CN107801093A - Video Rendering method, apparatus, computer equipment and readable storage medium storing program for executing - Google Patents
Video Rendering method, apparatus, computer equipment and readable storage medium storing program for executing Download PDFInfo
- Publication number
- CN107801093A CN107801093A CN201711020523.2A CN201711020523A CN107801093A CN 107801093 A CN107801093 A CN 107801093A CN 201711020523 A CN201711020523 A CN 201711020523A CN 107801093 A CN107801093 A CN 107801093A
- Authority
- CN
- China
- Prior art keywords
- video
- static region
- frame
- area
- region
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000009877 rendering Methods 0.000 title claims abstract description 133
- 238000000034 method Methods 0.000 title claims abstract description 72
- 230000003068 static effect Effects 0.000 claims abstract description 253
- 230000008859 change Effects 0.000 claims abstract description 40
- 230000011218 segmentation Effects 0.000 claims description 34
- 230000008569 process Effects 0.000 claims description 12
- 238000013135 deep learning Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 abstract description 11
- 238000004458 analytical method Methods 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 6
- 238000013136 deep learning model Methods 0.000 description 6
- 230000009471 action Effects 0.000 description 5
- 230000007812 deficiency Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000004043 dyeing Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 230000002045 lasting effect Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000006837 decompression Effects 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
-
- 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)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Television Signal Processing For Recording (AREA)
Abstract
The present invention relates to a kind of Video Rendering method, apparatus, computer equipment and readable storage medium storing program for executing, this Video Rendering method includes:The video and the area identification of video that the reception server is sent, dynamic area and the static region in video are identified according to area identification, playing sequence according to the frame of video in video renders first frame in each frame and current static region of current dynamic area, when current dynamic area and current static region change, first frame of the static region after then rendering each frame of the dynamic area after changing according to the playing sequence of the frame of video in video and change, until Video Rendering is completed.Above-mentioned Video Rendering method, apparatus, computer equipment and readable storage medium storing program for executing save computing resource, improve rendering efficiency, improve the rendering effect of high-resolution video.
Description
Technical field
The present invention relates to field of computer technology, more particularly to a kind of Video Rendering method, apparatus, computer equipment and
Readable storage medium storing program for executing.
Background technology
With the development of science and technology the use range of this intuitively information display methods of video is more and more wider, people for
Show the resolution requirement also more and more higher of video.Panoramic video and 3 D video more meet actual life due to its display effect
In 3D scenes, start to be widely used;To obtain panorama or the more preferable display effect of 3 D video, it usually needs to regarding
Frequency is according to carrying out rendering this operation.
It is the time sequencing according to video file that tradition, which renders process, renders the content of each two field picture;Current main-stream is hard
Part, the rendering capability of software equipment are limited, when rendering high-resolution video data, it is possible that rendering effect difference is asked
There is interim card, fall frame, mosaic in topic, the video after such as rendering.
The content of the invention
Based on this, it is necessary to during for rendering high-resolution video, the problem of rendering effect difference, there is provided a kind of Video Rendering
Method, apparatus, computer equipment and readable storage medium storing program for executing.
A kind of Video Rendering method, including:
The video and the area identification of video that the reception server is sent;
Dynamic area and the static region in video are identified according to area identification;
Playing sequence according to the frame of video in video renders each frame and current static region of current dynamic area
First frame;
When current dynamic area and current static region change, then according to the playing sequence of the frame of video in video
First frame of the static region after rendering each frame of the dynamic area after changing and changing, until Video Rendering is completed.
In one of the embodiments, the step of current dynamic area and current static region change includes:
The duration for the static region that the reception server is sent;
The duration corresponding with current static region is chosen from the duration of the static region received;
When the display time of first frame in current static region being equal to the selected duration, then current dynamic area
Changed with current static region.
A kind of method for processing video frequency, including:
Obtain pending video and Processing Algorithm corresponding with pending video;
By pending Video segmentation it is dynamic area and static region by Processing Algorithm;
Dynamic area and static region Adding Area are identified;
When the video acquisition for receiving client is asked, then by pending video and the area identification of pending video
Send to client.
In one of the embodiments, it is dynamic area and static region by pending Video segmentation by Processing Algorithm
Also include after step:
The duration in statistical static region;
The step of area identification by pending video and pending video is sent to client, including:
The duration of pending video, the area identification of pending video and static region is sent to the client
End.
In one of the embodiments, it is dynamic area and static region by pending Video segmentation by Processing Algorithm
Step, including:
The difference of respective pixel in the consecutive frame of pending video is calculated by Processing Algorithm;
When difference is no more than preset value, then region corresponding to pixel is static region;
When difference exceedes preset value, then region corresponding to pixel is dynamic area.
In one of the embodiments, it is dynamic area and static region by pending Video segmentation by Processing Algorithm
Step, including:
When Processing Algorithm is deep learning algorithm, then Matching Model corresponding with pending video is obtained;
Pending video frequency output is obtained into dynamic area and static region into Matching Model.
A kind of Video Rendering device, including:
Receiving module, the video and the area identification of video sent for the reception server;
Identification module, for identifying dynamic area and static region in video according to area identification;
Rendering module, for rendering each frame of current dynamic area according to the playing sequence of the frame of video in video and working as
First frame of preceding static region;
Judge module, for when current dynamic area and current static region change, then according to regarding in video
The playing sequence of frequency frame renders the first frame of each frame and the static region after change of the dynamic area after changing, until video
Render completion.
A kind of video process apparatus, including:
Algoritic module, for obtaining pending video and Processing Algorithm corresponding with pending video;
Split module, for by pending Video segmentation being dynamic area and static region by Processing Algorithm;
Mark module, for dynamic area and static region Adding Area mark;
Sending module, for when the video acquisition for receiving client is asked, then by pending video and pending
The area identification of video is sent to client.
A kind of computer equipment, including memory, processor and storage can be run on a memory and on a processor
Computer program, the step in the above method is realized during the computing device described program.
A kind of readable storage medium storing program for executing, is stored thereon with computer program, and the program realizes above-mentioned side when being executed by processor
Step in method.
Above-mentioned Video Rendering method, apparatus, computer equipment and storage medium, it is not required in all videos of real-time rendering
Hold, but be dynamic area and static region by Video segmentation to be rendered, when performing Rendering operations, only render current static area
First frame in domain, and continue using this frame after rendering, also need to be split according to the actual conditions real-time update of video to be rendered
Dynamic area afterwards and static region;Only render the first frame of static region and continue to use, save computing resource, improve
Rendering efficiency so that when rendering apparatus under same rendering efficiency, can render the video data of higher resolution, improve
The rendering effect of high-resolution video.
Brief description of the drawings
Fig. 1 is Video Rendering method application scenario diagram in an embodiment;
Fig. 2 is the flow chart of Video Rendering method in an embodiment;
Fig. 3 is that current dynamic area and the current static region change in Video Rendering method in an embodiment
The flow chart of step;
Fig. 4 is the flow chart of method for processing video frequency in an embodiment;
Fig. 5 is the structure chart of Video Rendering device in an embodiment;
Fig. 6 is the structure chart of video process apparatus in an embodiment;
Fig. 7 is the structural representation for the computer equipment that Video Rendering is performed in an embodiment;
Fig. 8 is the structural representation for the computer equipment that Video processing is performed in an embodiment.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that specific embodiment described herein is used only for explaining the present invention, and
It is not used in the restriction present invention.
Describe in detail according to an embodiment of the invention before, it should be noted that, described embodiment essentially consist in
The step of Video Rendering method, apparatus, computer equipment and readable storage medium qualitative correlation and the combination of system component.Therefore, institute
Category system component and method and step are showed in position by ordinary symbol in the accompanying drawings, and are only shown
The details relevant with understanding embodiments of the invention, so as not to because for have benefited from those of ordinary skill in the art of the present invention and
Those obvious details of speech have obscured the disclosure.
Herein, such as left and right, upper and lower, front and rear, first and second etc relational terms are used merely to area
Divide an entity or action and another entity or action, and not necessarily require or imply and be between this entity or action any
Actual this relation or order.Term " comprising ", "comprising" or any other variant are intended to including for nonexcludability, by
This make it that including the process of a series of elements, method, article or equipment not only includes these key elements, but also comprising not bright
The key element that the other element really listed is either this process, method, article or equipment are intrinsic.
Fig. 1 is referred to, Fig. 1 provides Video Rendering method application scenario diagram in an embodiment, set including Video Rendering
Standby and video server, Video Rendering equipment and video server can carry out network connection, and Video Rendering equipment can be 3D
Video playback apparatus, such as 3D glasses or computer equipment, video processnig algorithms are provided with video server, by corresponding
Pending Video segmentation is dynamic area and static region and identified by algorithm, and the video after mark then is sent into video wash with watercolours
Dyeing equipment;Video Rendering equipment receives the video of video server transmission and the area identification of video, is known according to area identification
Other dynamic area and static region, real-time rendering dynamic area and the content for updating dynamic area, and static region is only rendered
First frame simultaneously continues to use, and when static region changes, is rendered according to the region after change according to the foregoing mode that renders, until whole
Individual Video Rendering is completed so that Video Rendering equipment can be according to the algorithm of video server, the dynamic area to being partitioned into respectively
Domain and static region carry out different Rendering operations.
Refer to Fig. 2, there is provided a kind of flow chart of Video Rendering method, the present embodiment are applied to above-mentioned Fig. 1 in this way
In Video Rendering equipment come for example, in the Video Rendering equipment operation have Video Rendering program, pass through the Video Rendering
Program renders to the video to be rendered that video server is sent.This method comprises the following steps:
S202:The video and the area identification of video that the reception server is sent.
Wherein, area identification is that server is treated after render video analyzed, dynamic to can distinguishing for the video labeling
State region and the mark of static region.Such as this mark can be label or flag bit;Spy is preset such as in video data
Positioning is used as flag bit, and if dynamic area, then the flag is 0, and if static region, then the flag is 1;Or regarding
Frequency file is finally specified in digit and sets particular piece of data, and the particular piece of data is the dynamic area and quiet in video to be rendered
Pixel coordinate section corresponding to the difference of state region.
Specifically, after video to be rendered is divided into dynamic area and static region by server according to respective algorithms, according to
Video after mark is sent to Video Rendering equipment by the request of Video Rendering equipment.And the band generally taken up due to video file
It is wide larger, the operation such as the video to be rendered after mark can be encoded and be compressed before sending, to facilitate transmission, be serviced in addition
Static region in the video to be rendered that device is sent to Video Rendering equipment can only include in the duration of the static region
The first frame in static region, to reduce transmission quantity.
S204:Dynamic area and the static region in video are identified according to area identification.
Specifically, Video Rendering equipment receive server transmission mark after video to be rendered after, it is to be rendered to this
Video is rendered, and reads the area identification of video first before rendering, and the dynamic area of video is got according to area identification
And static region.Wherein, if video to be rendered has been encoded or compressed in server end, Video Rendering equipment is then first right
This document carries out the operations such as corresponding decoding and decompression;Further according to area identification, dynamic corresponding with area identification is identified
Region and static region.
S206:Playing sequence according to the frame of video in video renders each frame and current static area of current dynamic area
First frame in domain.
Specifically, Video Rendering equipment is identifying the dynamic area of the video to be rendered of server mark and static region
Afterwards, real-time rendering is carried out according to rendering requirements to all the elements of dynamic area, i.e., for dynamic area, according to broadcasting for frame of video
Put forward the image that sequence renders each frame;And for static region, in a period of time, the video content of static region is not substantially
Change, it is not necessary to real-time update, therefore when a certain region is identified as static region, only need to render this region and be identified
For the first two field picture in the time of static region, and all the time using the first frame after rendering within the duration of static region
Image is shown.
For example, a video file includes 20 frames.The first area of each of which frame is dynamic area, and second area is quiet
State region, when rendering, the dynamic area of 10 two field picture is rendered in sequence, and only render the static zones of the first frame
Domain, and in continuously display 20 frame the first frame second area, and the every of the first area after rendering is shown by video playback order
One frame, until 20 two field pictures render completion.
S208:When current dynamic area and current static region change, then broadcasting according to the frame of video in video
The first frame of the static region after sequence renders each frame of the dynamic area after changing and changed is put forward, until Video Rendering is complete
Into.
Specifically, if current dynamic area and current static region change, i.e., first frame in current static region is not
Corresponding region in next frame can be represented again, then the static state in next two field picture is obtained according to the area identification of next two field picture
Region, and the static region in the duration of the static region in next two field picture only in render image, and hold
The continuous dynamic area for rendering subsequent image frames.
For example, in the video file of above-mentioned 20 frame, the first area of each frame is dynamic area in preceding 10 frame, second area
For static region, and the first area of each frame is static region in the 11st to 20 frame, and second area is dynamic area;Rendering
When, first the second area of preceding 10 two field picture is rendered in sequence, and the first area of the 1st frame is only rendered, and in preceding 10 frame
All the time the first area of the 1st frame is shown, and the second area of each frame is shown by the playing sequence of 10 frame videos;Then in order
The first area in the 11st to 20 frame is rendered, and only renders the second area of the 11st frame, and in the 11st to 20 frame, is shown all the time
The first area of each frame for showing this 10 frame in order of the second area sum of 11st frame, until the display of 20 two field pictures is completed.
Above-mentioned Video Rendering method, all the elements that Video Rendering equipment is not required to treat render video are rendered, only
The first frame of the static region identified is rendered, and shows the first of static region all the time within the duration of this static region
Two field picture, the image of dynamic area need to be only updated, saves the computing resource for rendering each two field picture of static region, improved
The rendering efficiency of rendering apparatus so that current Video Rendering equipment can support the wash with watercolours to the video file of higher resolution
Dye requires, avoids the occurrence of when video resolution to be rendered is higher, the computing capability deficiency of rendering apparatus, and interim card occurs, fall
The problems such as frame, mosaic, improve the rendering effect to high-resolution video.
Fig. 3 is referred to, in a wherein embodiment, current dynamic area and current quiet in the step S208 in the above method
The step of state region changes can include:
S302:The duration for the static region that the reception server is sent.
Specifically, server to video when carrying out dynamic analysis, when certain region is identified as static state within a certain period of time
Region, and when the region is all identified as static region in follow-up continuous several frames, server then counts the static region
Duration, i.e., within the duration, the position of corresponding static region is fixed, and after reaching the duration, dynamic
Region and the position of static region change.Rendering apparatus also connects while the video to be rendered that the reception server is sent
Receive the duration of the corresponding static region of server mark.
S304:The duration corresponding with current static region is chosen from the duration of the static region received.
Specifically, Video Rendering equipment is chosen according to current static region from the duration of received static region
To the duration of static region.Such as Video Rendering equipment is carried out to video in render video according to video playback order
Rendered, the duration of the static region can also be ranked up according to video playback order, if Video Rendering equipment is opened
Beginning when rendering current static region, then directly reads the duration in current static region, if current static region it is lasting when
Between when reaching, then continue the static region in render picture frame, and read continuing for next static region in sequence
The duration of time, i.e. next frame picture frame.
S306:It is when the display time of first frame in current static region being equal to the selected duration, then current dynamic
State region and current static region change.
Specifically, when the display time of the first frame of a certain static region being equal to the duration of corresponding static region,
Then think that dynamic area and the static region of the next frame of video to be rendered are different from previous frame, it is necessary to according to the dynamic newly identified
Region and static region continue render video, i.e., identify the static region and dynamic area in next image frame according to area identification
Domain, and rendered in the manner described above.
Wherein, if having multiple dynamic areas and multiple static regions, it is necessary to count respectively simultaneously in a video file
The duration of each static region, after wherein the first static region reaches its duration, in next frame picture frame, the
One static region changes, and the display time of other static regions is not equal to the corresponding duration, then next two field picture
In frame, the display image of the first static region changes, and other static regions do not change and still show pair after rendering
Answer the first two field picture in the current duration of static region.Such as the first static region and the in a certain video file be present
During two static regions, duration of the first static region is 1 second, and the duration of the second static region is 2 seconds, when first quiet
When state region is changed into dynamic area after 1 second, when Video Rendering equipment can still keep the second static region display correspondence persistently
The first interior frame, without rendering the first frame of the second static region after 1 second again.
When rendering the video of complexity, single area identification can not accurately reflect the image change situation of video.Service
Device is needed to area identification corresponding to the video progress of complexity, and counts the duration of the static region after mark, and video
Rendering apparatus enables to each static region only reaching the duration corresponding to this static region by the above method
When, just need to render and show the content of next frame, by other static regions will not be changed is influenceed.Rendering regarding for complexity
During frequency, the rendering effect of video had both been ensure that, has also saved the computing resource of rendering apparatus to the full extent.
Above-described embodiment, Video Rendering equipment are judged static region and moved by the duration corresponding with static region
The situation of change in state region, by the method server can be made more accurately to identify the situation of change of video to be rendered, depending on
Frequency rendering apparatus can also realize more accurate rendering effect according to the recognition result of server.
Fig. 4 is referred to, Fig. 4 provides the flow chart of method for processing video frequency in an embodiment, and the present embodiment is applied in this way
Come to the server in above-mentioned Fig. 1 for example, on the server operation have video processing program, pass through the video processing program
To handle pending video.This method comprises the following steps:
S402:Obtain pending video and Processing Algorithm corresponding with pending video.
Specifically, server obtains pending video, and is joined according to the complexity of pending video and processing requirement etc.
Processing Algorithm corresponding to number selection, to carry out dynamic analysis to pending video.Such as each server can be set as needed
Corresponding Processing Algorithm is put, so as to when pending video is transferred to the server, then directly obtain corresponding to server and locate
Adjustment method is handled pending video.Or each pending video carries complexity and processing requirement ginseng
Count, server Processing Algorithm corresponding to according to the complexity and processing requirement parameter acquiring, in the case of this kind, server can
To preset the weight of the rank M of complexity and processing requirement level n, such as respectively m and n, Processing Algorithm is then calculated
Grade=M × m+N × n, obtain corresponding algorithm further according to the grade of resulting algorithm.Wherein, Processing Algorithm can be
Frame differential method, deep learning algorithm or edge detection method etc..
S404:By pending Video segmentation it is dynamic area and static region by Processing Algorithm.
Specifically, dynamic analysis are carried out to pending video by above-mentioned Processing Algorithm, is by pending Video segmentation
Dynamic area and static region, so that client is to Rendering operations corresponding to the different zones progress of pending video:Real-time wash with watercolours
Dynamic area is contaminated, and the first frame is only rendered to static region and continues to use;When static region changes, according to the area after change
Domain renders according to the foregoing mode that renders, until whole Video Rendering is completed.
S406:Dynamic area and static region Adding Area are identified.
Wherein, area identification is that server is treated after render video analyzed, dynamic to can distinguishing for the video labeling
State region and the mark of static region.Such as this mark can be label or flag bit;Spy is preset such as in video data
Positioning is used as flag bit, and if dynamic area, then the flag is 0, and if static region, then the flag is 1;Or regarding
Frequency file is finally specified in digit and sets particular piece of data, and the particular piece of data is the dynamic area and quiet in video to be rendered
Pixel coordinate section corresponding to the difference of state region.
S408:When the video acquisition for receiving client is asked, then by the area of pending video and pending video
Domain identifier is sent to client.
Wherein, video acquisition request is the acquisition video to be rendered that client (i.e. Video Rendering equipment) is sent to server
Request, video to be rendered is the video after server process, including pending video and area identification.
Specifically, the bandwidth generally taken up due to video file is larger, can be before sending to the video to be rendered after mark
Encoded and the operation such as compress, to facilitate transmission, in the video to be rendered that server is sent to Video Rendering equipment in addition
Static region can only include the static region in the first frame in the duration of the static region, to reduce transmission quantity.Visitor
After pending video and the area identification of pending video that family end the reception server is sent, according to above-mentioned Video Rendering method
This video is rendered.
In above-mentioned method for processing video frequency, pending Video segmentation is by server by pending video according to respective algorithms
State region and static region, and the dynamic area after segmentation and static region tab area are identified, then by pending video
Client is sent jointly to area identification, passes through this operation of the segmentation of dynamic area and static region so that Video Rendering
Equipment (i.e. client) can treat render video according to the situation of change of different zones and perform the Rendering operations adapted to, video wash with watercolours
All the elements that dyeing equipment is not required to treat render video are rendered, and only render the first frame of the static region identified, and
All the time the first two field picture of static region is shown in the duration of this static region, only need to update the image of dynamic area i.e.
Can, the computing resource for rendering each two field picture of static region is saved, improves the rendering efficiency of rendering apparatus so that current
Video Rendering equipment can support the rendering requirements to the video file of higher resolution, avoid the occurrence of and differentiated in video to be rendered
When rate is higher, the computing capability deficiency of rendering apparatus, and interim card occur, fall the problems such as frame, mosaic, improve to high-resolution
The rendering effect of video.
In one of the embodiments, when selected algorithm is frame differential method, the step S404 shown in Fig. 4,
The step of i.e. by Processing Algorithm by pending Video segmentation being dynamic area and static region, can include:Pass through Processing Algorithm
Calculate the difference of respective pixel in the consecutive frame of pending video;When difference is no more than preset value, then region corresponding to pixel
For static region;When difference exceedes preset value, then region corresponding to pixel is dynamic area.
Wherein, frame differential method subtracts each other the corresponding pixel points of consecutive frame, when obtained by a region all pixels point
When the absolute value of difference is respectively less than preset value in several consecutive frames, this region is static region, conversely, being then dynamic area.
Above-mentioned difference can be the difference of consecutive frame corresponding pixel points brightness;The gray value of image can also be calculated, upper several differences take phase
The difference of the gray value of adjacent frame corresponding pixel points.
Specifically, server subtracts each other to the brightness value of pixel or gray value corresponding to the consecutive frame of pending video,
When gained difference both less than preset value in continuous several consecutive frames of a pixel, this pixel is static pixels;Work as phase
When adjacent pixel exceedes static pixels threshold value, this some adjacent pixel is collectively referred to as static region.
For example, a pending video totally 20 frame, wherein include 10 pixels per frame, the brightness of the every two field picture of server extraction
Value or gray value, and since the first frame, by corresponding pixel in each pixel in every two field picture and next two field picture
Point subtracts each other, and obtains difference, if the absolute value of the difference of preceding 5 pixels in 20 two field pictures is respectively less than threshold value, first 5
Pixel is referred to as static pixels, and the default static pixels threshold value of server is 3, and preceding 5 static pixels are adjacent and meet
The condition of static region is formed, then preceding 5 pixels of every two field picture of this video are collectively referred to as static region.
Dynamic analysis are carried out to pending video using frame difference method in above-described embodiment, can be corresponding by consecutive frame
The change of corresponding region in the differential analysis video of pixel, by way of setting threshold value, draws the situation of change of respective pixel,
It is static region that unconspicuous partial segmentation, which will be changed, and it is dynamic area to change obvious partial segmentation, and to dynamic after segmentation
State region and static region Adding Area mark, so as to client different region is performed corresponding to Rendering operations, and interframe
Differential technique is applicable to all video files, enters action to video according to the situation of change of the brightness of video file or gray scale
State is analyzed, and is had a wide range of application.
In one of the embodiments, when selected algorithm is deep learning algorithm, the step of shown in Fig. 4
The step of pending Video segmentation that is, by Processing Algorithm is dynamic area and static region by S404 can include:Pass through place
Adjustment method obtains Matching Model corresponding with the pending video;By the pending video frequency output into the Matching Model
Obtain dynamic area and static region.
Specifically, deep learning algorithm, i.e. server can analyzing to pending video, identify pending video
Main body, and deep learning model is established according to main body, then according to deep learning model, by each frame in pending video
Matched with deep learning model.
For example, in a video processing operation, server is analyzed 10 frames before pending video, is identified at this
The main body (such as certain personage) of the pending video of 10 frames, and deep learning model is established according to main body, then according to deep learning mould
Type, each frame in pending video is matched with deep learning model, then can be with deep learning model in each frame
The pixel region of matching is dynamic area, and other regions are static region, i.e., in this 10 frame video, personage's main body for identifying
Movement locus and the region of variation of figure action be dynamic area.
In above-described embodiment using deep learning algorithm to pending video carry out dynamic analysis, server can by
Main body with pending video, main part corresponding with Matching Model is divided into dynamic area, other region segmentations are quiet
State region, and the dynamic area after segmentation and static region Adding Area are identified, so that client performs to different regions
Corresponding Rendering operations so that client can not do reality according to the movement locus of main render video main body for other regions
When render and update, make Rendering operations more intelligent, more targetedly.
In one of the embodiments, above-mentioned method for processing video frequency can also comprise the following steps:Statistical static region
Duration.Accordingly, step S408, i.e., when the video acquisition for receiving client is asked, then by pending video and
The area identification of pending video, which is sent to client, can include, when the video acquisition for receiving client is asked, waiting to locate
Reason video, the area identification of pending video and the duration of static region are sent to the client.
Specifically, server obtains pending video, and after selection Processing Algorithm corresponding with pending video, according to place
Adjustment method carries out dynamic analysis to video, is dynamic area and static region by pending Video segmentation, and to dynamic after segmentation
State region and static region Adding Area mark, when certain region is identified as static region within a certain period of time, and the region exists
When being all identified as static region in follow-up continuous several frames, server then counts the duration of the static region, that is, is holding
In the continuous time, the position of corresponding static region is fixed, and after reaching the duration, dynamic area and static region
Position changes, when the video acquisition for receiving client is asked, by the duration of static region and pending video,
The area identification of pending video is sent to the client together, in order to which client is according to the duration of the static region
To judge whether the position of static region and dynamic area changes.
Further, when a certain static region is identified as static state in continuous multiple frames (quantity that can voluntarily set successive frame)
During region, then the duration of the reproduction time of this continuous multiple frames, as static region is counted.Server is done to pending video
After complete above-mentioned processing, the duration of pending video, area identification and static region is sent to client.
Video Rendering equipment receives the duration of the pending video, area identification and static region, from being received
Duration to static region chooses the duration for the static region currently to be rendered.Such as Video Rendering equipment is rendering
During video, according to video playback order render video, the duration of the static region can also be according to video
Playing sequence is ranked up, if Video Rendering equipment starts to render current static region, directly reads current static region
Duration, if current static region duration reach, continue render picture frame in static region,
And read the duration of next static region in sequence, i.e. duration of next frame picture frame.
Above-described embodiment, Video Rendering equipment are judged static region and moved by the duration corresponding with static region
The situation of change in state region, by the method server can be made more accurately to identify the situation of change of video to be rendered, depending on
Frequency rendering apparatus can also realize more accurate rendering effect according to the recognition result of server.
In one of the embodiments, reference can be made to Fig. 5, there is provided the structural representation of a Video Rendering device, the video wash with watercolours
Dye device 500 includes:
Receiving module 502, the video and the area identification of video sent for the reception server.
Identification module 504, for identifying dynamic area and static region in video according to area identification.
Rendering module 506, for rendering each frame of current dynamic area according to the playing sequence of the frame of video in video
With first frame in current static region.
Judge module 508, for when current dynamic area and current static region change, then according in video
The playing sequence of frame of video renders the first frame of each frame and the static region after change of the dynamic area after changing, until regarding
Frequency renders completion.
In one of the embodiments, the judge module 518 in above-mentioned Video Rendering equipment 510 includes:
Receiving unit, the duration of the static region sent for the reception server.
Unit is chosen, for choosing hold corresponding with current static region from the duration of the static region received
The continuous time.
Judging unit, when the display time for the first frame when current static region is equal to the selected duration,
Then current dynamic area and current static region change.
The above-mentioned specific restriction on Video Rendering device may refer to the restriction above in connection with Video Rendering method,
This is repeated no more.
In one of the embodiments, reference can be made to Fig. 6, there is provided the structural representation of a video process apparatus, Video processing
Device 600 includes:
Algoritic module 602, for obtaining pending video and Processing Algorithm corresponding with pending video.
Split module 604, for by pending Video segmentation being dynamic area and static region by Processing Algorithm.
Mark module 606, for dynamic area and static region Adding Area mark.
Sending module 608, for when the video acquisition for receiving client is asked, then by pending video and waiting to locate
The area identification of reason video is sent to client.
In one of the embodiments, video process apparatus can also include:
Timing module, the duration for statistical static region.
Above-mentioned sending module is additionally operable to send the duration of static region to client.
In one of the embodiments, the segmentation module 604 in above-mentioned video process apparatus 610 can include:
Computing unit, the difference of respective pixel in the consecutive frame for calculating pending video by Processing Algorithm.
First cutting unit, for when difference is no more than preset value, then region corresponding to pixel to be static region.It is on duty
When value exceedes preset value, then region corresponding to pixel is dynamic area.
In one of the embodiments, the segmentation module 604 in above-mentioned video process apparatus 610 can include:
Acquiring unit, for when Processing Algorithm is deep learning algorithm, then obtaining matching corresponding with pending video
Model.
Second cutting unit, for pending video frequency output to be obtained into dynamic area and static region into Matching Model.
The above-mentioned specific restriction on video process apparatus may refer to the restriction above in connection with method for processing video frequency,
This is repeated no more.
In one of the embodiments, Fig. 7 is referred to, there is provided one performs the structural representation of the computer equipment of Video Rendering
Figure, the computer equipment can perform Video Rendering equipment, be General Server or other any suitable computer equipments, bag
The Video Rendering that includes memory, processor, operating system, database and storage on a memory and can run on a processor
Program, wherein memory can include built-in storage, realize following steps during computing device Video Rendering program:Receive service
The video and the area identification of video that device is sent;Dynamic area and the static region in video are identified according to area identification;Press
According to the frame of video in video playing sequence render current dynamic area each frame and current static region the first frame;When work as
When preceding dynamic area and current static region change, then after rendering change according to the playing sequence of the frame of video in video
First frame of the static region after each frame of dynamic area and change, until Video Rendering is completed.
In one of the embodiments, the current dynamic area realized during computing device program and the current static
The step of region changes can include:The duration for the static region that the reception server is sent, from the static state received
The duration corresponding with current static region is chosen in the duration in region, when the display of first frame in current static region
When time is equal to the selected duration, then current dynamic area and current static region change.
The above-mentioned specific restriction on computer equipment may refer to the restriction above in connection with Video Rendering method, herein
Repeat no more.
In one embodiment, please continue to refer to Fig. 7, there is provided a kind of computer-readable storage medium, be stored thereon with computer
Program, the program realize following steps when being executed by processor:The video and the area identification of video that the reception server is sent;
Dynamic area and the static region in video are identified according to area identification;Playing sequence according to the frame of video in video, which renders, works as
First frame in each frame and current static region of preceding dynamic area;When current dynamic area and current static region change
When, then the static zones after rendering each frame of the dynamic area after changing according to the playing sequence of the frame of video in video and change
First frame in domain, until Video Rendering is completed.
In one of the embodiments, the current dynamic area realized when the program is executed by processor and described current
The step of static region changes can include:The duration for the static region that the reception server is sent, from what is received
Corresponding with current static region duration is chosen in the duration of static region, when first frame in current static region
When the display time is equal to the selected duration, then current dynamic area and current static region change.
The above-mentioned specific restriction on computer-readable storage medium may refer to the restriction above in connection with Video Rendering method,
It will not be repeated here.
In one embodiment, Fig. 8 is referred to, there is provided one performs the structural representation of the computer equipment of Video processing
Figure, the computer equipment can perform video processing equipment, be General Server or other any suitable computer equipments, bag
The Video processing that includes memory, processor, operating system, database and storage on a memory and can run on a processor
Program, wherein memory can include built-in storage, realize following steps during computing device video processing program:Obtain and wait to locate
Manage video and Processing Algorithm corresponding with pending video;By Processing Algorithm by pending Video segmentation be dynamic area and
Static region;Dynamic area and static region Adding Area are identified;When the video acquisition for receiving client is asked, then will
The area identification of pending video and pending video is sent to client.
In one of the embodiments, that is realized during computing device program waits to locate by the Processing Algorithm by described
It can also include after the step of reason Video segmentation is dynamic area and static region:The duration in statistical static region, and
The duration of static region is sent to client.
In one of the embodiments, that is realized during computing device program waits to locate by the Processing Algorithm by described
The step of reason Video segmentation is dynamic area and static region can also include:The phase of pending video is calculated by Processing Algorithm
The difference of respective pixel in adjacent frame, when difference is no more than preset value, then region corresponding to pixel is static region, when difference surpasses
When crossing preset value, then region corresponding to pixel is dynamic area.
In one of the embodiments, that is realized during computing device program waits to locate by the Processing Algorithm by described
The step of Video segmentation is dynamic area and static region is managed, can also be included:When Processing Algorithm is deep learning algorithm, then
Matching Model corresponding with pending video is obtained, pending video frequency output is obtained into dynamic area and static state into Matching Model
Region.
The above-mentioned specific restriction on computer equipment may refer to the restriction above in connection with method for processing video frequency, herein
Repeat no more.
In one embodiment, please continue to refer to Fig. 8, there is provided a kind of computer-readable storage medium, be stored thereon with computer
Program, the program realize following steps when being executed by processor:Obtain pending video and place corresponding with pending video
Adjustment method;By pending Video segmentation it is dynamic area and static region by Processing Algorithm;To dynamic area and static region
Adding Area identifies;When the video acquisition for receiving client is asked, then by the area of pending video and pending video
Domain identifier is sent to client.
In one of the embodiments, realized when the program is executed by processor by the Processing Algorithm will described in
It can also include after the step of pending Video segmentation is dynamic area and static region:Statistical static region it is lasting when
Between, and the duration of static region is sent to client.
In one of the embodiments, realized when the program is executed by processor by the Processing Algorithm will described in
The step of pending Video segmentation is dynamic area and static region can also include:Pending video is calculated by Processing Algorithm
Consecutive frame in respective pixel difference, when difference is no more than preset value, then region corresponding to pixel is static region, is on duty
When value exceedes preset value, then region corresponding to pixel is dynamic area.
In one of the embodiments, realized when the program is executed by processor by the Processing Algorithm will described in
The step of pending Video segmentation is dynamic area and static region, can also include:When Processing Algorithm is deep learning algorithm
When, then Matching Model corresponding with pending video is obtained, pending video frequency output is obtained into dynamic area into Matching Model
And static region.
The above-mentioned specific restriction on computer-readable storage medium may refer to the restriction above in connection with method for processing video frequency,
It will not be repeated here.
One of ordinary skill in the art will appreciate that realize all or part of flow in above-described embodiment method, being can be with
Calculating can be read to instruct the hardware of correlation to be stored in a non-volatile computer the program completed by computer program
In machine storage medium, the program is upon execution, it may include such as the flow of the embodiment of above-mentioned each method.Wherein, it is computer-readable
The computer-readable storage medium taken can be magnetic disc, CD, read-only memory (Read-Only Memory, ROM) etc..
Each technical characteristic of above example can be combined arbitrarily, to make description succinct, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, lance is not present in the combination of these technical characteristics
Shield, all it is considered to be the scope of this specification record.
Embodiment described above only expresses the several embodiments of the present invention, and its description is more specific and detailed, but simultaneously
Can not therefore it be construed as limiting the scope of the patent.It should be pointed out that come for one of ordinary skill in the art
Say, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to the protection of the present invention
Scope.Therefore, the protection domain of patent of the present invention should be determined by the appended claims.
Claims (10)
- A kind of 1. Video Rendering method, it is characterised in that including:The video and the area identification of the video that the reception server is sent;Dynamic area and the static region in the video are identified according to the area identification;Playing sequence according to the frame of video in the video renders each frame and current static region of current dynamic area First frame;When the current dynamic area and the current static region change, then according to the frame of video in the video Playing sequence renders the first frame of each frame and the static region after change of the dynamic area after changing, until the video wash with watercolours Dye is completed.
- 2. according to the method for claim 1, it is characterised in that the current dynamic area and current static region hair Raw the step of changing, including:Receive the duration for the static region that the server is sent;The duration corresponding with the current static region is chosen from the duration of the static region received;When the display time of first frame in the current static region being equal to the selected duration, then the current dynamic Region and the current static region change.
- A kind of 3. method for processing video frequency, it is characterised in that including:Obtain pending video and Processing Algorithm corresponding with the pending video;By the pending Video segmentation it is dynamic area and static region by the Processing Algorithm;The dynamic area and the static region Adding Area are identified;When the video acquisition for receiving client is asked, then by the region of the pending video and the pending video Mark is sent to the client.
- 4. according to the method for claim 3, it is characterised in that it is described by the Processing Algorithm by the pending video After the step of being divided into dynamic area and static region, in addition to:Count the duration of the static region;The step of area identification by the pending video and the pending video is sent to the client, bag Include:By the duration of the pending video, the area identification of the pending video and the static region send to The client.
- 5. according to the method for claim 3, it is characterised in that it is described by the Processing Algorithm by the pending video The step of being divided into dynamic area and static region, including:The difference of respective pixel in the consecutive frame of the pending video is calculated by the Processing Algorithm;When the difference is no more than preset value, then region corresponding to the pixel is static region;When the difference exceedes preset value, then region corresponding to the pixel is dynamic area.
- 6. according to the method for claim 3, it is characterised in that it is described by the Processing Algorithm by the pending video The step of being divided into dynamic area and static region, including:When the Processing Algorithm is deep learning algorithm, then Matching Model corresponding with the pending video is obtained;The pending video frequency output is obtained into dynamic area and static region into the Matching Model.
- A kind of 7. Video Rendering device, it is characterised in that including:Receiving module, the video and the area identification of the video sent for the reception server;Identification module, for identifying dynamic area and static region in the video according to the area identification;Rendering module, for rendering each frame of current dynamic area according to the playing sequence of the frame of video in the video and working as First frame of preceding static region;Judge module, for when the current dynamic area and the current static region change, then being regarded according to described The playing sequence of frame of video in frequency renders the first frame of each frame and the static region after change of the dynamic area after changing, Until the Video Rendering is completed.
- A kind of 8. video process apparatus, it is characterised in that including:Algoritic module, for obtaining pending video and Processing Algorithm corresponding with the pending video;Split module, for by the pending Video segmentation being dynamic area and static region by the Processing Algorithm;Mark module, for the dynamic area and static region Adding Area mark;Sending module, for when the video acquisition for receiving client is asked, then by the pending video and described treat The area identification of processing video is sent to the client.
- 9. a kind of computer equipment, including memory, processor and storage can be run on a memory and on a processor Computer program, it is characterised in that the step in the methods described of claim 1 or 2 is realized during the computing device described program Suddenly.
- 10. a kind of readable storage medium storing program for executing, is stored thereon with computer program, it is characterised in that when the program is executed by processor Realize the step in the methods described of claim 1 or 2.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711020523.2A CN107801093B (en) | 2017-10-26 | 2017-10-26 | Video rendering method and device, computer equipment and readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711020523.2A CN107801093B (en) | 2017-10-26 | 2017-10-26 | Video rendering method and device, computer equipment and readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107801093A true CN107801093A (en) | 2018-03-13 |
CN107801093B CN107801093B (en) | 2020-01-07 |
Family
ID=61548153
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711020523.2A Active CN107801093B (en) | 2017-10-26 | 2017-10-26 | Video rendering method and device, computer equipment and readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107801093B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110087096A (en) * | 2019-04-15 | 2019-08-02 | 北京奇艺世纪科技有限公司 | Method for processing video frequency, device and computer readable storage medium |
CN110582021A (en) * | 2019-09-26 | 2019-12-17 | 深圳市商汤科技有限公司 | Information processing method and device, electronic equipment and storage medium |
CN112333516A (en) * | 2020-08-20 | 2021-02-05 | 深圳Tcl新技术有限公司 | Dynamic display method, device, equipment and computer readable storage medium |
CN113596561A (en) * | 2021-07-29 | 2021-11-02 | 北京达佳互联信息技术有限公司 | Video stream playing method and device, electronic equipment and computer readable storage medium |
WO2022037343A1 (en) * | 2020-08-21 | 2022-02-24 | 腾讯科技(深圳)有限公司 | Video information processing method and apparatus, electronic device, and storage medium |
CN116761018A (en) * | 2023-08-18 | 2023-09-15 | 湖南马栏山视频先进技术研究院有限公司 | Real-time rendering system based on cloud platform |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1646220A1 (en) * | 2004-10-05 | 2006-04-12 | Magix AG | System and method for creating a photo movie |
CN1851709A (en) * | 2006-05-25 | 2006-10-25 | 浙江大学 | Embedded multimedia content-based inquiry and search realizing method |
CN106156747A (en) * | 2016-07-21 | 2016-11-23 | 四川师范大学 | The method of the monitor video extracting semantic objects of Behavior-based control feature |
CN106408646A (en) * | 2015-07-27 | 2017-02-15 | 常州市武进区半导体照明应用技术研究院 | Instant light color rendering system and method used for play scenes |
CN106454348A (en) * | 2015-08-05 | 2017-02-22 | 中国移动通信集团公司 | Video coding method, video decoding method, video coding device, and video decoding device |
-
2017
- 2017-10-26 CN CN201711020523.2A patent/CN107801093B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1646220A1 (en) * | 2004-10-05 | 2006-04-12 | Magix AG | System and method for creating a photo movie |
CN1851709A (en) * | 2006-05-25 | 2006-10-25 | 浙江大学 | Embedded multimedia content-based inquiry and search realizing method |
CN106408646A (en) * | 2015-07-27 | 2017-02-15 | 常州市武进区半导体照明应用技术研究院 | Instant light color rendering system and method used for play scenes |
CN106454348A (en) * | 2015-08-05 | 2017-02-22 | 中国移动通信集团公司 | Video coding method, video decoding method, video coding device, and video decoding device |
CN106156747A (en) * | 2016-07-21 | 2016-11-23 | 四川师范大学 | The method of the monitor video extracting semantic objects of Behavior-based control feature |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110087096A (en) * | 2019-04-15 | 2019-08-02 | 北京奇艺世纪科技有限公司 | Method for processing video frequency, device and computer readable storage medium |
CN110582021A (en) * | 2019-09-26 | 2019-12-17 | 深圳市商汤科技有限公司 | Information processing method and device, electronic equipment and storage medium |
CN112333516A (en) * | 2020-08-20 | 2021-02-05 | 深圳Tcl新技术有限公司 | Dynamic display method, device, equipment and computer readable storage medium |
CN112333516B (en) * | 2020-08-20 | 2024-04-30 | 深圳Tcl新技术有限公司 | Dynamic display method, device, equipment and computer readable storage medium |
WO2022037343A1 (en) * | 2020-08-21 | 2022-02-24 | 腾讯科技(深圳)有限公司 | Video information processing method and apparatus, electronic device, and storage medium |
CN113596561A (en) * | 2021-07-29 | 2021-11-02 | 北京达佳互联信息技术有限公司 | Video stream playing method and device, electronic equipment and computer readable storage medium |
CN113596561B (en) * | 2021-07-29 | 2023-06-27 | 北京达佳互联信息技术有限公司 | Video stream playing method, device, electronic equipment and computer readable storage medium |
CN116761018A (en) * | 2023-08-18 | 2023-09-15 | 湖南马栏山视频先进技术研究院有限公司 | Real-time rendering system based on cloud platform |
CN116761018B (en) * | 2023-08-18 | 2023-10-17 | 湖南马栏山视频先进技术研究院有限公司 | Real-time rendering system based on cloud platform |
Also Published As
Publication number | Publication date |
---|---|
CN107801093B (en) | 2020-01-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107801093A (en) | Video Rendering method, apparatus, computer equipment and readable storage medium storing program for executing | |
CN111464833B (en) | Target image generation method, target image generation device, medium and electronic device | |
CN111950723B (en) | Neural network model training method, image processing method, device and terminal equipment | |
CN111383201A (en) | Scene-based image processing method and device, intelligent terminal and storage medium | |
US9082039B2 (en) | Method and apparatus for recognizing a character based on a photographed image | |
CN107451066A (en) | Interim card treating method and apparatus, storage medium, terminal | |
CN111445424B (en) | Image processing method, device, equipment and medium for processing mobile terminal video | |
JP5080302B2 (en) | Image processing method | |
CN106550244A (en) | The picture quality enhancement method and device of video image | |
CN112233049B (en) | Image fusion method for improving image definition | |
CN107113464B (en) | Content providing apparatus, display apparatus, and control method thereof | |
WO2023193521A9 (en) | Video inpainting method, related apparatus, device and storage medium | |
CN112383824A (en) | Video advertisement filtering method, device and storage medium | |
CN111787240B (en) | Video generation method, apparatus and computer readable storage medium | |
CN108668129A (en) | A kind of coding method and device | |
CN113452996B (en) | Video coding and decoding method and device | |
CN110662080A (en) | Machine-oriented universal coding method | |
CN104424485A (en) | Method and device for obtaining specific information based on image recognition | |
CN110996128B (en) | Online teaching video push management system | |
CN117459661A (en) | Video processing method, device, equipment and machine-readable storage medium | |
CN113313635A (en) | Image processing method, model training method, device and equipment | |
CN106303366B (en) | Video coding method and device based on regional classification coding | |
US9798932B2 (en) | Video extraction method and device | |
CN113628121B (en) | Method and device for processing and training multimedia data | |
CN108009516A (en) | Video matching method, device and terminal |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20201214 Address after: 518000 1902, phase I, international student venture building, No. 29, Gaoxin South Ring Road, high tech Zone community, Yuehai street, Nanshan District, Shenzhen City, Guangdong Province Patentee after: Shenzhen Talos Innovation Co.,Ltd. Address before: 902, building 5, Dachong International Center, 39 Tonggu Road, Nanshan District, Shenzhen City, Guangdong Province Patentee before: SHENZHEN DKVISION TECHNOLOGY Co.,Ltd. |