CN106060581A - Video real-time transmission data processing method, device and system - Google Patents
Video real-time transmission data processing method, device and system Download PDFInfo
- Publication number
- CN106060581A CN106060581A CN201610526058.9A CN201610526058A CN106060581A CN 106060581 A CN106060581 A CN 106060581A CN 201610526058 A CN201610526058 A CN 201610526058A CN 106060581 A CN106060581 A CN 106060581A
- Authority
- CN
- China
- Prior art keywords
- algorithm
- special effect
- video
- effect processing
- specially good
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs
- H04N21/2343—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements
Abstract
The embodiment of the invention discloses a video real-time transmission data processing method, device and system, and aims to solve the technical problem of lack of a technical scheme for supporting multiple special effects in existing high-definition video live broadcast, and the technical problem of frame loss of video data under the situation of implementation of the special effects during high-definition video live broadcast since an existing video live broadcast special effect processing technology can only perform one-by-one circular processing. The video real-time transmission data processing method in the embodiment of the invention comprises the following steps: acquiring a live video special effect processing instruction; determining a corresponding algorithm number according to the live video special effect processing instruction; and creating a corresponding number of special effect processing channels in a CPU (Central Processing Unit) according to the algorithm number, and performing real-time video special effect processing on live videos at the same time according to algorithms in a GPU (Graphics Processing Unit) through the special effect processing channels.
Description
Technical field
The present invention relates to the Internet images processing technology field, particularly relate to a kind of realtime video transmission data process side
Method, Apparatus and system.
Background technology
Video living transmission system is that on-the-spot signal (video camera), TV signal (such as TV programme, video-tape) etc. are carried out
Real-time Collection is encoded into that standard flow data (FLV, WMV) are managed, classification etc. is sent on server be sent out by page format
Cloth is gone out, and watches live show or TV programme for everybody in real time by network.
At present net cast is increasingly burning hoter, and the video instrument that starts broadcasting is also the most, especially at HD video, as differentiated
Rate is under the situation of 1280*720P, and net cast supports that the implementation of many specially good effects belongs to deficient state, and current regarding
The most live special effect processing technology can only circular treatment one by one so that when HD video is live, video data realizes
The technical problem of frame losing is caused in the case of specially good effect.
Summary of the invention
A kind of realtime video transmission data processing method of embodiment of the present invention offer, Apparatus and system, solve at present
The technical problem that the technical scheme of the many specially good effects of the live support of HD video is deficient, and current net cast special effect processing technology
Can only circular treatment one by one so that when HD video is live, in the case of the video data caused realizes specially good effect
The technical problem of frame losing.
A kind of realtime video transmission data processing method that the embodiment of the present invention provides, including:
Get the instruction of live video special effect processing；
Corresponding algorithm quantity is determined according to the instruction of described live video special effect processing；
In CPU, the special effect processing passage of respective amount is created according to described algorithm quantity, and by described special effect processing
Described live video is carried out real-time video special effect processing according to described algorithm in GPU by passage simultaneously.
Alternatively, determine that corresponding algorithm quantity specifically includes according to the instruction of described live video special effect processing:
Determine the algorithm quantity of corresponding whitening specially good effect according to the instruction of live video whitening special effect processing, described whitening is special
Effect includes that skin color model algorithm, brightness improve algorithm, Image Sharpening Algorithm；
And/or
Determine the algorithm quantity of corresponding filter specially good effect according to the instruction of live video filter special effect processing, described filter is special
The filter algorithm of effect is corresponding with the filter type that backstage selects；
And/or
Determine that corresponding image scaled changes the algorithm number of specially good effect according to the weight reducing special effect processing instruction of live video thinning face
Amount, it is image stretch and scaling algorithm that described image scaled changes the algorithm of specially good effect.
Alternatively, in CPU, create the special effect processing passage of respective amount according to described algorithm quantity, and by described spy
Described live video is carried out real-time video special effect processing according to described algorithm in GPU simultaneously and specifically includes by effect treatment channel:
Algorithm quantity according to described whitening specially good effect and/or the algorithm quantity of described filter specially good effect and/or described image ratio
The algorithm quantity of example change specially good effect creates the special effect processing passage of respective amount in described CPU；
By described special effect processing passage in described GPU simultaneously that described live video is special according to corresponding described whitening
The algorithm of effect and/or the algorithm of described filter specially good effect and/or described image scaled change the algorithm of specially good effect and carry out real-time video spy
Effect processes.
Alternatively, by described special effect processing passage in described GPU simultaneously by described live video according to corresponding institute
The algorithm of the algorithm and/or the algorithm of described filter specially good effect and/or described image scaled change specially good effect of stating whitening specially good effect carries out reality
Time special video effect process specifically include:
If described whitening specially good effect, then pass through corresponding described special effect processing passage in described GPU successively according to described
It is beautiful that skin color model algorithm, described brightness improve algorithm, the processing sequence of described Image Sharpening Algorithm carries out real-time video to image
White special effect processing；
And/or
If described filter specially good effect, then by corresponding described special effect processing passage carry out in described GPU with described after
The picture point real-time video filter special effect processing of the described filter type that platform selects；
And/or
If described image scaled changes specially good effect, then by corresponding described special effect processing passage basis in described GPU
Described image stretch and scaling algorithm carry out real time video image ratio and change special effect processing image.
Alternatively, described Image Sharpening Algorithm includes that image level finds that marginal point algorithm is vertical with image finds marginal point
Algorithm.
Alternatively, in CPU, create the special effect processing passage of respective amount according to described algorithm quantity, and by described spy
Effect treatment channel is also wrapped after described live video being carried out real-time video special effect processing according to described algorithm in GPU simultaneously
Include:
After special video effect having been processed by the main broadcaster's end echo thread created and user side recording thread respectively simultaneously
Specially good effect transmission of video play out to main broadcaster's end of corresponding current special effect processing and the user side of viewing video.
A kind of realtime video transmission data processing equipment that the embodiment of the present invention provides, including:
Acquiring unit, is used for getting the instruction of live video special effect processing；
Algorithm quantity determines unit, for determining corresponding algorithm number according to the instruction of described live video special effect processing
Amount；
Passage creates and special effect processing unit, for creating the specially good effect of respective amount in CPU according to described algorithm quantity
Treatment channel, and described live video is carried out according to described algorithm in real time in GPU by described special effect processing passage simultaneously
Special video effect processes.
Alternatively, algorithm quantity determines that unit specifically includes:
First algorithm quantity determines subelement, for determining corresponding U.S. according to the instruction of live video whitening special effect processing
The algorithm quantity of Bai Texiao, described whitening specially good effect include skin color model algorithm, brightness improve algorithm, Image Sharpening Algorithm, wherein,
Described Image Sharpening Algorithm includes that image level finds that marginal point algorithm is vertical with image finds marginal point algorithm；
And/or
Second algorithm quantity determines subelement, for determining corresponding filter according to the instruction of live video filter special effect processing
The algorithm quantity of mirror specially good effect, the filter algorithm of described filter specially good effect is corresponding with the filter type that backstage selects；
And/or
Third algorithm quantity determines subelement, for determining corresponding according to the weight reducing special effect processing instruction of live video thinning face
Image scaled change specially good effect algorithm quantity, described image scaled change specially good effect algorithm be image stretch and scaling algorithm.
Alternatively, passage creates and special effect processing unit specifically includes:
Passage creates subelement, for the algorithm quantity according to described whitening specially good effect and/or the algorithm of described filter specially good effect
The algorithm quantity of quantity and/or described image scaled change specially good effect creates the special effect processing passage of respective amount in described CPU；
Special effect processing subelement, for by described special effect processing passage in described GPU simultaneously by described live video
Specially good effect is changed according to the algorithm of corresponding described whitening specially good effect and/or the algorithm of described filter specially good effect and/or described image scaled
Algorithm carry out real-time video special effect processing.
Alternatively, special effect processing subelement specifically includes:
Whitening special efficacy processing module, if for described whitening specially good effect, then existing by corresponding described special effect processing passage
Described GPU improves algorithm, the processing sequence of described Image Sharpening Algorithm according to described skin color model algorithm, described brightness successively
Image is carried out real-time video whitening special effect processing；
And/or
Filter special efficacy processing module, if for described filter specially good effect, then existing by corresponding described special effect processing passage
Described GPU carries out the picture point real-time video filter special effect processing of the described filter type selected with described backstage；
And/or
Image scaled changes special efficacy processing module, if changing specially good effect for described image scaled, then by corresponding institute
State special effect processing passage and according to described image stretch and scaling algorithm, image is carried out real time video image ratio in described GPU
Change special effect processing.
Alternatively, realtime video transmission data processing equipment also includes:
Multi-thread transmission unit, will for recording thread by the main broadcaster's end echo thread created and user side respectively simultaneously
Special video effect processed after specially good effect transmission of video to main broadcaster's end of corresponding current special effect processing and the user of viewing video
End plays out.
A kind of realtime video transmission data handling system that the embodiment of the present invention provides, including:
At least one user side, and any one described realtime video transmission data process dress that the present invention mentions
Put；
At least one described user side is set up with described realtime video transmission data processing equipment communication connection relation.
As can be seen from the above technical solutions, the embodiment of the present invention has the advantage that
A kind of realtime video transmission data processing method of embodiment of the present invention offer, Apparatus and system, wherein, video is real
Time transmission data processing method include: get live video special effect processing instruction；According to the instruction of live video special effect processing really
Fixed corresponding algorithm quantity；In CPU, the special effect processing passage of respective amount is created according to algorithm quantity, and by specially good effect
Live video is carried out real-time video special effect processing according to algorithm in GPU by reason passage simultaneously.In the present embodiment, by according to straight
Broadcast special video effect process instruction and determine corresponding algorithm quantity, then in CPU, create respective amount further according to algorithm quantity
Special effect processing passage, and according to algorithm, live video to be carried out real-time video by special effect processing passage in GPU special simultaneously
Effect processes, it is achieved multichannel also deposits the function that image carries out special effect processing, how special solves the live support of current HD video
The technical problem that the technical scheme of effect is deficient, and current net cast special effect processing technology can only be one by one at circulation
Reason, so that when HD video is live, the video data caused realizes the technical problem of frame losing in the case of specially good effect.
Further, if whitening specially good effect, then corresponding special effect processing passage is passed through in GPU successively according to skin color model
Algorithm, brightness improve algorithm, the processing sequence of Image Sharpening Algorithm carries out real-time video whitening special effect processing, greatly to image
Alleviate the extra load that GPU processes.
Further, main broadcaster's end echo thread of establishment and user side are recorded after special video effect processed by thread simultaneously
Specially good effect transmission of video play out to main broadcaster's end of corresponding current special effect processing and the user side of viewing video, it is to avoid work as
Image needs to be shown to the technical problem of frame losing when main broadcaster's end and user side and produces.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
In having technology to describe, the required accompanying drawing used is briefly described, it should be apparent that, the accompanying drawing in describing below is only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, also may be used
To obtain other accompanying drawing according to these accompanying drawings.
The flow process of one embodiment of a kind of realtime video transmission data processing method that Fig. 1 provides for the embodiment of the present invention
Schematic diagram；
The stream of another embodiment of a kind of realtime video transmission data processing method that Fig. 2 provides for the embodiment of the present invention
Journey schematic diagram；
The structure of one embodiment of a kind of realtime video transmission data processing equipment that Fig. 3 provides for the embodiment of the present invention
Schematic diagram；
The knot of another embodiment of a kind of realtime video transmission data processing equipment that Fig. 4 provides for the embodiment of the present invention
Structure schematic diagram；
The structure of one embodiment of a kind of realtime video transmission data handling system that Fig. 5 provides for the embodiment of the present invention
Schematic diagram；
Fig. 6 is the application examples schematic diagram of Fig. 2；
Fig. 7 is the software interface schematic diagram that the application examples of Fig. 5 is corresponding.
Detailed description of the invention
A kind of realtime video transmission data processing method of embodiment of the present invention offer, Apparatus and system, solve at present
The technical problem that the technical scheme of the many specially good effects of the live support of HD video is deficient, and current net cast special effect processing technology
Can only circular treatment one by one so that when HD video is live, in the case of the video data caused realizes specially good effect
The technical problem of frame losing.
For making the goal of the invention of the present invention, feature, the advantage can be the most obvious and understandable, below in conjunction with the present invention
Accompanying drawing in embodiment, is clearly and completely described the technical scheme in the embodiment of the present invention, it is clear that disclosed below
Embodiment be only a part of embodiment of the present invention, and not all embodiment.Based on the embodiment in the present invention, this area
All other embodiments that those of ordinary skill is obtained under not making creative work premise, broadly fall into present invention protection
Scope.
Refer to Fig. 1, an embodiment of a kind of realtime video transmission data processing method that the embodiment of the present invention provides
Including:
101, the instruction of live video special effect processing is got；
In the present embodiment, when needing the image that HD video is live is carried out many special effect processing, it is necessary first to get
Live video special effect processing instructs.
The instruction of this live video special effect processing can be by triggering at corresponding special effect processing interface.
102, corresponding algorithm quantity is determined according to the instruction of live video special effect processing；
After getting the instruction of live video special effect processing, need to determine relatively according to the instruction of live video special effect processing
The algorithm quantity answered.
103, in CPU, the special effect processing passage of respective amount is created according to algorithm quantity, and by special effect processing passage
In GPU, live video is carried out real-time video special effect processing according to algorithm simultaneously.
After determining corresponding algorithm quantity according to the instruction of live video special effect processing, need to exist according to algorithm quantity
CPU creates the special effect processing passage of respective amount, and by special effect processing passage in GPU simultaneously by live video according to calculation
Method carries out real-time video special effect processing.
In the present embodiment, by determining corresponding algorithm quantity, root the most again according to the instruction of live video special effect processing
In CPU, the special effect processing passage of respective amount is created according to algorithm quantity, and simultaneously will be straight in GPU by special effect processing passage
Broadcast video and carry out real-time video special effect processing according to algorithm, it is achieved multichannel also deposits the function that image carries out special effect processing, solve
The technical problem that the technical scheme of the current HD video many specially good effects of live support of having determined is deficient, and current net cast specially good effect
Treatment technology can only circular treatment one by one so that when HD video is live, the video data caused realizes specially good effect
In the case of the technical problem of frame losing.
The above is the description that the process to realtime video transmission data processing method is carried out, below will be to special effect processing process
It is described in detail, refers to Fig. 2, another of a kind of realtime video transmission data processing method that the embodiment of the present invention provides
Individual embodiment includes:
201, the instruction of live video special effect processing is got；
In the present embodiment, when needing the image that HD video is live is carried out many special effect processing, it is necessary first to get
Live video special effect processing instructs.
The instruction of this live video special effect processing can be by triggering at corresponding special effect processing interface.
The when of it should be noted that carry out special video effect process, need to judge that the client of current specially good effect demand is necessary
It is to possess GPU.
202, the algorithm quantity of corresponding whitening specially good effect is determined according to the instruction of live video whitening special effect processing；
After getting the instruction of live video special effect processing, need to determine according to the instruction of live video whitening special effect processing
The algorithm quantity of corresponding whitening specially good effect, whitening specially good effect includes that skin color model algorithm, brightness improve algorithm, image sharpening is calculated
Method.
203, the algorithm quantity of corresponding filter specially good effect is determined according to the instruction of live video filter special effect processing；
After getting the instruction of live video special effect processing, need to determine according to the instruction of live video filter special effect processing
The algorithm quantity of corresponding filter specially good effect, the filter algorithm of filter specially good effect is corresponding with the filter type that backstage selects.
204, determine that corresponding image scaled changes the calculation of specially good effect according to the weight reducing special effect processing instruction of live video thinning face
Method quantity；
After getting the instruction of live video special effect processing, need according to the weight reducing special effect processing instruction of live video thinning face
Determining that corresponding image scaled changes the algorithm quantity of specially good effect, it is image stretch and scaling that image scaled changes the algorithm of specially good effect
Algorithm.
205, spy is changed according to the algorithm quantity of whitening specially good effect and/or the algorithm quantity of filter specially good effect and/or image scaled
The algorithm quantity of effect creates the special effect processing passage of respective amount in CPU；
After step 202 and/or step 203 and/or step 204, need according to the algorithm quantity of whitening specially good effect and/or
The algorithm quantity of filter specially good effect and/or image scaled change the algorithm quantity of specially good effect and create in CPU at the specially good effect of respective amount
Reason passage.
It should be noted that in aforesaid step 202, in 203,204, can be there is no sequencing, can be to judge
Whether enabling whitening specially good effect, if enabling, judging whether to enable filter specially good effect, if enabling, judging whether to enable weight reducing/thinning face special
Effect (image scaled change specially good effect), aforesaid to enable any specially good effect be no, then abandon the special effect processing of correspondence, do not perform
Follow-up passage creates.
206, by special effect processing passage in GPU simultaneously by live video according to the algorithm of corresponding whitening specially good effect and/
Or the algorithm of the algorithm of filter specially good effect and/or image scaled change specially good effect carries out real-time video special effect processing；
When the algorithm quantity according to whitening specially good effect and/or the algorithm quantity of filter specially good effect and/or image scaled change specially good effect
Algorithm quantity in CPU, create respective amount special effect processing passage after, need by special effect processing passage in GPU with
Time live video is changed specially good effect according to the algorithm of corresponding whitening specially good effect and/or the algorithm of filter specially good effect and/or image scaled
Algorithm carry out real-time video special effect processing.
Should be noted that, by special effect processing passage in GPU simultaneously by live video according to corresponding whitening specially good effect
Algorithm and/or the algorithm of filter specially good effect and/or image scaled change the algorithm of specially good effect to carry out real-time video special effect processing concrete
Including:
If whitening specially good effect, then pass through corresponding special effect processing passage in GPU successively according to skin color model algorithm, brightness
Improve algorithm, the processing sequence of Image Sharpening Algorithm carries out real-time video whitening special effect processing to image；
And/or
If filter specially good effect, then in GPU, carried out the filter type selected with backstage by corresponding special effect processing passage
Picture point real-time video filter special effect processing；
And/or
If image scaled changes specially good effect, then pass through corresponding special effect processing passage in GPU according to image stretch and contracting
Put algorithm and image is carried out real time video image ratio change special effect processing.
Wherein, Image Sharpening Algorithm includes that image level finds that marginal point algorithm is vertical with image finds marginal point algorithm,
Being establishment passage corresponding to this Image Sharpening Algorithm is two passages, is to find marginal point algorithm and figure with image level respectively
As vertical searching marginal point algorithm is corresponding.
207, record thread by the main broadcaster's end echo thread created and user side respectively to have been processed by special video effect simultaneously
Specially good effect transmission of video after one-tenth plays out to main broadcaster's end of corresponding current special effect processing and the user side of viewing video.
When by special effect processing passage in GPU simultaneously by live video according to the algorithm of corresponding whitening specially good effect and/or
After the algorithm of the algorithm of filter specially good effect and/or image scaled change specially good effect carries out real-time video special effect processing, need to lead to respectively
Cross the main broadcaster's end echo thread created and user side records the specially good effect transmission of video after special video effect has been processed by thread simultaneously
Play out to main broadcaster's end of corresponding current special effect processing and the user side of viewing video.
Being described with a concrete application scenarios below, as shown in Figure 6, application examples includes:
In the case of Y companion can accomplish that many specially good effects are opened simultaneously, frame number remains to about 25-30 frame
Specially good effect: whitening (comprises skin color model+brightness raising+image edge acuity and processes+independent colour of skin whitening+mill skin)
Filter: comprise the filter that 12 sections of main broadcasters use；
Weight reducing, scene, seal etc.；
Illustrating: frame number also has much relations with hardware configuration, contrast said herein is based under same hardware case of machines
(the i5 tetra-core CPU network bandwidth is enough).If frame number is low, the code check of video is the lowest.And there will be video card and pause, Hua Ping, horse
The phenomenons such as Sai Ke.
As it can be seen, after collection video, image is passed to YY companion (a net cast of YY company start broadcasting instrument),
Being different from starting broadcasting of other, this instrument just goes multiple specially good effect to set up the mode of multiple PASS after opening inside CPU, the most incoming
To GPU process.
The way of YY companion: the way of newly-built multiple PASS can be greatly saved amount of calculation and the consumption of CPU and GPU in CPU
Time, save the step of Video processing, be very helpful to improving frame per second.
One algorithm=mono-PASS, can regard a task as, and YY companion uses fixing sequential processing PASS, respectively
Dependence before and after having between individual PASS necessarily, as follows:
PASS1: be first skin color model algorithm, each point to image, a pre-value (such as 120), that image are set
In point just can show that divided by pre-value whether it be to have started to grind skin after the weight (0.0-1.0) of the colour of skin has calculated, mill skin obtains
The image gone out and artwork need to merge, and fusion formula is: the some * weighted value of the some * (1-weighted value) of original painting+mill skin.
PASS2: raising brightness algorithm/be equivalent to whitening, owing to PASS1 has calculated the value of each point in image,
Each point being carried out whitening and needs not rely on other point, calculating so directly carrying out whitening formula, used here as general
Log calculates, and each brightness put is put on.
PASS3+PASS4: Image Sharpening Algorithm, sharpens the definition that can improve image, it is important that find marginal point, this
In be divided into 2 PASS and gone, a level is looked for, and vertically looks for for one, if only looking for the point of surrounding, it is likely that do not find edge
(point of such as certain row is 25 10 35 40 45 50 100 the most probably to have treated as marginal point 10 to point, should be in fact
100)。
Aforesaid PASS1, PASS2, PASS3+PASS4 are for carrying out special effect processing successively.
PASS5: filter algorithm, which filter user selects, and (YY companion has 16 filters just to use corresponding algorithm to get final product
Algorithm) mainly picture point is carried out some additional effect
PASS6: weight reducing/thinning face algorithm, this is a kind of filtering interpolation algorithm, image is carried out a certain proportion of stretching and
Scaling.
After GPU has processed PASS task, need to be shown to by image inside main broadcaster's end/user side, and YY companion.As
Fruit is put into a process and spreads out of, and the situation having frame losing occurs, and at this time YY companion uses multiple threads, and echo is newly-built
One process, the most newly-built process of recorded video, thus do not interfere with the video effect of main broadcaster's end and user side.
Can be as it is shown in fig. 7, main broadcaster opens whitening, weight reducing and filter specially good effect, and the three of whitening parameters are (sharp
Change, grind skin, whitening) also open the highest, under such conditions, notes seeing the parameter on the left side, the CamMajor-In fps of centre
It is the frame number (here be sieve skill high definition C920 photographic head) of camera collection: (YY companion has processed specially good effect to 30Merge-Cut
After output frame number): 30 frames, it may be said that almost without frame losing.
Aforesaid PASS is i.e. special effect processing passage.
In the present embodiment, by determining corresponding algorithm quantity, root the most again according to the instruction of live video special effect processing
In CPU, the special effect processing passage of respective amount is created according to algorithm quantity, and simultaneously will be straight in GPU by special effect processing passage
Broadcast video and carry out real-time video special effect processing according to algorithm, it is achieved multichannel also deposits the function that image carries out special effect processing, solve
The technical problem that the technical scheme of the current HD video many specially good effects of live support of having determined is deficient, and current net cast specially good effect
Treatment technology can only circular treatment one by one so that when HD video is live, the video data caused realizes specially good effect
In the case of the technical problem of frame losing.
Further, if whitening specially good effect, then corresponding special effect processing passage is passed through in GPU successively according to skin color model
Algorithm, brightness improve algorithm, the processing sequence of Image Sharpening Algorithm carries out real-time video whitening special effect processing, greatly to image
Alleviate the extra load that GPU processes.
Further, main broadcaster's end echo thread of establishment and user side are recorded after special video effect processed by thread simultaneously
Specially good effect transmission of video play out to main broadcaster's end of corresponding current special effect processing and the user side of viewing video, it is to avoid work as
Image needs to be shown to the technical problem of frame losing when main broadcaster's end and user side and produces.
Refer to Fig. 3, an embodiment of a kind of realtime video transmission data processing equipment that the embodiment of the present invention provides
Including:
Acquiring unit 301, is used for getting the instruction of live video special effect processing；
Algorithm quantity determines unit 302, for determining corresponding algorithm quantity according to the instruction of live video special effect processing；
Passage creates and special effect processing unit 303, for creating in CPU at the specially good effect of respective amount according to algorithm quantity
Reason passage, and in GPU, live video is carried out real-time video special effect processing according to algorithm by special effect processing passage simultaneously.
In the present embodiment, determine that unit 302 determines corresponding according to the instruction of live video special effect processing by algorithm quantity
Algorithm quantity, then passage create and special effect processing unit 303 in CPU, create the spy of respective amount further according to algorithm quantity
Effect treatment channel, and live video is carried out at real-time video specially good effect according to algorithm in GPU by special effect processing passage simultaneously
Reason, it is achieved multichannel also deposits the function that image carries out special effect processing, solves the current HD video many specially good effects of live support
The technical problem that technical scheme is deficient, and current net cast special effect processing technology can only circular treatment one by one, from
And making when HD video is live, the video data caused realizes the technical problem of frame losing in the case of specially good effect.
The above is the description that each unit to realtime video transmission data processing equipment is carried out, below by sub-unit and mould
Block is described, and refers to Fig. 4, and another of a kind of realtime video transmission data processing equipment that the embodiment of the present invention provides is real
Execute example to include:
Acquiring unit 401, is used for getting the instruction of live video special effect processing；
Algorithm quantity determines unit 402, for determining corresponding algorithm quantity according to the instruction of live video special effect processing；
Algorithm quantity determines that unit 402 specifically includes:
First algorithm quantity determines subelement 4021, for determining corresponding according to the instruction of live video whitening special effect processing
The algorithm quantity of whitening specially good effect, whitening specially good effect includes that skin color model algorithm, brightness improve algorithm, Image Sharpening Algorithm, wherein,
Image Sharpening Algorithm includes that image level finds that marginal point algorithm is vertical with image finds marginal point algorithm；
And/or
Second algorithm quantity determines subelement 4022, for determining corresponding according to the instruction of live video filter special effect processing
The algorithm quantity of filter specially good effect, the filter algorithm of filter specially good effect is corresponding with the filter type that backstage selects；
And/or
Third algorithm quantity determines subelement 4023, for determining phase according to the weight reducing special effect processing instruction of live video thinning face
Corresponding image scaled changes the algorithm quantity of specially good effect, and it is image stretch and scaling algorithm that image scaled changes the algorithm of specially good effect.
Passage creates and special effect processing unit 403, for creating in CPU at the specially good effect of respective amount according to algorithm quantity
Reason passage, and in GPU, live video is carried out real-time video special effect processing according to algorithm by special effect processing passage simultaneously.
Passage creates and special effect processing unit 403 specifically includes:
Passage creates subelement 4031, for the algorithm quantity according to whitening specially good effect and/or the algorithm quantity of filter specially good effect
And/or the algorithm quantity of image scaled change specially good effect creates the special effect processing passage of respective amount in CPU；
Special effect processing subelement 4032, for by special effect processing passage in GPU simultaneously by live video according to correspondence
The algorithm of whitening specially good effect and/or the algorithm of filter specially good effect and/or image scaled change the algorithm of specially good effect to carry out real-time video special
Effect processes.
Special effect processing subelement 4032 specifically includes:
Whitening special efficacy processing module 4032a, if for whitening specially good effect, then by corresponding special effect processing passage at GPU
In improve algorithm, the processing sequence of Image Sharpening Algorithm according to skin color model algorithm, brightness successively image carried out real-time video
Whitening special effect processing；
And/or
Filter special efficacy processing module 4032b, if for filter specially good effect, then by corresponding special effect processing passage at GPU
In carry out the picture point real-time video filter special effect processing of filter type that selects with backstage；
And/or
Image scaled changes special efficacy processing module 4033c, if changing specially good effect for image scaled, then by corresponding spy
Effect treatment channel carries out real time video image ratio according to image stretch and scaling algorithm to image in GPU and changes at specially good effect
Reason.
Multi-thread transmission unit 404, same for recording thread by the main broadcaster's end echo thread created and user side respectively
Time special video effect has been processed after specially good effect transmission of video to main broadcaster's end of corresponding current special effect processing and viewing video
User side plays out.
In the present embodiment, determine that unit 402 determines corresponding according to the instruction of live video special effect processing by algorithm quantity
Algorithm quantity, then passage create and special effect processing unit 403 in CPU, create the spy of respective amount further according to algorithm quantity
Effect treatment channel, and live video is carried out at real-time video specially good effect according to algorithm in GPU by special effect processing passage simultaneously
Reason, it is achieved multichannel also deposits the function that image carries out special effect processing, solves the current HD video many specially good effects of live support
The technical problem that technical scheme is deficient, and current net cast special effect processing technology can only circular treatment one by one, from
And making when HD video is live, the video data caused realizes the technical problem of frame losing in the case of specially good effect.
Further, whitening special efficacy processing module 4032a passes through corresponding special effect processing passage in GPU successively according to skin
Colour discrimination algorithm, brightness improve algorithm, the processing sequence of Image Sharpening Algorithm carries out real-time video whitening special effect processing to image,
It is greatly reduced the extra load that GPU processes.
Further, multi-thread transmission unit 404 creates main broadcaster's end echo thread and user side recording thread will simultaneously
Special video effect processed after specially good effect transmission of video to main broadcaster's end of corresponding current special effect processing and the user of viewing video
End plays out, it is to avoid the technical problem of frame losing produces when image needs to be shown to main broadcaster's end and user side.
Refer to Fig. 5, an enforcement of a kind of realtime video transmission data handling system provided in the embodiment of the present invention
Example includes:
At least one user side 51, and the realtime video transmission data processing equipment 52 that Fig. 3 and Fig. 4 embodiment is mentioned；
At least one user side 51 is set up with realtime video transmission data processing equipment 52 communication connection relation.
The beneficial effect of the present embodiment includes: image adds many specially good effects, and the processing mode of not frame losing；=attenuating CPU disappears
Consumption, saves the implementation of GPU operation time, provides more preferable video effect for main broadcaster.A kind of special video effect is provided to process
Scheme, allows main broadcaster can open multiple specially good effect (skin, weight reducing, filter etc. are ground in whitening) live when, and frame per second can reach
More than 25 frames (the collection frame number of high-definition camera is 30, and the photographic head of technical grade can reach 60).
Those skilled in the art is it can be understood that arrive, for convenience and simplicity of description, and the system of foregoing description,
The specific works process of device and unit, is referred to the corresponding process in preceding method embodiment, does not repeats them here.
In several embodiments provided herein, it should be understood that disclosed system, apparatus and method are permissible
Realize by another way.Such as, device embodiment described above is only schematically, such as, and described unit
Dividing, be only a kind of logic function and divide, actual can have other dividing mode, the most multiple unit or assembly when realizing
Can in conjunction with or be desirably integrated into another system, or some features can be ignored, or does not performs.Another point, shown or
The coupling each other discussed or direct-coupling or communication connection can be the indirect couplings by some interfaces, device or unit
Close or communication connection, can be electrical, machinery or other form.
The described unit illustrated as separating component can be or may not be physically separate, shows as unit
The parts shown can be or may not be physical location, i.e. may be located at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected according to the actual needs to realize the mesh of the present embodiment scheme
's.
It addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, it is also possible to
It is that unit is individually physically present, it is also possible to two or more unit are integrated in a unit.Above-mentioned integrated list
Unit both can realize to use the form of hardware, it would however also be possible to employ the form of SFU software functional unit realizes.
If described integrated unit realizes and as independent production marketing or use using the form of SFU software functional unit
Time, can be stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially
The part that in other words prior art contributed or this technical scheme completely or partially can be with the form of software product
Embodying, this computer software product is stored in a storage medium, including some instructions with so that a computer
Equipment (can be personal computer, server, or the network equipment etc.) performs the complete of method described in each embodiment of the present invention
Portion or part steps.And aforesaid storage medium includes: USB flash disk, portable hard drive, read only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can store journey
The medium of sequence code.
The above, above example only in order to technical scheme to be described, is not intended to limit；Although with reference to front
State embodiment the present invention has been described in detail, it will be understood by those within the art that: it still can be to front
State the technical scheme described in each embodiment to modify, or wherein portion of techniques feature is carried out equivalent；And these
Amendment or replacement, do not make the essence of appropriate technical solution depart from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (12)
1. a realtime video transmission data processing method, it is characterised in that including:
Get the instruction of live video special effect processing；
Corresponding algorithm quantity is determined according to the instruction of described live video special effect processing；
In CPU, the special effect processing passage of respective amount is created according to described algorithm quantity, and by described special effect processing passage
In GPU, described live video is carried out real-time video special effect processing according to described algorithm simultaneously.
Realtime video transmission data processing method the most according to claim 1, it is characterised in that according to described live video
Special effect processing instruction determines that corresponding algorithm quantity specifically includes:
The algorithm quantity of corresponding whitening specially good effect, described whitening specially good effect bag is determined according to the instruction of live video whitening special effect processing
Include skin color model algorithm, brightness improves algorithm, Image Sharpening Algorithm；
And/or
The algorithm quantity of corresponding filter specially good effect is determined according to the instruction of live video filter special effect processing, described filter specially good effect
Filter algorithm is corresponding with the filter type that backstage selects；
And/or
Determine that corresponding image scaled changes the algorithm quantity of specially good effect, institute according to the weight reducing special effect processing instruction of live video thinning face
The algorithm stating image scaled change specially good effect is image stretch and scaling algorithm.
Realtime video transmission data processing method the most according to claim 2, it is characterised in that according to described algorithm quantity
In CPU, create the special effect processing passage of respective amount, and by described special effect processing passage in GPU simultaneously by described live
Video carries out real-time video special effect processing according to described algorithm and specifically includes:
Algorithm quantity according to described whitening specially good effect and/or the algorithm quantity of described filter specially good effect and/or described image scaled change
The algorithm quantity becoming specially good effect creates the special effect processing passage of respective amount in described CPU；
By described special effect processing passage in described GPU simultaneously by described live video according to corresponding described whitening specially good effect
Algorithm and/or the algorithm of described filter specially good effect and/or described image scaled change the algorithm of specially good effect and carry out at real-time video specially good effect
Reason.
Realtime video transmission data processing method the most according to claim 3, it is characterised in that by described special effect processing
Passage is simultaneously special according to algorithm and/or the described filter of corresponding described whitening specially good effect by described live video in described GPU
The algorithm of the algorithm of effect and/or described image scaled change specially good effect carries out real-time video special effect processing and specifically includes:
If described whitening specially good effect, then pass through corresponding described special effect processing passage in described GPU successively according to the described colour of skin
It is special that recognizer, described brightness improve algorithm, the processing sequence of described Image Sharpening Algorithm carries out real-time video whitening to image
Effect processes；
And/or
If described filter specially good effect, then carry out selecting with described backstage in described GPU by corresponding described special effect processing passage
The picture point real-time video filter special effect processing of the described filter type selected；
And/or
If described image scaled changes specially good effect, then pass through corresponding described special effect processing passage in described GPU according to described
Image stretch and scaling algorithm carry out real time video image ratio and change special effect processing image.
Realtime video transmission data processing method the most according to claim 2, it is characterised in that described Image Sharpening Algorithm
Find including image level that marginal point algorithm is vertical with image finds marginal point algorithm.
Realtime video transmission data processing method the most as claimed in any of claims 1 to 5, it is characterised in that root
In CPU, the special effect processing passage of respective amount is created according to described algorithm quantity, and by described special effect processing passage in GPU
Also include after described live video being carried out real-time video special effect processing according to described algorithm simultaneously:
The spy after special video effect has been processed by thread simultaneously is recorded respectively by the main broadcaster's end echo thread created and user side
Effect transmission of video plays out to main broadcaster's end of corresponding current special effect processing and the user side of viewing video.
7. a realtime video transmission data processing equipment, it is characterised in that including:
Acquiring unit, is used for getting the instruction of live video special effect processing；
Algorithm quantity determines unit, for determining corresponding algorithm quantity according to the instruction of described live video special effect processing；
Passage creates and special effect processing unit, for creating the special effect processing of respective amount in CPU according to described algorithm quantity
Passage, and in GPU, described live video is carried out real-time video according to described algorithm by described special effect processing passage simultaneously
Special effect processing.
Realtime video transmission data processing equipment the most according to claim 7, it is characterised in that algorithm quantity determines unit
Specifically include:
First algorithm quantity determines subelement, for determining that corresponding whitening is special according to the instruction of live video whitening special effect processing
The algorithm quantity of effect, described whitening specially good effect includes that skin color model algorithm, brightness improve algorithm, Image Sharpening Algorithm, wherein, described
Image Sharpening Algorithm includes that image level finds that marginal point algorithm is vertical with image finds marginal point algorithm；
And/or
Second algorithm quantity determines subelement, for determining that corresponding filter is special according to the instruction of live video filter special effect processing
The algorithm quantity of effect, the filter algorithm of described filter specially good effect is corresponding with the filter type that backstage selects；
And/or
Third algorithm quantity determines subelement, for determining corresponding figure according to the weight reducing special effect processing instruction of live video thinning face
As ratio changes the algorithm quantity of specially good effect, it is image stretch and scaling algorithm that described image scaled changes the algorithm of specially good effect.
Realtime video transmission data processing equipment the most according to claim 8, it is characterised in that passage creates and at specially good effect
Reason unit specifically includes:
Passage creates subelement, for the algorithm quantity according to described whitening specially good effect and/or the algorithm quantity of described filter specially good effect
And/or described image scaled changes the algorithm quantity of specially good effect and creates the special effect processing passage of respective amount in described CPU；
Special effect processing subelement, for by described special effect processing passage in described GPU simultaneously by described live video according to
The algorithm of corresponding described whitening specially good effect and/or the algorithm of described filter specially good effect and/or described image scaled change the calculation of specially good effect
Method carries out real-time video special effect processing.
Realtime video transmission data processing equipment the most according to claim 9, it is characterised in that special effect processing subelement
Specifically include:
Whitening special efficacy processing module, if for described whitening specially good effect, then by corresponding described special effect processing passage described
In GPU successively according to described skin color model algorithm, described brightness improve algorithm, described Image Sharpening Algorithm processing sequence to figure
As carrying out real-time video whitening special effect processing；
And/or
Filter special efficacy processing module, if for described filter specially good effect, then by corresponding described special effect processing passage described
GPU carries out the picture point real-time video filter special effect processing of the described filter type selected with described backstage；
And/or
Image scaled changes special efficacy processing module, if changing specially good effect for described image scaled, then by corresponding described spy
Effect treatment channel carries out real time video image ratio change according to described image stretch with scaling algorithm in described GPU to image
Special effect processing.
11. according to the realtime video transmission data processing equipment described in any one in claim 7 to 10, it is characterised in that
Realtime video transmission data processing equipment also includes:
Multi-thread transmission unit, for recording thread simultaneously by video by the main broadcaster's end echo thread created and user side respectively
Specially good effect transmission of video after special effect processing completes enters to main broadcaster's end of corresponding current special effect processing and the user side of viewing video
Row is play.
12. 1 kinds of realtime video transmission data handling systems, it is characterised in that including:
At least one user side, and the realtime video transmission data process dress as described in any one in claim 7 to 11
Put；
At least one described user side is set up with described realtime video transmission data processing equipment communication connection relation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610526058.9A CN106060581B (en) | 2016-07-05 | 2016-07-05 | A kind of realtime video transmission data processing method, apparatus and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610526058.9A CN106060581B (en) | 2016-07-05 | 2016-07-05 | A kind of realtime video transmission data processing method, apparatus and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106060581A true CN106060581A (en) | 2016-10-26 |
| CN106060581B CN106060581B (en) | 2019-05-07 |
Family
ID=57201035
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610526058.9A Active CN106060581B (en) | 2016-07-05 | 2016-07-05 | A kind of realtime video transmission data processing method, apparatus and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106060581B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107295285A (en) * | 2017-08-11 | 2017-10-24 | 腾讯科技（深圳）有限公司 | Processing method, processing unit and the storage medium of video data |
| CN107749956A (en) * | 2017-09-27 | 2018-03-02 | 北京嗨动视觉科技有限公司 | Video source switches special efficacy realization device and video source switching special efficacy implementation method |
| CN107948733A (en) * | 2017-12-04 | 2018-04-20 | 腾讯科技（深圳）有限公司 | Method of video image processing and device, electronic equipment |
| CN108986017A (en) * | 2018-06-29 | 2018-12-11 | 北京微播视界科技有限公司 | Image special effect processing method, device and computer readable storage medium |
| CN109803165A (en) * | 2019-02-01 | 2019-05-24 | 北京达佳互联信息技术有限公司 | Method, apparatus, terminal and the storage medium of video processing |
| CN110012352A (en) * | 2019-04-17 | 2019-07-12 | 广州华多网络科技有限公司 | Image special effect processing method, device and net cast terminal |
| CN111953905A (en) * | 2020-08-26 | 2020-11-17 | 维沃移动通信有限公司 | Beautifying function starting method and device and electronic equipment |
| WO2022001508A1 (en) * | 2020-06-28 | 2022-01-06 | 腾讯科技（深圳）有限公司 | Video special effect processing method and apparatus, and electronic device |
| CN114760492A (en) * | 2022-04-22 | 2022-07-15 | 咪咕视讯科技有限公司 | Live broadcast special effect generation method, device and system and computer readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130120406A1 (en) * | 2011-11-14 | 2013-05-16 | Nvidia Corporation | Graphics processing |
| CN103440117A (en) * | 2013-08-29 | 2013-12-11 | 广东威创视讯科技股份有限公司 | Method and system for video image processing |
| CN103617626A (en) * | 2013-12-16 | 2014-03-05 | 武汉狮图空间信息技术有限公司 | Central processing unit (CPU) and ground power unit (GPU)-based remote-sensing image multi-scale heterogeneous parallel segmentation method |
| CN103686450A (en) * | 2013-12-31 | 2014-03-26 | 广州华多网络科技有限公司 | Video processing method and system |
| US20140368494A1 (en) * | 2013-06-18 | 2014-12-18 | Nvidia Corporation | Method and system for rendering simulated depth-of-field visual effect |
-
2016
- 2016-07-05 CN CN201610526058.9A patent/CN106060581B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130120406A1 (en) * | 2011-11-14 | 2013-05-16 | Nvidia Corporation | Graphics processing |
| US20140368494A1 (en) * | 2013-06-18 | 2014-12-18 | Nvidia Corporation | Method and system for rendering simulated depth-of-field visual effect |
| CN103440117A (en) * | 2013-08-29 | 2013-12-11 | 广东威创视讯科技股份有限公司 | Method and system for video image processing |
| CN103617626A (en) * | 2013-12-16 | 2014-03-05 | 武汉狮图空间信息技术有限公司 | Central processing unit (CPU) and ground power unit (GPU)-based remote-sensing image multi-scale heterogeneous parallel segmentation method |
| CN103686450A (en) * | 2013-12-31 | 2014-03-26 | 广州华多网络科技有限公司 | Video processing method and system |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107295285A (en) * | 2017-08-11 | 2017-10-24 | 腾讯科技（深圳）有限公司 | Processing method, processing unit and the storage medium of video data |
| CN107749956A (en) * | 2017-09-27 | 2018-03-02 | 北京嗨动视觉科技有限公司 | Video source switches special efficacy realization device and video source switching special efficacy implementation method |
| CN107948733A (en) * | 2017-12-04 | 2018-04-20 | 腾讯科技（深圳）有限公司 | Method of video image processing and device, electronic equipment |
| CN107948733B (en) * | 2017-12-04 | 2020-07-10 | 腾讯科技（深圳）有限公司 | Video image processing method and device and electronic equipment |
| CN108986017A (en) * | 2018-06-29 | 2018-12-11 | 北京微播视界科技有限公司 | Image special effect processing method, device and computer readable storage medium |
| CN109803165A (en) * | 2019-02-01 | 2019-05-24 | 北京达佳互联信息技术有限公司 | Method, apparatus, terminal and the storage medium of video processing |
| CN110012352A (en) * | 2019-04-17 | 2019-07-12 | 广州华多网络科技有限公司 | Image special effect processing method, device and net cast terminal |
| WO2022001508A1 (en) * | 2020-06-28 | 2022-01-06 | 腾讯科技（深圳）有限公司 | Video special effect processing method and apparatus, and electronic device |
| CN111953905A (en) * | 2020-08-26 | 2020-11-17 | 维沃移动通信有限公司 | Beautifying function starting method and device and electronic equipment |
| CN111953905B (en) * | 2020-08-26 | 2021-11-16 | 维沃移动通信有限公司 | Beautifying function starting method and device, electronic equipment and readable storage medium |
| CN114760492A (en) * | 2022-04-22 | 2022-07-15 | 咪咕视讯科技有限公司 | Live broadcast special effect generation method, device and system and computer readable storage medium |
| CN114760492B (en) * | 2022-04-22 | 2023-10-20 | 咪咕视讯科技有限公司 | Live special effect generation method, device and system and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106060581B (en) | 2019-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106060581A (en) | Video real-time transmission data processing method, device and system | |
| JP5492087B2 (en) | Content-based image adjustment | |
| WO2018099136A1 (en) | Method and device for denoising image with low illumination, and storage medium | |
| CN105208376B (en) | A kind of digital noise reduction method and apparatus | |
| US20070147504A1 (en) | Selecting key frames from video frames | |
| AU2006252195B2 (en) | MPEG noise reduction | |
| CN104469179A (en) | Method for combining dynamic pictures into mobile phone video | |
| CN111988561B (en) | Adaptive adjustment method and device for video analysis, computer equipment and medium | |
| CN110620924B (en) | Method and device for processing coded data, computer equipment and storage medium | |
| CN111899197B (en) | Image brightening and denoising method and device, mobile terminal and storage medium | |
| Purohit et al. | Depth-guided dense dynamic filtering network for bokeh effect rendering | |
| CN106027854B (en) | A kind of Federated filter noise-reduction method applied in camera suitable for FPGA realization | |
| CN106060544A (en) | Image encoding method and relevant equipment and system | |
| DE112009002346T5 (en) | Processing video data in devices with limited resources | |
| CN105118077A (en) | Method for improving file shooting fluency and system for improving file shooting fluency | |
| CN113253890B (en) | Video image matting method, system and medium | |
| Seizinger et al. | Efficient multi-lens bokeh effect rendering and transformation | |
| CN110378860A (en) | Method, apparatus, computer equipment and the storage medium of restored video | |
| Men et al. | Visual quality assessment for interpolated slow-motion videos based on a novel database | |
| WO2019239396A1 (en) | Method and system for automatic real-time frame segmentation of high resolution video streams into constituent features and modifications of features in each frame to simultaneously create multiple different linear views from same video source | |
| US20230276070A1 (en) | Artificial intelligence (ai) encoding apparatus and method and ai decoding apparatus and method for region of object of interest in image | |
| US20230343017A1 (en) | Virtual viewport generation method and apparatus, rendering and decoding methods and apparatuses, device and storage medium | |
| CN111754412B (en) | Method and device for constructing data pair and terminal equipment | |
| CN105163081A (en) | Real object display method and system based on asynchronous rendering | |
| CN116894770A (en) | Image processing method, image processing apparatus, and computer program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210122 Address after: 510000 3108, 79 Wanbo 2nd Road, Nancun Town, Panyu District, Guangzhou City, Guangdong Province Patentee after: GUANGZHOU CUBESILI INFORMATION TECHNOLOGY Co.,Ltd. Address before: 511449 Wanda Plaza, Nancun Town, Panyu District, Guangzhou City, Guangdong Province Patentee before: GUANGZHOU HUADUO NETWORK TECHNOLOGY Co.,Ltd. |