CN106713964A - Method of generating video abstract viewpoint graph and apparatus thereof - Google Patents
Method of generating video abstract viewpoint graph and apparatus thereof Download PDFInfo
- Publication number
- CN106713964A CN106713964A CN201611101886.4A CN201611101886A CN106713964A CN 106713964 A CN106713964 A CN 106713964A CN 201611101886 A CN201611101886 A CN 201611101886A CN 106713964 A CN106713964 A CN 106713964A
- Authority
- CN
- China
- Prior art keywords
- video
- key frame
- frame
- viewpoint
- threshold
- 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 58
- 239000012634 fragment Substances 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 10
- 238000001914 filtration Methods 0.000 claims description 9
- 239000000284 extract Substances 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 abstract description 9
- 230000015654 memory Effects 0.000 description 18
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 5
- 238000013461 design Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000002699 waste material Substances 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
- H04N21/431—Generation of visual interfaces for content selection or interaction; Content or additional data rendering
- H04N21/4312—Generation of visual interfaces for content selection or interaction; Content or additional data rendering involving specific graphical features, e.g. screen layout, special fonts or colors, blinking icons, highlights or animations
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Television Signal Processing For Recording (AREA)
Abstract
Embodiments of the invention provide a method of generating a video abstract viewpoint graph and an apparatus thereof. The method comprises the following steps of dividing a video into a plurality of video segments; for each video segment, if the video segment contains a key frame, extracting the key frame, wherein the key frame is a video frame when a video picture generates a scene change; and according to all the extracted key frames, generating an abstract viewpoint graph of the video. In the embodiments of the invention, the video is divided into the plurality of video segments, then whether each video segment contains the video frame when the video picture generates the scene change is determined, and the video frames are taken as the key frames and are extracted so as to generate an abstract viewpoint graph so that important frames which possess generality in the video are acquired. Therefore, through checking the important frames, a user can increase efficiency for browsing the video and user time is saved.
Description
Technical field
The present invention relates to internet video play-back technology field, more particularly to a kind of method for generating video frequency abstract viewpoint figure
And device.
Background technology
With developing rapidly for internet, the video based on internet is also becoming increasingly popular, and user is gradually from traditional
Reception television station signals " seeing TV " is transferred to watches the video frequency programs such as various live, program requests on internet video platform.Hair
A person of good sense realize it is of the invention during find, due to many videos, redundancy is higher in time, part-time segment information amount
It is sparse, or, in other words, content user of the video on some time periods may and be lost interest in, so user often has
The progress bar of video playback is pulled to fast skip the demand of current slot or the whole video content of fast browsing, but
In the prior art, user is being pulled when progress bar is browsed with certain blindness due to the Limited information for obtaining, and is made
Into waste of time.
The content of the invention
The present invention provides a kind of method and device for generating video frequency abstract viewpoint figure, to improve effect when user browses video
Rate.
First aspect according to embodiments of the present invention, there is provided a kind of method of generation video frequency abstract viewpoint figure, methods described
Including：
Divide video into multiple video segments；
For video segment each described：If including key frame in the video segment, the key frame is extracted, its
Described in key frame be video pictures in occurrence scene change when frame of video；
The summary viewpoint figure of the video is generated according to all described key frame for extracting.
Optionally, if including key frame in the video segment, the key frame is extracted, including：
It is multiple picture sub-blocks by each the frame of video cutting in the video segment；
According to preset algorithm, the center histogram of gradients of the center sub-block of each frame of video is obtained, wherein the center is sub
Block is the picture sub-block positioned at central area；
Judge the mean square error of center histogram of gradients of two adjacent video frames whether more than first threshold；
If the mean square error is more than the first threshold, or two in the two adjacent video frames is extracted
Individual frame of video is used as key frame.
Optionally, before the summary viewpoint figure of the video is generated according to all described key frame for extracting, methods described
Also include：
Judge previous video segment in two adjacent video fragment last key frame and latter video segment
Whether one mean square error of key frame is more than the first threshold；
If no more than described first threshold, last key frame or latter video of previous video segment are filtered
First key frame of fragment.
Optionally, before the summary viewpoint figure of the video is generated according to all described key frame for extracting, methods described
Also include：
Calculate the signal to noise ratio of each key frame；
Filter key frame of the signal to noise ratio less than Second Threshold.
Optionally, the summary viewpoint figure of the video is generated according to all described key frame for extracting, including：
Obtain each thumbnail of the key frame under different resolution；
Summary viewpoint figure using all thumbnails under same resolution ratio as the video under the resolution ratio.
Second aspect according to embodiments of the present invention, there is provided a kind of device of generation video frequency abstract viewpoint figure, described device
Including：
Video division module, for dividing video into multiple video segments；
Key-frame extraction module, for for video segment each described, if including key frame in the video segment,
The key frame is then extracted, wherein the key frame is frame of video when occurrence scene changes in video pictures；
Summary viewpoint figure generation module, the summary viewpoint for generating the video according to all described key frame for extracting
Figure.
Optionally, the key-frame extraction module includes：
Frame of video processes submodule, for being multiple picture sub-blocks by each the frame of video cutting in the video segment,
According to preset algorithm, obtain the center histogram of gradients of the center sub-block of each frame of video, wherein the center sub-block be positioned at
The picture sub-block of central area；
Key frame judging submodule, for judge two adjacent video frames center histogram of gradients mean square error whether
More than first threshold, if the mean square error is more than the first threshold, in the two adjacent video frames is extracted
Individual or two frame of video are used as key frame.
Optionally, described device also includes：
First key frame filtering module, for generating institute according to all described key frame for extracting in the summary viewpoint figure
Before stating the summary viewpoint figure of video, judge last key frame of previous video segment in two adjacent video fragment with after
Whether the mean square error of first key frame of one video segment is more than the first threshold, if no more than described first
Threshold value, then filter last key frame of previous video segment or first key frame of latter video segment.
Optionally, described device also includes：
Second key frame filtering module, for generating institute according to all described key frame for extracting in the summary viewpoint figure
Before stating the summary viewpoint figure of video, the signal to noise ratio of each key frame is calculated, filter key frame of the signal to noise ratio less than Second Threshold.
Optionally, the summary viewpoint figure generation module is used for：
Obtain each thumbnail of the key frame under different resolution；
Summary viewpoint figure using all thumbnails under same resolution ratio as the video under the resolution ratio.
Technical scheme provided in an embodiment of the present invention can include the following benefits：
In embodiments of the present invention, multiple video segments are first divided video into, then judge in each video segment whether
Comprising in video pictures occurrence scene change frame of video, and using these frame of video as key-frame extraction out, generate video
Summary viewpoint figure, so as to obtain having recapitulative important picture to video, such user is by checking these important pictures
Efficiency when browsing video is greatly improved, the time of user is also saved.
It should be appreciated that the general description of the above and detailed description hereinafter are only exemplary and explanatory, not
Can the limitation present invention.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
The accompanying drawing to be used needed for having technology description is briefly described, it should be apparent that, for those of ordinary skill in the art
Speech, without having to pay creative labor, can also obtain other accompanying drawings according to these accompanying drawings.Additionally, these are situated between
Continue and do not constitute restriction to embodiment, the element with same reference numbers label is expressed as similar element in accompanying drawing, removes
It is non-to have especially statement, the figure not composition limitation in accompanying drawing.
Fig. 1 is a kind of flow of the method for the generation video frequency abstract viewpoint figure according to an exemplary embodiment of the invention
Figure；
Fig. 2 is that summary viewpoint figure according to an exemplary embodiment of the invention link identification on a progress bar is illustrated
Figure；
Fig. 3 is a kind of stream of the method for the generation video frequency abstract viewpoint figure according to another exemplary embodiment of the present invention
Cheng Tu；
Fig. 4 is the frame of video picture segmentation schematic diagram according to an exemplary embodiment of the invention；
Fig. 5 is a kind of stream of the method for the generation video frequency abstract viewpoint figure according to further example embodiment of the present invention
Cheng Tu；
Fig. 6 is a kind of stream of the method for the generation video frequency abstract viewpoint figure according to further example embodiment of the present invention
Cheng Tu；
Fig. 7 is a kind of stream of the method for the generation video frequency abstract viewpoint figure according to further example embodiment of the present invention
Cheng Tu；
Fig. 8 is the traffic scene schematic diagram according to an exemplary embodiment of the invention；
Fig. 9 is a kind of signal of the device of the generation video frequency abstract viewpoint figure according to an exemplary embodiment of the invention
Figure；
Figure 10 is a kind of device of the generation video frequency abstract viewpoint figure according to another exemplary embodiment of the present invention
Schematic diagram；
Figure 11 is a kind of device of the generation video frequency abstract viewpoint figure according to further example embodiment of the present invention
Schematic diagram；
Figure 12 is a kind of device of the generation video frequency abstract viewpoint figure according to further example embodiment of the present invention
Schematic diagram；
Figure 13 is the electricity of the method for the execution generation video frequency abstract viewpoint figure according to an exemplary embodiment of the invention
The hardware architecture diagram of sub- equipment.
Specific embodiment
Here exemplary embodiment will be illustrated in detail, its example is illustrated in the accompanying drawings.Following description is related to
During accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawings represent same or analogous key element.Following exemplary embodiment
Described in implementation method do not represent and the consistent all implementation methods of the present invention.Conversely, they be only with it is such as appended
The example of the consistent apparatus and method of some aspects being described in detail in claims, of the invention.
Embodiment one
Fig. 1 is a kind of flow of the method for the generation video frequency abstract viewpoint figure according to an exemplary embodiment of the invention
Figure.The method for example can be used for the mobile phone with certain computing capability, panel computer, PC, TV, server etc. and set
It is standby.
Shown in Figure 1, the method can include：
Step S101, divides video into multiple video segments.
Text can have summary, and video can also have summary.In embodiments of the present invention, shown using summary viewpoint figure
The summary of video.Summary viewpoint figure can essentially be one group of picture, wherein the width being all originated from per pictures in video
Picture (or perhaps a frame of video).User checks summary viewpoint figure, just can substantially know the substance of the video.
In order to obtain viewpoint figure of making a summary, multiple video segments are divided video into first in embodiments of the present invention.Video
Fragment can be described as video segment again.For improving video code conversion speed and distribution speed and needing the reasons such as encryption, to regarding
Length that can be first according to video when being processed frequently makes video segment.The length of each video segment can be waited according to demand
Voluntarily specified by technical staff.Generally video more long, video segment is also more.When being multiple videos video slicing
After fragment, just parallel processing can be carried out to each video segment, so as to be favorably improved treatment effeciency.
Step S102, for video segment each described：If including key frame in the video segment, extract described
Key frame, wherein the key frame is frame of video when occurrence scene changes in video pictures.
Even if very short video, many frame of video are also usually contained, so choosing which frame of video constitutes the video
Summary, is a major issue.Frame of video can for example be randomly selected, it is also possible to just choose a video every a time period
Frame, and in the present embodiment, for more preferable reflecting video content, video is preferably summarized, selection is that video is drawn
Frame of video when occurrence scene changes in face.
For how to judge whether occurrence scene changes in picture, and the present embodiment is simultaneously not limited, such as can use
Various methods such as frame difference method, histogram method, edge calculations, those skilled in the art can according to different demands different scenes and
Voluntarily select, design, in these selections used herein and can design all without departing from spirit and scope of the invention.
Step S103, the summary viewpoint figure of the video is generated according to all described key frame for extracting.
For example, can directly using key frame as summary viewpoint figure, or as plucking after key frame is carried out into image scaling
Want viewpoint figure.
After summary viewpoint figure is generated, when the video is played, just can on a progress bar link each summary and regard
Point diagram, can be found in shown in Fig. 2 as an example, 201 be each summary viewpoint figure link identification on a progress bar in fig. 2,
User just can see the summary viewpoint figure at the time point by clicking on the mark.
In the present embodiment, multiple video segments are first divided video into, then judges whether included in each video segment
In video pictures occurrence scene change frame of video, and using these frame of video as key-frame extraction out, generate video frequency abstract
Viewpoint figure, so as to obtain having recapitulative important picture to video, such user is by checking that these important pictures can be big
The big efficiency improved when browsing video, also saves the time of user.
Embodiment two
Fig. 3 is a kind of stream of the method for the generation video frequency abstract viewpoint figure according to another exemplary embodiment of the present invention
Cheng Tu.The present embodiment is based on embodiment one, in the present embodiment, if including key frame in the video segment, extracts institute
Key frame is stated, be may comprise steps of：
Step S301, is multiple picture sub-blocks by each the frame of video cutting in the video segment.
As an example reference can be made to shown in Fig. 4, in fig. 4, current video frame 401 is divided into 9 picture sub-blocks.
Step S302, according to preset algorithm, obtains the center histogram of gradients of the center sub-block of each frame of video, wherein institute
The center sub-block of stating is the picture sub-block positioned at central area.
In fig. 4, can be using picture sub-block 402 as center sub-block.Certainly in other embodiments of the present invention, can be with
Two or more picture sub-blocks of picture central area will be located at as center sub-block, this embodiment of the present invention is not carried out
Limitation.
Particular content the present embodiment for preset algorithm is simultaneously not limited.As an example, in the present embodiment, in order to
Accelerate the accuracy that calculating speed ensures detection again simultaneously, use local edge interpolation method.First according to the resolution ratio of video
Cutting is carried out to each frame.The usual bigger picture of resolution ratio can be cut into more sub-blocks, and the smaller picture of resolution ratio
Then sub-block is fewer.After piecemeal can one or two sub-block of Zhi Dui centers be analyzed because the often change of scene
It is most it will be evident that and background is then possible to be reused by each frame in picture central area.As an example, it is possible to use sobel
Centering center block does convolution to operator in x directions (namely horizontal) and y directions (namely longitudinal direction) respectively, obtains center sub-block in horizontal stroke
To with longitudinal direction on skirt response Gx and Gy, a kind of example given below：
Wherein A represents center sub-block, can be specifically a matrix, and matrix element value for example can be value of pixel etc.
Deng.
Then according to Gx and Gy, the direction θ of intensity G and gradient can be further obtained, for example, is shown below：
If assuming that gradient direction is divided into 16 grades, then intensity G is done histogram of gradients according to θ direction value, just be can obtain
The one 16 center histogram of gradients of dimension.
Whether step S303, judge the mean square error of center histogram of gradients of two adjacent video frames more than the first threshold
Value.
Step S304, if the mean square error is more than the first threshold, in extracting the two adjacent video frames
One or two frame of video as key frame.
In other words, when the mean square error of former and later two adjacent frame of video a, b is more than first threshold, it is believed that regard
Frequency picture there occurs scene changes during from frame of video a to frame of video b, or perhaps there occurs Shot change.Can be by
Frame of video b is used as key frame, naturally it is also possible to using video a as key frame, or using frame of video a, b as key frame, it is right
This present embodiment is simultaneously not limited, and those skilled in the art can decide in its sole discretion according to scene or demand.
Additionally, in the present embodiment or some other embodiments of the invention, after each key frame is extracted, according to extraction
All described key frame generate the summary viewpoint figure of the video before, key frame can also be filtered, to filter one
A little key frames repeat or insignificant.
As an example, the mode of filtering can have two kinds：
Filter type 1：
Judge previous video segment in two adjacent video fragment last key frame and latter video segment
Whether one mean square error of key frame is more than the first threshold；
If no more than described first threshold, last key frame or latter video of previous video segment are filtered
First key frame of fragment.
The key frame repeated before and after just can so filtering out at video segment position.
Filter type 2：
Calculate the signal to noise ratio of each key frame；
Filter key frame of the signal to noise ratio less than Second Threshold.
Just can so filter the key frames such as those completely black or blank because these key frames and be not provided with value letter
Breath.
It is real to this present invention it should be noted that both the above filter type can be used alone, it is also possible to which superposition is used
Apply example and be not limited.
In addition also, it should be noted that for individual other special circumstances, such as last of previous video segment is crucial
The mean square error of first key frame of frame and latter video segment is exactly equal to first threshold, and those skilled in the art can
With according to demand or scene etc. voluntarily determines the now execution which kind of operation, to this embodiment of the present invention and it is not limited.
In the present embodiment, by the center histogram of gradients of adjacent video frames picture central area, that can be oriented
A little frame of video namely key frame that there occurs scene switching.Additionally, being filtered by key frame, one can be effectively filtered
A little key frames repeat or insignificant, so as to be favorably improved the efficiency of subsequent treatment.
Embodiment three
Fig. 5 is a kind of stream of the method for the generation video frequency abstract viewpoint figure according to further example embodiment of the present invention
Cheng Tu.The present embodiment is based on embodiment one or embodiment two.
In some other embodiment, summary viewpoint of all key frames that will can be extracted directly as the video
Figure.But in the present embodiment, it is also possible to viewpoint figure of making a summary is re-used as after key frame is processed.It is shown in Figure 5, at this
In embodiment, the summary viewpoint figure of the video is generated according to all described key frame for extracting, can included：
Step S501, obtains each thumbnail of the key frame under different resolution.
Step S502, summary of all thumbnails under same resolution ratio as the video under the resolution ratio is regarded
Point diagram.
Because, the resolution ratio that different clients is supported may be different, such as same video, in TV
Upper broadcasting be the video a kind of resolution ratio, and on mobile phone play when be another resolution ratio.So in order that various
Client can smoothly using summary viewpoint figure, when key frame is converted into summary viewpoint figure, can be according to different resolutions
Rate is processed key frame, so as to obtain various thumbnails of same key frame, so also can just be obtained for same video
To many set thumbnails, to adapt to different resolution ratio, the demand of different occasion different users is met.
In addition, it is shown in Figure 6, in the present embodiment or some other embodiments of the invention, in view of the summary of video is regarded
Point diagram may includes numerous pictures, in order to save memory space and be easy to management, by all breviaries under same resolution ratio
After summary viewpoint figure of the figure as the video under the resolution ratio, can be with further by following this mode to one
The summary viewpoint figure of video is compressed：
All thumbnails under same resolution ratio are constituted a pictures, and generate corresponding with the picture by step S601
System file, wherein in the system file at least include positional information of each thumbnail in the picture；
Step S602, stores the picture and the system file.
For example, row interpolation is down-sampled can to enter key frame, it is allowed to form the thumbnail for meeting client viewpoint figure size.
Then a big figure of N × M is combined into according to time relationship, i.e., this magnifies figure and is formed by N × M small figure arrangement.Generate simultaneously
One system file, the various information for recording this big figure can for example include video information, small figure resolution information, small
Figure arrangement information, the relative position of each small figure and corresponding timestamp information, etc..
Referring also to shown in Fig. 7, store after the picture and the system file, methods described can also include：
Step S701, receives request of the client to the summary viewpoint figure of the video.
For example, client can be the terminal devices such as mobile phone, panel computer, PC, TV, projector.
Step S702, obtains the resolution ratio corresponding to the client.
Step S703, the picture and corresponding system file under the resolution ratio that acquisition is stored.
Step S704, by the picture is split as thumbnail and is sent to the client according to the system file.
As an example reference can be made to shown in Fig. 8, in fig. 8, server 801 for certain video is generated more covers summary viewpoint figures
Afterwards, corresponding thumbnail can be sent to by client according to the request of different clients such as mobile phone 802 or TV 803.So
After be linked to each thumbnail on progress bar by client, user just can be by checking that thumbnail carries out fast browsing to video
.
In the present embodiment, the problem of different resolution is also contemplated in generation summary viewpoint figure, many sets is generated and is plucked
Want viewpoint figure, so as to meet all kinds of clients the need for.Additionally, in the present embodiment, storage is taken to summary viewpoint figure
When split into the storage management mode that small figure is transmitted again when being combined into big figure storage, using, save memory space, also side
Management.
Following is apparatus of the present invention embodiment, can be used for performing the inventive method embodiment.For apparatus of the present invention reality
The details not disclosed in example is applied, the inventive method embodiment is refer to.
Fig. 9 is a kind of signal of the device of the generation video frequency abstract viewpoint figure according to an exemplary embodiment of the invention
Figure.The device for example can be used for the mobile phone with certain computing capability, panel computer, PC, TV, server etc. and set
It is standby.
Shown in Figure 9, the device can include：
Video division module 901, for dividing video into multiple video segments.
In order to obtain viewpoint figure of making a summary, multiple video segments are divided video into first in embodiments of the present invention.Video
Fragment can be described as video segment again.For improving video code conversion speed and distribution speed and needing the reasons such as encryption, to regarding
Length that can be first according to video when being processed frequently makes video segment.The length of each video segment can be waited according to demand
Voluntarily specified by technical staff.Generally video more long, video segment is also more.When being multiple videos video slicing
After fragment, just parallel processing can be carried out to each video segment, so as to be favorably improved treatment effeciency.
Key-frame extraction module 902, for for video segment each described, if comprising key in the video segment
Frame, then extract the key frame, wherein the key frame is frame of video when occurrence scene changes in video pictures.
For how to judge whether occurrence scene changes in picture, and the present embodiment is simultaneously not limited, such as can use
Various methods such as frame difference method, histogram method, edge calculations, those skilled in the art can according to different demands different scenes and
Voluntarily select, design, in these selections used herein and can design all without departing from spirit and scope of the invention.
Summary viewpoint figure generation module 903, the summary for generating the video according to all described key frame for extracting
Viewpoint figure.
Shown in Figure 10, in the present embodiment or some other embodiments of the invention, the key-frame extraction module can
To include：
Frame of video processes submodule 1001, for being multiple picture by each the frame of video cutting in the video segment
Block, according to preset algorithm, obtains the center histogram of gradients of the center sub-block of each frame of video, wherein the center sub-block is position
In the picture sub-block of central area；
Key frame judging submodule 1002, the mean square error of the center histogram of gradients for judging two adjacent video frames
Whether first threshold is more than, if the mean square error is more than the first threshold, in extracting the two adjacent video frames
One or two frame of video as key frame.
In other words, when the mean square error of former and later two adjacent frame of video a, b is more than first threshold, it is believed that regard
Frequency picture there occurs scene changes during from frame of video a to frame of video b, or perhaps there occurs Shot change.Can be by
Frame of video b is used as key frame, naturally it is also possible to using video a as key frame, or using frame of video a, b as key frame, it is right
This present embodiment is simultaneously not limited, and those skilled in the art can decide in its sole discretion according to scene or demand.
In the present embodiment, by the center histogram of gradients of adjacent video frames picture central area, that can be oriented
A little frame of video namely key frame that there occurs scene switching.Additionally, being filtered by key frame, one can be effectively filtered
A little key frames repeat or insignificant, so as to be favorably improved the efficiency of subsequent treatment.
Shown in Figure 11, in the present embodiment or some other embodiments of the invention, described device can also include：
First key frame filtering module 1101, for being given birth to according to all described key frame for extracting in the summary viewpoint figure
Into before the summary viewpoint figure of the video, last key frame of previous video segment in two adjacent video fragment is judged
Whether it is more than the first threshold with the first of latter video segment mean square error of key frame, if be not more than described
First threshold, then filter last key frame of previous video segment or first key frame of latter video segment.
The key frame repeated before and after just can so filtering out at video segment position.
Shown in Figure 12, in the present embodiment or some other embodiments of the invention, described device can also include：
Second key frame filtering module 1201, for being given birth to according to all described key frame for extracting in the summary viewpoint figure
Into before the summary viewpoint figure of the video, the signal to noise ratio of each key frame is calculated, filter pass of the signal to noise ratio less than Second Threshold
Key frame.
Just can so filter the key frames such as those completely black or blank because these key frames and be not provided with value letter
Breath.
In the present embodiment or some other embodiments of the invention, the summary viewpoint figure generation module can specifically be used
In：
Obtain each thumbnail of the key frame under different resolution；
Summary viewpoint figure using all thumbnails under same resolution ratio as the video under the resolution ratio.
In some other embodiment, summary viewpoint of all key frames that will can be extracted directly as the video
Figure.But in the present embodiment, it is also possible to viewpoint figure of making a summary is re-used as after key frame is processed.Therefore in the present embodiment
In, the summary viewpoint figure of the video being generated according to all described key frame for extracting, can include：
Obtain each thumbnail of the key frame under different resolution；
Summary viewpoint figure using all thumbnails under same resolution ratio as the video under the resolution ratio.
Because, the resolution ratio that different clients is supported may be different, such as same video, in TV
Upper broadcasting be the video a kind of resolution ratio, and on mobile phone play when be another resolution ratio.So in order that various
Client can smoothly using summary viewpoint figure, when key frame is converted into summary viewpoint figure, can be according to different resolutions
Rate is processed key frame, so as to obtain various thumbnails of same key frame, so also can just be obtained for same video
To many set thumbnails, to adapt to different resolution ratio, the demand of different occasion different users is met.
In addition, in the present embodiment or some other embodiments of the invention, in view of the summary viewpoint figure of video may be included
Numerous pictures, in order to save memory space and be easy to management, regard using all thumbnails under same resolution ratio as described
After summary viewpoint figure of the frequency under the resolution ratio, summary viewpoint figure generation module can be with further by following this mode
Summary viewpoint figure to a video is compressed：
All thumbnails under same resolution ratio are constituted into a pictures, and generates system text corresponding with the picture
Part, wherein at least including positional information of each thumbnail in the picture in the system file；
Store the picture and the system file.
Additionally, after storing the picture and the system file, the summary viewpoint figure generation module can be also used for：
Receive request of the client to the summary viewpoint figure of the video；
Obtain the resolution ratio corresponding to the client；
The picture and corresponding system file under the resolution ratio that acquisition is stored；
The picture is split as by thumbnail according to the system file and the client is sent to.
So, the problem of different resolution is also contemplated in generation summary viewpoint figure, many set summary viewpoint figures are generated,
The need for so as to meet all kinds of clients.Additionally, in the present embodiment, being combined into when taking storage to summary viewpoint figure big
Figure splits into the storage management mode that small figure is transmitted again when storing, using, and saves memory space, has been also convenient for management.
On the device in above-described embodiment, wherein unit module perform the concrete mode of operation relevant
It has been described in detail in the embodiment of the method, explanation will be not set forth in detail herein.
The embodiment of the invention also discloses a kind of nonvolatile computer storage media, the computer that is stored with is executable to be referred to
Order, the computer executable instructions are set to：
Divide video into multiple video segments；
For video segment each described：If including key frame in the video segment, the key frame is extracted, its
Described in key frame be video pictures in occurrence scene change when frame of video；
The summary viewpoint figure of the video is generated according to all described key frame for extracting.
Figure 13 is the electricity of the method for the execution generation video frequency abstract viewpoint figure according to an exemplary embodiment of the invention
The hardware architecture diagram of sub- equipment, as shown in figure 13, the equipment includes：
One or more processors 1310 and memory 1320, in Figure 13 by taking a processor 1310 as an example.
The electronic equipment for performing the method for generation video frequency abstract viewpoint figure can also include：Input unit 1330 and output are filled
Put 1340.
Processor 1310, memory 1320, input unit 1330 and output device 1340 can by bus or other
Mode is connected, in Figure 13 as a example by being connected by bus.
Memory 1320 can be used to store non-volatile software journey as a kind of non-volatile computer readable storage medium storing program for executing
Sequence, non-volatile computer executable program and module, the side of the generation video frequency abstract viewpoint figure such as in the embodiment of the present invention
Corresponding programmed instruction/the module of method is (for example, video division module 901, key-frame extraction module 902 and summary shown in accompanying drawing 9
Viewpoint figure generation module 903).Processor 1310 is by running the non-volatile software program stored in memory 1320, referring to
Order and module, so that the various function application of execute server and data processing, that is, realize that above method embodiment is generated
The method of video frequency abstract viewpoint figure.
Memory 1320 can include storing program area and storage data field, wherein, storing program area can store operation system
Application program required for system, at least one function；Storage data field can store the device according to generation video frequency abstract viewpoint figure
Use created data etc..Additionally, memory 1320 can include high-speed random access memory, can also include non-easy
The property lost memory, for example, at least one disk memory, flush memory device or other non-volatile solid state memory parts.One
In a little embodiments, memory 1320 is optional including the memory remotely located relative to processor 1310, these remote memories
Can be by network connection to the device for generating video frequency abstract viewpoint figure.The example of above-mentioned network include but is not limited to internet,
Intranet, LAN, mobile radio communication and combinations thereof.
Input unit 1330 can receive the data such as video file, information or instruction.Output device 1340 may include display screen
Deng display device, and or, the PORT COM such as wired or wireless network interface.
One or more of modules are stored in the memory 1320, when by one or more of processors
During 1310 execution, the method for performing the generation video frequency abstract viewpoint figure in above-mentioned any means embodiment.
The method that the executable embodiment of the present invention of the said goods is provided, possesses the corresponding functional module of execution method and has
Beneficial effect.Not ins and outs of detailed description in the present embodiment, reference can be made to the method that the embodiment of the present invention is provided.
The electronic equipment of the embodiment of the present invention exists in a variety of forms, including but not limited to:
Mobile communication equipment:The characteristics of this kind equipment is that possess mobile communication function, and to provide speech, data communication
It is main target.This Terminal Type includes:Smart mobile phone (such as iPhone), multimedia handset, feature mobile phone, and low side hand
Machine etc..
Super mobile personal computer equipment:This kind equipment belongs to the category of personal computer, there is calculating and processing function, one
As also possess mobile Internet access characteristic.This Terminal Type includes:PDA, MID and UMPC equipment etc., such as iPad.
Portable entertainment device:This kind equipment can show and play content of multimedia.The kind equipment includes:Audio, regard
Frequency player (such as iPod), handheld device, e-book, and intelligent toy and portable car-mounted navigation equipment.
Server:The equipment for providing the service of calculating, the composition of server includes processor, hard disk, internal memory, system bus
Deng, server is similar with general computer architecture, but due to needing to provide highly reliable service, therefore disposal ability,
The requirement of the aspects such as stability, reliability, security, scalability, manageability is higher.
Other have the electronic installation of data interaction function.
Device embodiment described above is only schematical, wherein the unit illustrated as separating component can
To be or may not be physically separate, the part shown as unit can be or may not be physics list
Unit, you can with positioned at a place, or can also be distributed on multiple NEs.It can according to the actual needs be selected
In some or all of module realize the purpose of this embodiment scheme.
Through the above description of the embodiments, those skilled in the art can be understood that each implementation method can
Realized by the mode of software plus general hardware platform, naturally it is also possible to by hardware.Based on such understanding, above-mentioned technology
The part that scheme substantially contributes to correlation technique in other words can be embodied in the form of software product, the computer
Software product can be stored in a computer-readable storage medium, and such as ROM/RAM, magnetic disc, CD, including some instructions are used to
So that computer equipment (can be personal computer, server, or network equipment etc.) perform each embodiment or
Method described in some parts of embodiment.
Finally it should be noted that：The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
The present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those within the art that：It still may be used
Modified with to the technical scheme described in foregoing embodiments, or equivalent is carried out to which part technical characteristic；
And these modification or replace, do not make appropriate technical solution essence depart from various embodiments of the present invention technical scheme spirit and
Scope.
Claims (10)
1. it is a kind of generate video frequency abstract viewpoint figure method, it is characterised in that methods described includes：
Divide video into multiple video segments；
For video segment each described：If including key frame in the video segment, the key frame is extracted, wherein institute
It is frame of video when occurrence scene changes in video pictures to state key frame；
The summary viewpoint figure of the video is generated according to all described key frame for extracting.
2. method according to claim 1, it is characterised in that if including key frame in the video segment, extract
The key frame, including：
It is multiple picture sub-blocks by each the frame of video cutting in the video segment；
According to preset algorithm, the center histogram of gradients of the center sub-block of each frame of video is obtained, wherein the center sub-block is
Positioned at the picture sub-block of central area；
Judge the mean square error of center histogram of gradients of two adjacent video frames whether more than first threshold；
If the mean square error is more than the first threshold, one or two extracted in the two adjacent video frames is regarded
Frequency frame is used as key frame.
3. method according to claim 2, it is characterised in that the video is generated according to all described key frame for extracting
Summary viewpoint figure before, methods described also includes：
Judge previous video segment in two adjacent video fragment last key frame and first of latter video segment
Whether the mean square error of key frame is more than the first threshold；
If no more than described first threshold, last key frame or latter video segment of previous video segment are filtered
First key frame.
4. method according to claim 1, it is characterised in that the video is generated according to all described key frame for extracting
Summary viewpoint figure before, methods described also includes：
Calculate the signal to noise ratio of each key frame；
Filter key frame of the signal to noise ratio less than Second Threshold.
5. method according to claim 1, it is characterised in that the video is generated according to all described key frame for extracting
Summary viewpoint figure, including：
Obtain each thumbnail of the key frame under different resolution；
Summary viewpoint figure using all thumbnails under same resolution ratio as the video under the resolution ratio.
6. it is a kind of generate video frequency abstract viewpoint figure device, it is characterised in that described device includes：
Video division module, for dividing video into multiple video segments；
Key-frame extraction module, for for video segment each described, if including key frame in the video segment, carrying
The key frame is taken, wherein the key frame is frame of video when occurrence scene changes in video pictures；
Summary viewpoint figure generation module, the summary viewpoint figure for generating the video according to all described key frame for extracting.
7. device according to claim 6, it is characterised in that the key-frame extraction module includes：
Frame of video processes submodule, for being multiple picture sub-blocks by each the frame of video cutting in the video segment, according to
Preset algorithm, obtains the center histogram of gradients of the center sub-block of each frame of video, wherein the center sub-block is positioned at center
The picture sub-block in region；
Key frame judging submodule, for judging whether the mean square error of center histogram of gradients of two adjacent video frames is more than
First threshold, if the mean square error is more than the first threshold, extract one in the two adjacent video frames or
Two frame of video are used as key frame.
8. device according to claim 7, it is characterised in that described device also includes：
First key frame filtering module, for being regarded according to all described key frame generation extracted in the summary viewpoint figure
Before the summary viewpoint figure of frequency, judge last key frame of previous video segment in two adjacent video fragment and latter regard
Whether the mean square error of first key frame of frequency fragment is more than the first threshold, if no more than described first threshold
Value, then filter last key frame of previous video segment or first key frame of latter video segment.
9. device according to claim 6, it is characterised in that described device also includes：
Second key frame filtering module, for being regarded according to all described key frame generation extracted in the summary viewpoint figure
Before the summary viewpoint figure of frequency, the signal to noise ratio of each key frame is calculated, filter key frame of the signal to noise ratio less than Second Threshold.
10. device according to claim 6, it is characterised in that the summary viewpoint figure generation module is used for：
Obtain each thumbnail of the key frame under different resolution；
Summary viewpoint figure using all thumbnails under same resolution ratio as the video under the resolution ratio.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611101886.4A CN106713964A (en) | 2016-12-05 | 2016-12-05 | Method of generating video abstract viewpoint graph and apparatus thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611101886.4A CN106713964A (en) | 2016-12-05 | 2016-12-05 | Method of generating video abstract viewpoint graph and apparatus thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106713964A true CN106713964A (en) | 2017-05-24 |
Family
ID=58935581
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611101886.4A Pending CN106713964A (en) | 2016-12-05 | 2016-12-05 | Method of generating video abstract viewpoint graph and apparatus thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106713964A (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107222795A (en) * | 2017-06-23 | 2017-09-29 | 南京理工大学 | A kind of video abstraction generating method of multiple features fusion |
| CN107360476A (en) * | 2017-08-31 | 2017-11-17 | 苏州科达科技股份有限公司 | Video abstraction generating method and device |
| CN107872683A (en) * | 2017-11-21 | 2018-04-03 | 广州视源电子科技股份有限公司 | A kind of video data handling procedure, device, equipment and storage medium |
| CN107948646A (en) * | 2017-09-26 | 2018-04-20 | 北京字节跳动网络技术有限公司 | A kind of video abstraction generating method and video re-encoding method |
| WO2019007020A1 (en) * | 2017-07-05 | 2019-01-10 | 优酷网络技术（北京）有限公司 | Method and device for generating video summary |
| CN109511004A (en) * | 2017-09-14 | 2019-03-22 | 中兴通讯股份有限公司 | A kind of method for processing video frequency and device |
| CN109525901A (en) * | 2018-11-27 | 2019-03-26 | Oppo广东移动通信有限公司 | Method for processing video frequency, device, electronic equipment and computer-readable medium |
| CN110087142A (en) * | 2019-04-16 | 2019-08-02 | 咪咕文化科技有限公司 | A kind of video segment method, terminal and storage medium |
| CN110324706A (en) * | 2018-03-30 | 2019-10-11 | 优酷网络技术（北京）有限公司 | A kind of generation method, device and the computer storage medium of video cover |
| CN110545470A (en) * | 2018-05-29 | 2019-12-06 | 北京字节跳动网络技术有限公司 | Media file loading method and device and storage medium |
| WO2020010997A1 (en) * | 2018-07-09 | 2020-01-16 | 腾讯科技（深圳）有限公司 | Video frame extraction method and apparatus, computer readable medium, and electronic device |
| CN110798735A (en) * | 2019-08-28 | 2020-02-14 | 腾讯科技（深圳）有限公司 | Video processing method and device and electronic equipment |
| CN110830852A (en) * | 2018-08-07 | 2020-02-21 | 北京优酷科技有限公司 | Video content processing method and device |
| CN111078078A (en) * | 2019-11-29 | 2020-04-28 | 深圳市咨聊科技有限公司 | Video playing control method, device, terminal and computer readable storage medium |
| CN111078070A (en) * | 2019-11-29 | 2020-04-28 | 深圳市咨聊科技有限公司 | PPT video barrage play control method, device, terminal and medium |
| CN111770386A (en) * | 2020-05-29 | 2020-10-13 | 维沃移动通信有限公司 | Video processing method, video processing device and electronic equipment |
| CN112651336A (en) * | 2020-12-25 | 2021-04-13 | 深圳万兴软件有限公司 | Method, device and computer readable storage medium for determining key frame |
| CN113051233A (en) * | 2021-03-30 | 2021-06-29 | 联想(北京)有限公司 | Processing method and device |
| CN113329139A (en) * | 2020-02-28 | 2021-08-31 | 中国电信股份有限公司 | Video stream processing method, device and computer readable storage medium |
| CN114071226A (en) * | 2022-01-14 | 2022-02-18 | 飞狐信息技术（天津）有限公司 | Video preview graph generation method and device, storage medium and electronic equipment |
| CN114786052A (en) * | 2022-04-29 | 2022-07-22 | 同方知网数字出版技术股份有限公司 | Academic live video fast browsing method based on key frame extraction |
| CN115767031A (en) * | 2022-11-17 | 2023-03-07 | 北京众谊越泰科技有限公司 | Low-delay video monitoring image display method and system for moving loop system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101464893A (en) * | 2008-12-31 | 2009-06-24 | 清华大学 | Method and device for extracting video abstract |
| CN102184221A (en) * | 2011-05-06 | 2011-09-14 | 北京航空航天大学 | Real-time video abstract generation method based on user preferences |
| CN103227963A (en) * | 2013-03-20 | 2013-07-31 | 西交利物浦大学 | Static surveillance video abstraction method based on video moving target detection and tracing |
| US20150055875A1 (en) * | 2012-03-29 | 2015-02-26 | Panasonic Corporation | Site estimation device, site estimation method, and site estimation program |
| CN104992453A (en) * | 2015-07-14 | 2015-10-21 | 国家电网公司 | Target tracking method under complicated background based on extreme learning machine |
-
2016
- 2016-12-05 CN CN201611101886.4A patent/CN106713964A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101464893A (en) * | 2008-12-31 | 2009-06-24 | 清华大学 | Method and device for extracting video abstract |
| CN102184221A (en) * | 2011-05-06 | 2011-09-14 | 北京航空航天大学 | Real-time video abstract generation method based on user preferences |
| US20150055875A1 (en) * | 2012-03-29 | 2015-02-26 | Panasonic Corporation | Site estimation device, site estimation method, and site estimation program |
| CN103227963A (en) * | 2013-03-20 | 2013-07-31 | 西交利物浦大学 | Static surveillance video abstraction method based on video moving target detection and tracing |
| CN104992453A (en) * | 2015-07-14 | 2015-10-21 | 国家电网公司 | Target tracking method under complicated background based on extreme learning machine |
Cited By (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107222795A (en) * | 2017-06-23 | 2017-09-29 | 南京理工大学 | A kind of video abstraction generating method of multiple features fusion |
| WO2019007020A1 (en) * | 2017-07-05 | 2019-01-10 | 优酷网络技术（北京）有限公司 | Method and device for generating video summary |
| CN107360476A (en) * | 2017-08-31 | 2017-11-17 | 苏州科达科技股份有限公司 | Video abstraction generating method and device |
| CN107360476B (en) * | 2017-08-31 | 2019-09-20 | 苏州科达科技股份有限公司 | Video abstraction generating method and device |
| US11582506B2 (en) | 2017-09-14 | 2023-02-14 | Zte Corporation | Video processing method and apparatus, and storage medium |
| CN109511004B (en) * | 2017-09-14 | 2023-09-01 | 中兴通讯股份有限公司 | Video processing method and device |
| CN109511004A (en) * | 2017-09-14 | 2019-03-22 | 中兴通讯股份有限公司 | A kind of method for processing video frequency and device |
| CN107948646A (en) * | 2017-09-26 | 2018-04-20 | 北京字节跳动网络技术有限公司 | A kind of video abstraction generating method and video re-encoding method |
| CN107948646B (en) * | 2017-09-26 | 2019-02-05 | 北京字节跳动网络技术有限公司 | A kind of video abstraction generating method and video re-encoding method |
| CN107872683A (en) * | 2017-11-21 | 2018-04-03 | 广州视源电子科技股份有限公司 | A kind of video data handling procedure, device, equipment and storage medium |
| CN110324706B (en) * | 2018-03-30 | 2022-03-04 | 阿里巴巴（中国）有限公司 | Video cover generation method and device and computer storage medium |
| CN110324706A (en) * | 2018-03-30 | 2019-10-11 | 优酷网络技术（北京）有限公司 | A kind of generation method, device and the computer storage medium of video cover |
| CN110545470A (en) * | 2018-05-29 | 2019-12-06 | 北京字节跳动网络技术有限公司 | Media file loading method and device and storage medium |
| US11200426B2 (en) | 2018-07-09 | 2021-12-14 | Tencent Technology (Shenzhen) Company Limited | Video frame extraction method and apparatus, computer-readable medium |
| WO2020010997A1 (en) * | 2018-07-09 | 2020-01-16 | 腾讯科技（深圳）有限公司 | Video frame extraction method and apparatus, computer readable medium, and electronic device |
| CN110830852A (en) * | 2018-08-07 | 2020-02-21 | 北京优酷科技有限公司 | Video content processing method and device |
| CN110830852B (en) * | 2018-08-07 | 2022-08-12 | 阿里巴巴（中国）有限公司 | Video content processing method and device |
| CN109525901A (en) * | 2018-11-27 | 2019-03-26 | Oppo广东移动通信有限公司 | Method for processing video frequency, device, electronic equipment and computer-readable medium |
| US11601630B2 (en) | 2018-11-27 | 2023-03-07 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Video processing method, electronic device, and non-transitory computer-readable medium |
| CN110087142A (en) * | 2019-04-16 | 2019-08-02 | 咪咕文化科技有限公司 | A kind of video segment method, terminal and storage medium |
| CN110087142B (en) * | 2019-04-16 | 2022-01-25 | 咪咕文化科技有限公司 | Video slicing method, device, terminal and storage medium |
| CN110798735A (en) * | 2019-08-28 | 2020-02-14 | 腾讯科技（深圳）有限公司 | Video processing method and device and electronic equipment |
| CN111078070A (en) * | 2019-11-29 | 2020-04-28 | 深圳市咨聊科技有限公司 | PPT video barrage play control method, device, terminal and medium |
| CN111078078A (en) * | 2019-11-29 | 2020-04-28 | 深圳市咨聊科技有限公司 | Video playing control method, device, terminal and computer readable storage medium |
| CN113329139A (en) * | 2020-02-28 | 2021-08-31 | 中国电信股份有限公司 | Video stream processing method, device and computer readable storage medium |
| CN113329139B (en) * | 2020-02-28 | 2023-11-03 | 天翼云科技有限公司 | Video stream processing method, device and computer readable storage medium |
| CN111770386A (en) * | 2020-05-29 | 2020-10-13 | 维沃移动通信有限公司 | Video processing method, video processing device and electronic equipment |
| CN112651336B (en) * | 2020-12-25 | 2023-09-29 | 深圳万兴软件有限公司 | Method, apparatus and computer readable storage medium for determining key frame |
| CN112651336A (en) * | 2020-12-25 | 2021-04-13 | 深圳万兴软件有限公司 | Method, device and computer readable storage medium for determining key frame |
| CN113051233A (en) * | 2021-03-30 | 2021-06-29 | 联想(北京)有限公司 | Processing method and device |
| CN114071226A (en) * | 2022-01-14 | 2022-02-18 | 飞狐信息技术（天津）有限公司 | Video preview graph generation method and device, storage medium and electronic equipment |
| CN114071226B (en) * | 2022-01-14 | 2022-04-26 | 飞狐信息技术（天津）有限公司 | Video preview graph generation method and device, storage medium and electronic equipment |
| CN114786052A (en) * | 2022-04-29 | 2022-07-22 | 同方知网数字出版技术股份有限公司 | Academic live video fast browsing method based on key frame extraction |
| CN115767031A (en) * | 2022-11-17 | 2023-03-07 | 北京众谊越泰科技有限公司 | Low-delay video monitoring image display method and system for moving loop system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106713964A (en) | Method of generating video abstract viewpoint graph and apparatus thereof | |
| US11500916B2 (en) | Identifying media components | |
| EP2481023B1 (en) | 2d to 3d video conversion | |
| CN109803180B (en) | Video preview generation method and device, computer equipment and storage medium | |
| US9848216B2 (en) | Security and/or tracing video media-content | |
| KR20180030885A (en) | System and method for dividing search indexes for improved efficiency in identifying media segments | |
| EP3234904B1 (en) | Method and apparatus for publishing locational copyrighted watermarking video | |
| Hua et al. | Similarity measure for image resizing using SIFT feature | |
| US11974013B2 (en) | Modifying digital video content | |
| CN111260037B (en) | Convolution operation method and device of image data, electronic equipment and storage medium | |
| CN112215171B (en) | Target detection method, device, equipment and computer readable storage medium | |
| KR20150083355A (en) | Augmented media service providing method, apparatus thereof, and system thereof | |
| CN116188821A (en) | Copyright detection method, system, electronic device and storage medium | |
| CN107864384B (en) | Method and device for redirecting internet video playing on cloud desktop | |
| CN111062854A (en) | Method, device, terminal and storage medium for detecting watermark | |
| CN107592118A (en) | The coding/decoding method and device of Variable Length Code file | |
| CN115527101A (en) | Image tampering detection method and processor | |
| CN111741329B (en) | Video processing method, device, equipment and storage medium | |
| JP5569830B2 (en) | Video processing system, video processing method, video processing apparatus, control method thereof, and control program | |
| CN114697741B (en) | Multimedia information playing control method and related equipment | |
| CN113762040A (en) | Video identification method and device, storage medium and computer equipment | |
| CN109657098B (en) | Video fingerprint extraction method and device | |
| CN113779304A (en) | Method and device for detecting infringement video | |
| CN117176979B (en) | Method, device, equipment and storage medium for extracting content frames of multi-source heterogeneous video | |
| Wang et al. | FISF: Better user experience using smaller bandwidth for panoramic virtual reality video |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170524 |