CN106375848A - Video playback prompting method and video playback prompting device - Google Patents
Video playback prompting method and video playback prompting device Download PDFInfo
- Publication number
- CN106375848A CN106375848A CN201510439978.2A CN201510439978A CN106375848A CN 106375848 A CN106375848 A CN 106375848A CN 201510439978 A CN201510439978 A CN 201510439978A CN 106375848 A CN106375848 A CN 106375848A
- Authority
- CN
- China
- Prior art keywords
- key frame
- template
- frame picture
- measured
- video stream
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 239000013598 vector Substances 0.000 claims abstract description 60
- 230000002123 temporal effect Effects 0.000 claims description 25
- 230000029058 respiratory gaseous exchange Effects 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 2
- 238000001514 detection method Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 10
- 238000004590 computer program 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
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003252 repetitive effect Effects 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 208000031481 Pathologic Constriction Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000694 effects Effects 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
- 210000001215 vagina Anatomy 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
- H04N21/43—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
- H04N21/435—Processing of additional data, e.g. decrypting of additional data, reconstructing software from modules extracted from the transport stream
- H04N21/4351—Processing of additional data, e.g. decrypting of additional data, reconstructing software from modules extracted from the transport stream involving reassembling additional data, e.g. rebuilding an executable program from recovered modules
-
- 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
- H04N21/44012—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 rendering scenes according to scene graphs, e.g. MPEG-4 scene graphs
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
Abstract
The invention discloses a video playback prompting method and a video playback prompting device. The method comprises steps: multiple template key frame images in a template video are extracted; a first target feature vector of each template key frame image is acquired; a to-be-measured key frame picture corresponding to the time information of each template key frame image is acquired from a real-time video stream sequentially according to a time sequence; a second target feature vector of the to-be-measured key frame image is determined; whether each first target feature vector is matched with corresponding each second target feature vector is compared sequentially; whether the to-be-measured key frame picture in the real-time video stream is matched with multiple template key frame images in the template video is determined according to a matching result; and when the to-be-measured key frame picture in the real-time video stream is matched with multiple template key frame images in the template video, the template video in the real-time video stream is prompted to be already played. Through the technical scheme of the invention, the video repetition test and the program prediction can be accurately carried out.
Description
Technical field
The present invention relates to technical field of video processing, particularly to a kind of video playback reminding method and device.
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 video playback reminding method and device, in order to the repeatability by videos such as programs
Detect and to carry out programming predictions.
The present invention provides a kind of video playback reminding method, comprising: the multiple template extracted in template video is closed
Key frame picture；
Obtain the first object characteristic vector of each template key frame picture；
The time letter with each template key frame picture is obtained sequentially in time successively from live video stream
The corresponding key frame picture to be measured of manner of breathing；
Determine the second target feature vector of described key frame picture to be measured；
Compare successively each described first object characteristic vector and each described second target characteristic corresponding to
Whether amount mates；
Determine key frame picture to be measured and the described template video in described live video stream according to matching result
In multiple template key frame picture whether mate；
When the multiple template in the key frame picture to be measured in described live video stream with described template video is closed
When key frame picture matches, point out to have started to play described template video in described live video stream；Otherwise,
Abandon pointing out to have started in described live video stream play described template video.
In one embodiment, described sequentially in time successively from live video stream obtain with each template
The corresponding key frame picture to be measured of the temporal information of key frame picture, comprising:
Determine the temporal information of each described template key frame picture；
Time letter with each template key frame picture is determined according to described temporal information and reproduction time threshold value
The corresponding key frame picture to be measured of manner of breathing.
In one embodiment, the described key frame to be measured being determined according to matching result in described live video stream
Whether picture is mated with the multiple template key frame picture in described template video, comprising:
When the second target characteristic with corresponding key frame picture to be measured in multiple described template key frame pictures
When the number of the first object characteristic vector that vector matches is more than preset number, determine described live video stream
In key frame picture to be measured match with the multiple template key frame picture in described template video；Otherwise,
Determine that the key frame picture to be measured in described live video stream is crucial with the multiple template in described template video
Frame picture mismatches.
In one embodiment, when having started to play described template video in pointing out described live video stream,
By the time matching with corresponding template key frame picture in described live video stream key to be measured the latest
The reproduction time of frame picture play cuing time in described live video stream as described template video.
In one embodiment, the described first object characteristic vector obtaining each template key frame picture, bag
Include:
Obtain the overall rectangular histogram of each described template key frame picture；
Each described template key frame picture is divided into m image block；
Obtain the local histogram of each the described image block in m described image block；
Described first object characteristic vector is determined according to described overall rectangular histogram and m described local histogram.
The present invention also provides a kind of video playback suggestion device, comprising:
Extraction module, for extracting the multiple template key frame picture in template video；
First acquisition module, for obtaining the first object characteristic vector of each template key frame picture；
Second acquisition module, is closed with each template for obtaining from live video stream successively sequentially in time
The corresponding key frame picture to be measured of the temporal information of key frame picture；
First determining module, for determining the second target feature vector of described key frame picture to be measured；
Matching module, for compare successively each described first object characteristic vector with corresponding each described
Whether two target feature vectors mate；
Second determining module, for determining the key frame figure to be measured in described live video stream according to matching result
Whether piece is mated with the multiple template key frame picture in described template video；
Processing module, for when in the key frame picture to be measured in described live video stream with described template video
Multiple template key frame picture when matching, point out to have started to play described template in described live video stream
Video；Otherwise, abandon pointing out to have started in described live video stream play described template video.
In one embodiment, described second acquisition module includes:
First determination sub-module, for determining the temporal information of each described template key frame picture；
Second determination sub-module, for determining and each template according to described temporal information and reproduction time threshold value
The corresponding key frame picture to be measured of the temporal information of key frame picture.
In one embodiment, described second determining module includes:
3rd determination sub-module, for when in multiple described template key frame pictures with corresponding key frame to be measured
When the number of the first object characteristic vector that the second target feature vector of picture matches is more than preset number,
Determine that the key frame picture to be measured in described live video stream is crucial with the multiple template in described template video
Frame picture matches；Otherwise, it determines the key frame picture to be measured in described live video stream is regarded with described template
Multiple template key frame picture in frequency mismatches.
In one embodiment, when having started to play described template video in pointing out described live video stream,
By the time matching with corresponding template key frame picture in described live video stream key to be measured the latest
The reproduction time of frame picture play cuing time in described live video stream as described template video.
In one embodiment, described first acquisition module includes:
First acquisition submodule, for obtaining the overall rectangular histogram of each described template key frame picture；
Divide submodule, for each described template key frame 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
Described first object characteristic vector.
The technical scheme that embodiment of the disclosure provides can include following beneficial effect:
By comparing first object characteristic vector and the correspondence of each the template key frame picture in template video
Live video stream in the second target feature vector of key frame picture to be measured whether mate, can be accurately true
Whether determine multiple template key frame picture in key frame picture to be measured in live video stream and template video
Coupling, and then accurate this template video that whether started broadcasting determining in live video stream, thus realize basis should
Template video carries out Accurate Prediction to the video play in live video stream.
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 video playback reminding method according to an exemplary embodiment.
Fig. 2 is a kind of block diagram of the video playback suggestion device according to an exemplary embodiment.
Fig. 3 is the block diagram of another kind of video playback suggestion device according to an exemplary embodiment.
Fig. 4 is the block diagram of another the video playback suggestion device according to an exemplary embodiment.
Fig. 5 is the block diagram of another the video playback suggestion device 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 video playback reminding method, should
Method is be applied to video playback attention program, system or device, as shown in figure 1, step s101, extracts
Multiple template key frame picture in template video；Wherein, template video can be derived in epg system
Close on same program that the time (moment that for example, certain of yesterday and the day before yesterday is almost fixed) occurred (or
Permitted different collection numbers, the not same period), whether play this section for the same time in detection live video stream again
Mesh, thus realize video repeatability detection and programming predictions exactly.Certainly, carrying out video in the present invention
It is only limited to identical video content detection during repeatability detection (i.e. matching detection), be not related to picture
Deformation, change of color etc..
When selecting multiple template key frame picture from template video, similarity is more than two of certain threshold value
Template picture is considered identical picture, otherwise it is assumed that being different template key frame pictures；In addition, selecting
While template key frame picture, interval between two template key frame pictures of arbitrary neighborhood can be controlled
The number of template picture is preset number, had so both decreased the process of same template picture, and had decreased mould again
The data processing amount of plate picture, the control at interval it also avoid the loss of important information.
Step s102, obtains the first object characteristic vector of each template key frame picture；First object feature
Vector is used for this template key frame picture of unique mark, and the fingerprint for this template key frame picture regards
Frequency fingerprint.
Step s103, obtains and each template key frame picture sequentially in time successively from live video stream
The corresponding key frame picture to be measured of temporal information；In order to carry out programming predictions, time accurately and in real time
It is non-the normally off key, accordingly, it would be desirable to obtain successively in live video stream sequentially in time close with each template
The corresponding key frame picture to be measured of the temporal information of key frame picture, to avoid and each template key frame picture
The reproduction time of key frame picture to be measured and this template key frame picture reproduction time dislocation, and affect
Join result, carry out affecting the accuracy of programming predictions.For example: the temporal information of certain template key frame picture
During for t1, the temporal information of corresponding key frame picture to be measured also should be near t1.
Step s104, determines the second target feature vector of key frame picture to be measured；Second target feature vector
This key frame picture to be measured for unique mark, the fingerprint for this key frame picture to be measured is that video refers to
Stricture of vagina.
Step s105, compare successively each first object characteristic vector and each second target characteristic corresponding to
Whether amount mates；When the second target feature vector of arbitrary key frame picture to be measured is closed with corresponding arbitrary template
The first object characteristic vector of key frame picture match (i.e. similarity be higher than certain threshold value) when, this is described
One key frame picture to be measured and this arbitrary template key frame picture match；Otherwise, this arbitrary key frame figure to be measured
Piece is mismatched with this arbitrary template key frame picture.
Step s106, determines key frame picture to be measured and the template video in live video stream according to matching result
In multiple template key frame picture whether mate；When key frame picture to be measured the second target feature vector with
The first object characteristic vector of corresponding template key frame picture match number be higher than preset number when, explanation
Majority in live video stream key frame to be measured picture multiple template corresponding with template video key frame figure
Piece matches one by one, otherwise, illustrates in majority key frame to be measured picture and the template video in live video stream
Multiple template key frame picture all mismatch.
Step s107, when the multiple template in the key frame picture to be measured in live video stream with template video is closed
When key frame picture matches, point out to have started to play template video in live video stream；Otherwise, abandon pointing out
Play template video is had started in live video stream.
When the key frame picture to be measured that judgement obtains sequentially in time is multiple with obtain from template video
When corresponding template key frame picture matches, when illustrating corresponding with template video this section in live video stream
The video of interior broadcasting is higher with the matching degree of this template video, and repetitive rate is larger, then can determine in this section
In time, live video stream has started to play this template video, thus realizing having carried out the repetition of program exactly
Detection and prediction, at this point it is possible to prompting user is so that user can watch this program in time；Certainly, when
Judge that the key frame picture to be measured obtaining sequentially in time is multiple corresponding with obtain from template video
When template key frame picture mismatches, illustrate to broadcast in this period corresponding with template video in live video stream
The video put is relatively low with the matching degree of this template video, and repetitive rate is less, then can determine within this time
Live video stream does not commence play out this template video, also implies that in this time in this live video stream and broadcasts
Video be new video, rather than template video, then this template video can be updated, simultaneously
Broadcast in the same time without the prompting corresponding program of this template video of user again.Certainly, if template regards
Frequency is the program broadcasting in the same time period in recent epg, and live video stream is the broadcast of today
Program, then pass through such scheme, the present invention completes the real-time estimate to epg program, meanwhile, when
Judge that the key frame picture to be measured obtaining sequentially in time is multiple corresponding with obtain from template video
When template key frame picture mismatches, can also be by being updated completing to epg's to template video
Correction.
In one embodiment, above-mentioned steps s103 can be performed as:
Determine the temporal information of each template key frame picture；
Determine the temporal information phase with each template key frame picture according to temporal information and reproduction time threshold value
Corresponding key frame picture to be measured.
In order to carry out programming predictions accurately and in real time, the time is non-the normally off key, accordingly, it would be desirable to according to when
Between order obtain corresponding the treating of temporal information with each template key frame picture in live video stream successively
Survey key frame picture, with avoid with the reproduction time of the key frame picture to be measured of each template key frame picture with
The reproduction time dislocation of this template key frame picture is too many, and affects matching result, carries out affecting programming predictions
Accuracy.For example: the temporal information that certain template key frame picture records in template video (is broadcasted
Time) for t1 when, corresponding key frame picture to be measured in live video stream corresponding broadcast time be t1-
To t1+ reproduction time threshold value, wherein, reproduction time threshold value is preferably 1.8 minutes reproduction time threshold value.
In one embodiment, above-mentioned steps s106 can be performed as:
When the second target feature vector with corresponding key frame picture to be measured in multiple template key frame picture
When the number of the first object characteristic vector matching is more than preset number, determine to be measured in live video stream
Key frame picture is matched with the multiple template key frame picture in template video；Otherwise, it determines real-time video
Key frame picture to be measured in stream is mismatched with the multiple template key frame picture in template video.
When in template video the first object characteristic vector of the template key frame picture of first camera lens with corresponding
The second target feature vector of key frame picture to be measured when matching, illustrate that the template of first camera lens is crucial
Frame picture is matched with corresponding template key frame picture to be measured, then continue to compare the next one in template video
Corresponding to be measured in the first object characteristic vector of template key frame picture of camera lens and live video stream
Whether the second target feature vector of key frame picture mates, and circulates successively, then in statistical mask video
Match with the second target feature vector of corresponding key frame picture to be measured in multiple template key frame picture
First object characteristic vector number, when this number be more than preset number when, illustrate in this template video
The video of the broadcasting in this time period in camera lens and live video stream is more conform with, and rate is higher again, coupling
Degree preferably it is determined that key frame picture to be measured in this live video stream with multiple corresponding in template video
Template key frame picture matches；Otherwise, it determines the key frame picture to be measured in live video stream is regarded with template
Multiple corresponding template key frame picture in frequency mismatches；Certainly, due to the corresponding program of this template video
It is also possible to broadcast in other times section, that is, has changed broadcast time, therefore, determining live video stream
In key frame picture to be measured and the multiple corresponding template key frame picture in template video mismatch, permissible
Continue the key frame picture to be measured of detection live video stream broadcast within following a period of time whether with template
Video matching, to re-start accurate programming predictions.
In one embodiment, when having started to play template video in pointing out live video stream, will regard in real time
The broadcasting of the time that frequency is matched with corresponding template key frame picture in flowing key frame picture to be measured the latest
Play cuing time in live video stream as template video time.
When determining that having started to play the corresponding program of this template video in live video stream is to need one section of prediction
Between, and determine that time of this template video that started broadcasting is and is matched with corresponding template key frame picture
The reproduction time of time that frame key frame to be measured picture the most rearward, in addition, point out immediately in this reproduction time
Started broadcasting this template video, also plays the timely effect reminding user.
In one embodiment, above-mentioned steps s102 can be performed as:
Obtain the overall rectangular histogram of each template key frame picture；
Each template key frame picture is divided into m image block；
Obtain the local histogram of each image block in m image block；
First object characteristic vector is determined according to overall rectangular histogram and m local histogram.
In order to the first object characteristic vector of each template key frame picture more can be accurately acquired, can obtain
Take the overall rectangular histogram of this template key frame picture, to obtain the global characteristics of this template key frame picture, with
When this template key frame picture is divided into the region of m, straight with the local that obtains the image block in each region
Side's figure is thus get the local feature of each image block, and finally utilizes this global characteristics and m local
Feature obtains the first object characteristic vector of this higher template key frame picture of accuracy；Certainly, obtaining
During the second target feature vector of every key frame picture to be measured, it is possible to use the program, this is conducive to carrying
The repeatability detection of high video precision and video estimation precision, wherein, m is preferably 4.
As shown in Fig. 2 the present invention also provides a kind of video playback suggestion device, comprising: extraction module 201,
It is configured to extract the multiple template key frame picture in template video；
First acquisition module 202, be configured to obtain the first object feature of each template key frame picture to
Amount；
Second acquisition module 203, is configured to obtain from live video stream successively sequentially in time and every
The corresponding key frame picture to be measured of the temporal information of individual template key frame picture；
First determining module 204, be configured to determine that the second target characteristic of described key frame picture to be measured to
Amount；
Matching module 205, is configured to compare successively each described first object characteristic vector every with corresponding
Whether individual described second target feature vector mates；
Second determining module 206, is configured to be determined according to matching result to be measured in described live video stream
Whether key frame picture is mated with the multiple template key frame picture in described template video；
Processing module 207, is configured as the key frame picture to be measured in described live video stream and described mould
When multiple template key frame picture in plate video matches, point out to have started in described live video stream play
Described template video；Otherwise, abandon pointing out to have started in described live video stream play described template video.
As shown in figure 3, in one embodiment, described second acquisition module 203 includes:
First determination sub-module 2031, is configured to determine that the time letter of each described template key frame picture
Breath；
Second determination sub-module 2032, be configured to according to described temporal information and reproduction time threshold value determine with
The corresponding key frame picture to be measured of the temporal information of each template key frame picture.
As shown in figure 4, in one embodiment, described second determining module 206 includes:
3rd determination sub-module 2061, is configured as treating with corresponding in multiple described template key frame pictures
The number of the first object characteristic vector that the second target feature vector of survey key frame picture matches is more than pre-
If during number, determine multiple in key frame picture to be measured in described live video stream and described template video
Template key frame picture matches；Otherwise, it determines the key frame picture to be measured in described live video stream and institute
The multiple template key frame picture stated in template video mismatches.
In one embodiment, when having started to play described template video in pointing out described live video stream,
By the time matching with corresponding template key frame picture in described live video stream key to be measured the latest
The reproduction time of frame picture play cuing time in described live video stream as described template video.
As shown in figure 5, in one embodiment, described first acquisition module 202 includes:
First acquisition submodule 2021, is configured to obtain the overall Nogata of each described template key frame picture
Figure；
Divide submodule 2022, be configured to for each described template key frame picture to be divided into m image
Block；
Second acquisition submodule 2023, is configured to obtain each described image in m described image block
The local histogram of block；
4th determination sub-module 2024, is configured to straight according to described overall rectangular histogram and m described local
Side's figure determines described first object characteristic vector.
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 video playback suggestion device in the present invention is applied to terminal unit.For example, it may be it is mobile
Phone, computer, digital broadcast terminal, messaging devices, game console, tablet device, medical 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 video playback reminding method is it is characterised in that include:
Extract the multiple template key frame picture in template video；
Obtain the first object characteristic vector of each template key frame picture；
The time letter with each template key frame picture is obtained sequentially in time successively from live video stream
The corresponding key frame picture to be measured of manner of breathing；
Determine the second target feature vector of described key frame picture to be measured；
Compare successively each described first object characteristic vector and each described second target characteristic corresponding to
Whether amount mates；
Determine key frame picture to be measured and the described template video in described live video stream according to matching result
In multiple template key frame picture whether mate；
When the multiple template in the key frame picture to be measured in described live video stream with described template video is closed
When key frame picture matches, point out to have started to play described template video in described live video stream；Otherwise,
Abandon pointing out to have started in described live video stream play described template video.
2. method described in 1 is wanted according to right it is characterised in that
Described sequentially in time successively from live video stream obtain with each template key frame picture when
Between the corresponding key frame picture to be measured of information, comprising:
Determine the temporal information of each described template key frame picture；
Time letter with each template key frame picture is determined according to described temporal information and reproduction time threshold value
The corresponding key frame picture to be measured of manner of breathing.
3. method described in 1 is wanted according to right it is characterised in that
Described key frame picture to be measured and the described template being determined according to matching result in described live video stream
Whether the multiple template key frame picture in video mates, comprising:
When the second target characteristic with corresponding key frame picture to be measured in multiple described template key frame pictures
When the number of the first object characteristic vector that vector matches is more than preset number, determine described live video stream
In key frame picture to be measured match with the multiple template key frame picture in described template video；Otherwise,
Determine that the key frame picture to be measured in described live video stream is crucial with the multiple template in described template video
Frame picture mismatches.
4. method described in 1 is wanted according to right it is characterised in that
When having started to play described template video in pointing out described live video stream, by described live video stream
In time of matching with corresponding template key frame picture key frame picture to be measured the latest reproduction time
As the play cuing time in described live video stream for the described template video.
5. method any one of 1 to 4 is wanted according to right it is characterised in that
The described first object characteristic vector obtaining each template key frame picture, comprising:
Obtain the overall rectangular histogram of each described template key frame picture；
Each described template key frame picture is divided into m image block；
Obtain the local histogram of each the described image block in m described image block；
Described first object characteristic vector is determined according to described overall rectangular histogram and m described local histogram.
6. a kind of video playback suggestion device is it is characterised in that include:
Extraction module, for extracting the multiple template key frame picture in template video；
First acquisition module, for obtaining the first object characteristic vector of each template key frame picture；
Second acquisition module, is closed with each template for obtaining from live video stream successively sequentially in time
The corresponding key frame picture to be measured of the temporal information of key frame picture；
First determining module, for determining the second target feature vector of described key frame picture to be measured；
Matching module, for compare successively each described first object characteristic vector with corresponding each described
Whether two target feature vectors mate；
Second determining module, for determining the key frame figure to be measured in described live video stream according to matching result
Whether piece is mated with the multiple template key frame picture in described template video；
Processing module, for when in the key frame picture to be measured in described live video stream with described template video
Multiple template key frame picture when matching, point out to have started to play described template in described live video stream
Video；Otherwise, abandon pointing out to have started in described live video stream play described template video.
7. device described in 6 is wanted according to right it is characterised in that
Described second acquisition module includes:
First determination sub-module, for determining the temporal information of each described template key frame picture；
Second determination sub-module, for determining and each template according to described temporal information and reproduction time threshold value
The corresponding key frame picture to be measured of the temporal information of key frame picture.
8. device described in 6 is wanted according to right it is characterised in that
Described second determining module includes:
3rd determination sub-module, for when in multiple described template key frame pictures with corresponding key frame to be measured
When the number of the first object characteristic vector that the second target feature vector of picture matches is more than preset number,
Determine that the key frame picture to be measured in described live video stream is crucial with the multiple template in described template video
Frame picture matches；Otherwise, it determines the key frame picture to be measured in described live video stream is regarded with described template
Multiple template key frame picture in frequency mismatches.
9. device described in 6 is wanted according to right it is characterised in that
When having started to play described template video in pointing out described live video stream, by described live video stream
In time of matching with the template key frame picture that matches key frame picture to be measured the latest reproduction time
As the play cuing time in described live video stream for the described template video.
10. device any one of 6 to 9 is wanted according to right it is characterised in that
Described first acquisition module includes:
First acquisition submodule, for obtaining the overall rectangular histogram of each described template key frame picture；
Divide submodule, for each described template key frame 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
Described first object characteristic vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510439978.2A CN106375848A (en) | 2015-07-23 | 2015-07-23 | Video playback prompting method and video playback prompting device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510439978.2A CN106375848A (en) | 2015-07-23 | 2015-07-23 | Video playback prompting method and video playback prompting device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106375848A true CN106375848A (en) | 2017-02-01 |
Family
ID=57880920
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510439978.2A Pending CN106375848A (en) | 2015-07-23 | 2015-07-23 | Video playback prompting method and video playback prompting device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106375848A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111105406A (en) * | 2019-12-24 | 2020-05-05 | 杭州当虹科技股份有限公司 | Method for detecting video stream identity of public electronic screen |
| CN113542731A (en) * | 2021-07-15 | 2021-10-22 | 湖南广播影视集团有限公司 | Control method and device for video and audio playing |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040237102A1 (en) * | 2003-03-07 | 2004-11-25 | Richard Konig | Advertisement substitution |
| CN1820511A (en) * | 2003-07-11 | 2006-08-16 | 皇家飞利浦电子股份有限公司 | Method and device for generating and detecting a fingerprint functioning as a trigger marker in a multimedia signal |
| CN102760169A (en) * | 2012-06-13 | 2012-10-31 | 天脉聚源(北京)传媒科技有限公司 | Method for detecting advertising slots in television direct transmission streams |
| 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 |
| CN103235956A (en) * | 2013-03-28 | 2013-08-07 | 天脉聚源(北京)传媒科技有限公司 | Method and device for detecting advertisements |
| CN103297851A (en) * | 2013-05-16 | 2013-09-11 | 中国科学院自动化研究所 | Method and device for quickly counting and automatically examining and verifying target contents in long video |
-
2015
- 2015-07-23 CN CN201510439978.2A patent/CN106375848A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040237102A1 (en) * | 2003-03-07 | 2004-11-25 | Richard Konig | Advertisement substitution |
| CN1820511A (en) * | 2003-07-11 | 2006-08-16 | 皇家飞利浦电子股份有限公司 | Method and device for generating and detecting a fingerprint functioning as a trigger marker in a multimedia signal |
| CN102760169A (en) * | 2012-06-13 | 2012-10-31 | 天脉聚源(北京)传媒科技有限公司 | Method for detecting advertising slots in television direct transmission streams |
| 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 |
| CN103235956A (en) * | 2013-03-28 | 2013-08-07 | 天脉聚源(北京)传媒科技有限公司 | Method and device for detecting advertisements |
| CN103297851A (en) * | 2013-05-16 | 2013-09-11 | 中国科学院自动化研究所 | Method and device for quickly counting and automatically examining and verifying target contents in long video |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111105406A (en) * | 2019-12-24 | 2020-05-05 | 杭州当虹科技股份有限公司 | Method for detecting video stream identity of public electronic screen |
| CN111105406B (en) * | 2019-12-24 | 2023-05-30 | 杭州当虹科技股份有限公司 | Method for detecting identity of video streams of public electronic screen |
| CN113542731A (en) * | 2021-07-15 | 2021-10-22 | 湖南广播影视集团有限公司 | Control method and device for video and audio playing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110942006B (en) | Motion gesture recognition method, motion gesture recognition apparatus, terminal device, and medium | |
| EP2988513A1 (en) | Method for providing real-time video and device thereof as well as server and terminal device | |
| CN110298220B (en) | Action video live broadcast method, system, electronic equipment and storage medium | |
| CN113850248B (en) | Motion attitude evaluation method and device, edge calculation server and storage medium | |
| CN103763585B (en) | A kind of user's characteristic information acquisition methods, device and terminal device | |
| CN111241872B (en) | Video image shielding method and device | |
| CN109308437B (en) | Motion recognition error correction method, electronic device, and storage medium | |
| CN108712667B (en) | Smart television, screen capture application method and device thereof, and readable storage medium | |
| CN106375781B (en) | A kind of judgment method and device repeating video | |
| CN104811798B (en) | A kind of method and device for adjusting video playout speed | |
| CN110636315B (en) | Multi-user virtual live broadcast method and device, electronic equipment and storage medium | |
| US20140157294A1 (en) | Content providing apparatus, content providing method, image displaying apparatus, and computer-readable recording medium | |
| CN112115894A (en) | Training method and device for hand key point detection model and electronic equipment | |
| CN112287771A (en) | Method, apparatus, server and medium for detecting video event | |
| CN109325479A (en) | Paces detection method and device | |
| CN110941727B (en) | Resource recommendation method and device, electronic equipment and storage medium | |
| CN106375849B (en) | A kind of method, apparatus, the update method of video and device generating template | |
| CN106375848A (en) | Video playback prompting method and video playback prompting device | |
| CN110059653A (en) | A kind of method of data capture and device, electronic equipment, storage medium | |
| CN106354736A (en) | Judgment method and device of repetitive video | |
| CN106412690B (en) | Video playing determination method and device | |
| CN114299427A (en) | Method and device for detecting key points of target object, electronic equipment and storage medium | |
| CN111726649B (en) | Video stream processing method, device, computer equipment and medium | |
| CN116320711A (en) | Image shooting method and device | |
| CN111580683A (en) | Input method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170201 |