequencing
The first object characteristic vector of other To Template pictures in described target video in preset time period with
Whether the vector distance between the second target feature vector of corresponding other targets picture to be measured is respectively less than institute
State default vector distance, wherein, described preset time period includes described broadcast start time；
According to judged result, determine whether have started in described live video stream play in described template video storehouse
Described target video.
2. method described in 1 is wanted according to right it is characterised in that
Described according to judged result, determine whether have started in described live video stream play described template video
Described target video in storehouse, including：
When described vector distance is less than or equal to described default vector distance, when its in described target video
Second target of the first object characteristic vector of his To Template picture and other targets corresponding picture to be measured
When vector distance between characteristic vector is respectively less than described default vector distance, determine in described live video stream
Have started to play described target video, and send video playback cue；Otherwise, it determines described regard in real time
Frequency does not commence play out described target video in flowing.
3. the method described in 1 is wanted it is characterised in that methods described also includes according to right：
When described vector distance is more than described default vector distance, obtain and described mesh from live video stream
Time in the mark adjacent neighbouring reproduction time section of reproduction time section the most forward picture to be measured；
Judge the first object characteristic vector of described To Template picture and the second target of described picture to be measured
Whether the vector distance between characteristic vector is less than or equal to described default vector distance；
When the first object characteristic vector of described To Template picture and the second target of described picture to be measured are special
When levying vector distance between vector and being less than or equal to described default vector distance, continue to judge knot according to described
Really, determine that the described target whether having started in described live video stream play in described template video storehouse regards
Frequently；
When the first object characteristic vector of described To Template picture and the second target of described picture to be measured are special
When levying vector distance between vector and being more than described default vector distance, directly in the described live video stream of determination
Do not commence play out described target video.
4. method described in 1 is wanted according to right it is characterised in that
Before calculating described vector distance, respectively by the first object characteristic vector of described To Template picture
Carry out vector quantization with the second target feature vector of described target picture to be measured；And
The described first object characteristic vector calculating described To Template picture and described target picture to be measured
Vector distance between second target feature vector, including：
After first object characteristic vector according to the described To Template picture after vector quantization and vector quantization
Described target picture to be measured second target feature vector calculate described To Template picture first object
Vector distance between second target feature vector of characteristic vector and described target picture to be measured.
5. method any one of 1 to 4 is wanted according to right it is characterised in that
The described first object characteristic vector calculating described To Template picture, including：
Obtain the overall rectangular histogram of described To Template picture；
Described To Template picture is divided into M image block；
Obtain the local histogram of each the described image block in M described image block；
Determine the of described To Template picture according to described overall rectangular histogram and M described local histogram
One target feature vector.
6. a kind of determination device of video playback is it is characterised in that include：
Extraction module, during for extracting in template video storehouse the broadcast start time of target video and commence play out
Between corresponding To Template picture；
First acquisition module, for obtaining and To Template figure successively sequentially in time from live video stream
Time in the corresponding target reproduction time section of the broadcast start time of piece the most forward target picture to be measured；
Computing module, the first object characteristic vector for calculating described To Template picture is treated with described target
Vector distance between second target feature vector of mapping piece；
First judge module, for being less than or equal to default vector distance when described vector distance, according to described
Time sequencing judges other To Template pictures in the described target video in preset time period successively
Arrow between first object characteristic vector and the second target feature vector of other targets corresponding picture to be measured
Span is respectively less than described default vector distance from whether, and wherein, described preset time period includes described starting to broadcast
Put the time；
Determining module, for according to judged result, determining whether have started in described live video stream play institute
State the described target video in template video storehouse.
7. device described in 6 is wanted according to right it is characterised in that
Described determining module includes：
First determination sub-module, for described vector distance be less than or equal to described default vector distance when,
First object characteristic vector and other mesh corresponding when other To Template pictures in described target video
When marking vector distance between the second target feature vector of picture to be measured and being respectively less than described default vector distance,
Determine and have started in described live video stream play described target video, and send video playback cue；
Otherwise, it determines not commencing play out described target video in described live video stream.
8. the device described in 6 is wanted it is characterised in that described device also includes according to right：
Second acquisition module, for when described vector distance is more than described default vector distance, regarding from real time
The time that frequency obtains in the neighbouring reproduction time section adjacent with described target reproduction time section in flowing is the most forward
Picture to be measured；
Second judge module, the first object characteristic vector for judging described To Template picture is treated with described
Vector distance between second target feature vector of mapping piece whether less than or equal to described default vector away from
From；
Described determining module also includes：
Second determination sub-module, for treating with described when the first object characteristic vector of described To Template picture
When vector distance between second target feature vector of mapping piece is less than or equal to described default vector distance,
Continue according to described judged result, determine whether have started in described live video stream play described template video
Described target video in storehouse；
3rd determination sub-module, for treating with described when the first object characteristic vector of described To Template picture
When vector distance between second target feature vector of mapping piece is more than described default vector distance, directly really
Described target video is not commenced play out in fixed described live video stream.
9. the device described in 6 is wanted it is characterised in that described device also includes according to right：
Vector Quantization Module, for before calculating described vector distance, respectively by described To Template picture
First object characteristic vector and the second target feature vector of described target picture to be measured carry out vector quantization；
And
Described computing module includes：
Calculating sub module, for the first object feature according to the described To Template picture after vector quantization to
Second target feature vector of the described target picture to be measured after amount and vector quantization calculates described To Template
Arrow between second target feature vector of the first object characteristic vector of picture and described target picture to be measured
Span from.
10. device any one of 6 to 9 is wanted according to right it is characterised in that
Described computing module also includes：
First acquisition submodule, for obtaining the overall rectangular histogram of described To Template picture；
Divide submodule, for described To Template picture is divided into M image block；
Second acquisition submodule, for obtaining the local of each the described image block in M described image block
Rectangular histogram；
4th determination sub-module, for determining according to described overall rectangular histogram and M described local histogram
The first object characteristic vector of described To Template picture.
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 true CN106412690A (en) | 2017-02-15 |
| CN106412690B 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) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020135756A1 (en) * | 2018-12-29 | 2020-07-02 | 深圳Tcl新技术有限公司 | Video segment extraction method, apparatus and device, and computer-readable storage medium |
Citations (6)
| 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 |
| 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 |
-
2015
- 2015-07-23 CN CN201510438518.8A patent/CN106412690B/en not_active Expired - Fee Related
Patent Citations (6)
| 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 |
| 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 |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020135756A1 (en) * | 2018-12-29 | 2020-07-02 | 深圳Tcl新技术有限公司 | Video segment extraction method, apparatus and device, and computer-readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106412690B (en) | 2020-01-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108898086A (en) | Method of video image processing and device, computer-readable medium and electronic equipment | |
| CN106375781B (en) | A kind of judgment method and device repeating video | |
| CN104937638A (en) | Systems and methods for tracking and detecting a target object | |
| CN110298220B (en) | Action video live broadcast method, system, electronic equipment and storage medium | |
| CN110086988A (en) | Shooting angle method of adjustment, device, equipment and its storage medium | |
| CN106557759B (en) | Signpost information acquisition method and device | |
| CN105205494B (en) | Similar pictures recognition methods and device | |
| CN109618236A (en) | Video comments treating method and apparatus | |
| CN112115894B (en) | Training method and device of hand key point detection model and electronic equipment | |
| CN109005350A (en) | Image repeats shooting reminding method, device, storage medium and mobile terminal | |
| CN109474850A (en) | Move pixel special video effect adding method, device, terminal device and storage medium | |
| CN112508974B (en) | Training method and device for image segmentation model, electronic equipment and storage medium | |
| CN111401238B (en) | Method and device for detecting character close-up fragments in video | |
| US11244154B2 (en) | Target hand tracking method and apparatus, electronic device, and storage medium | |
| CN109348277A (en) | Move pixel special video effect adding method, device, terminal device and storage medium | |
| 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 | |
| CN112166435A (en) | Target tracking method and device, electronic equipment and storage medium | |
| CN109558505A (en) | Visual search method, apparatus, computer equipment and storage medium | |
| CN106412690A (en) | Determination method and device of video playing | |
| CN106375848A (en) | Video playback prompting method and video playback prompting device | |
| CN117437183A (en) | Training method and device for defect detection model | |
| CN106354736A (en) | Judgment method and device of repetitive video | |
| CN106375850B (en) | A kind of judgment method and device matching video | |
| CN114299427A (en) | Method and device for detecting key points of target object, electronic 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 | ||
| 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 |
|
| 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: 20200110 Termination date: 20210723 |