CN104105006A - Video image processing method and system - Google Patents
Video image processing method and system Download PDFInfo
- Publication number
- CN104105006A CN104105006A CN201410352578.3A CN201410352578A CN104105006A CN 104105006 A CN104105006 A CN 104105006A CN 201410352578 A CN201410352578 A CN 201410352578A CN 104105006 A CN104105006 A CN 104105006A
- Authority
- CN
- China
- Prior art keywords
- roi
- quality control
- control strategy
- server
- image
- 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
Abstract
The invention discloses a video image processing method and system. The method comprises the steps that an ROI calculating server determines the ROI and the non-ROI of images in video image data based on set rules; the ROI calculating server provides the video image data and ROI classification schemes of the video image data for at least one coding server; the coding server obtains coding demands and ROI quality control strategies and selects the ROI classification schemes and the ROI quality control strategies according to the coding demands; the video image data are coded according to the selected ROI classification schemes and the ROI quality control strategies. According to the video image processing method and system, the architectural pattern of separated operation of ROI calculating and video coding is provided. The ROI classification schemes and the ROI quality control strategies can be flexibly combined, and the different coding demands can be better handled. The ROI calculating and coding are operated separately, repeated calculating of the ROI classification schemes of the video image data is not needed, ROI calculating resources are saved, the operation efficiency is improved, and it is ensured that video programs are transmitted in real time.
Description
Technical field
The embodiment of the present invention relates to video processing technique, relates in particular to a kind of method of video image processing and system.
Background technology
Along with the development of video technique and broadcasting media technology, the propagation of vedio data is shared becomes indispensable Information Sharing means in people's work and life.
In the face of the vedio data of magnanimity, in order to reduce transmission code rate, conventionally need to carry out in data source the processing such as compressed encoding to video image.Compression meeting causes certain loss to the quality of video image, is difficult to take into account the relation between transmission code rate and video quality.Meanwhile, the same vedio data providing for same data source, different recipients also has different quality requirements and transmittability restriction, and this is also for the processing procedure of vedio data is had higher requirement.
So, if can be good at taking into account video quality, transmission code rate and different recipients' flexible demands, become and in video image processing technology, need one of problem of solution.
Summary of the invention
The invention provides a kind of method of video image processing and system, to optimize video image processing technology, improve its flexibility.
First aspect, the embodiment of the present invention provides a kind of method of video image processing, comprising:
ROI and the non-ROI of region of interest ROI calculation server based on setting image in the definite vedio data of rule;
Described ROI calculation server is by described vedio data, and the ROI splitting scheme of described vedio data, offers at least one encoder server;
Described encoder server obtains coding demand and ROI Quality Control Strategy, and selects described ROI splitting scheme and ROI Quality Control Strategy according to described coding demand;
Described encoder server according to the described ROI splitting scheme of selecting and ROI Quality Control Strategy to the processing of encoding of described vedio data.
Second aspect, the embodiment of the present invention also provides a kind of video image processing system, comprises region of interest ROI calculation server and at least one encoder server, wherein:
Described ROI calculation server comprises that ROI determination module and data provide module, described ROI determination module is for ROI and non-ROI based on setting the definite vedio data image of rule, described data provide module for by described vedio data, and the ROI splitting scheme of described vedio data, offer at least one encoder server;
Each described encoder server, interact with described ROI calculation server, comprise policy selection module and image coding module, described policy selection module is used for obtaining coding demand and ROI Quality Control Strategy, and select described ROI splitting scheme and ROI Quality Control Strategy according to described coding demand, described image coding module for according to the described ROI splitting scheme of selecting and ROI Quality Control Strategy to the processing of encoding of described vedio data.
The embodiment of the present invention provides a kind of ROI is calculated with Video coding and divides the architecture mode of open shop.Utilize this pattern, the operator that manipulates each encoder server can flexible assembling ROI splitting scheme and ROI Quality Control Strategy, can better tackle different coding demands.By the calculating of ROI and a coding point open shop, make the vedio data ROI splitting scheme needn't double counting, save ROI computational resource, improve operation efficiency, ensure real-time transmission of video program.
Brief description of the drawings
The flow chart of a kind of method of video image processing that Fig. 1 provides for the embodiment of the present invention one;
Fig. 2 is the configuration diagram of the applicable video image processing system of the embodiment of the present invention;
The configuration diagram of a kind of video image processing system that Fig. 3 provides for the embodiment of the present invention two.
Embodiment
Below in conjunction with drawings and Examples, the present invention is described in further detail.Be understandable that, specific embodiment described herein is only for explaining the present invention, but not limitation of the invention.It also should be noted that, for convenience of description, in accompanying drawing, only show part related to the present invention but not entire infrastructure.
Embodiment mono-
The flow chart of a kind of method of video image processing that Fig. 1 provides for the embodiment of the present invention one, the present embodiment carries out area-of-interest (Region of Interesting applicable to the vedio data that data source is provided, be called for short ROI) situation about processing of calculating and encode, the method is carried out by video image processing system, this system as shown in Figure 2, comprise ROI calculation server 210 and at least one encoder server 220, two kinds of preferably physically independent settings of server, but also can physically be integrated among a station server, realize respectively the logic function of two kinds of servers.
The method specifically comprises the steps:
Step 110, ROI and the non-ROI of ROI calculation server based on setting image in the definite vedio data of rule;
Above-mentioned steps is for determining ROI and the non-ROI of vedio data image, can be to all or part of two field picture in video, determining frame by frame, can be also multiple image to be carried out to batch determine, finally forms the ROI splitting scheme of image in vedio data.Setting rule can have multiple way of realization, for example, and can be by user by the ROI in the mode manual markings image of man-machine interaction.Or, based on vision noticing mechanism, by setting up the significance of feature in visual attention model computed image, then extract the region at conspicuousness higher feature place in image, as ROI.This significance is the contrast effect of other pixel character pair in certain feature of pixel in image and its surrounding environment.
As preferably, in the embodiment of the present invention, also provide a kind of definite method more succinct, and the ROI that amount of calculation is little determines rule, it is described ROI calculation server, in described vedio data, carry out zone line, human face region and/or caption area identification for image, using the region recognizing as described ROI, remaining area is as non-ROI.Technique scheme is determining when ROI, the mode that has adopted fixing ROI region to combine with unsteady ROI region.Zone line can be set as fixing ROI region, all can be using fixing zone line as ROI region in every frame.Human face region, caption area are also set as unsteady ROI region, in each frame, carry out the targeted identification of face and captions, determine the ROI region of floating and changing.In this operation scheme, three class regions are defined as to ROI region, both specified without man-machine interactively, so determine that mode is succinct, three class regions have covered the position that people pays close attention to substantially simultaneously, so determining of ROI is comparatively accurate, also less to the amount of calculation of region identification.Certainly, target area can be not limited to above-mentioned three classes, also can determine according to demand the target area of other targeted features.For example, can also be using mobile object region as unsteady ROI region, the face of cartoon character also can be used as face and identifies, the such as mammoth in Ice Age etc.The identification of mobile object can be associated before and after the image of several frames determine.
Step 120, described ROI calculation server are by described vedio data, and the ROI splitting scheme of described vedio data, offer at least one encoder server;
ROI splitting scheme can be represented by various ways, for example, inform ROI and the non-ROI dividing condition in image by the mode such as area coordinate, pixel coordinate to encoder server.The mark that vedio data specifically can be provided, for example program number, represents vedio data, then frame number and corresponding ROI splitting scheme are provided, and determines the ROI dividing condition of each two field picture.In the time setting rule difference, to same image, likely produce one or more ROI splitting schemes.
Step 130, described encoder server obtain coding demand and ROI Quality Control Strategy, and select described ROI splitting scheme and ROI Quality Control Strategy according to described coding demand;
For any one encoder server, it can determine coding demand according to the situation of self or video image recipient's situation.For example, this encoder server may need to provide high definition, SD or smooth picture, or may its transmission bandwidth changes and need to adjust encoding rate etc.Can determine encoding scheme by above-mentioned factor.ROI Quality Control Strategy is the strategy for determine the quality treatment how ROI and non-ROI are distinguished on ROI splitting scheme basis.This control strategy is one or more, specified by third party effector, or pre-configured multiple at encoder server, also can be specified by ROI calculation server.Encoder server can, according to coding demand, be selected ROI splitting scheme and corresponding ROI Quality Control Strategy.
Step 140, described encoder server according to the described ROI splitting scheme of selecting and ROI Quality Control Strategy to the processing of encoding of described vedio data.
Preferably, in described ROI Quality Control Strategy, after the processing of described ROI picture quality higher than the processing of described non-ROI after picture quality.Conventionally, ROI is the region that people's emphasis can be paid close attention to, so can control the picture quality of ROI higher than the picture quality of non-ROI, for example, makes the definition of ROI high, but not ROI is comparatively fuzzy etc.The control of this picture quality is typically embodied on compression quality, be described encoder server according to the described ROI splitting scheme of selecting and ROI Quality Control Strategy to the encode operation of processing of described vedio data, be specifically as follows: described encoder server is according to described ROI splitting scheme and the ROI Quality Control Strategy selected, adopt the first compression algorithm to compress to described ROI, adopt the second compression algorithm to compress to described non-ROI, wherein, the image impairment rate of described the first compression algorithm is lower than the image impairment rate of described the second compression algorithm.For example can with QP, (coding be quoted in printable character, Quoted-printable) method is carried out compressed encoding, and control the parameter that damages in this Lossy Compression Algorithm, realize different picture quality, ROI Quality Control Strategy is QP difference strategy.
The embodiment of the present invention provides a kind of ROI is calculated with Video coding and divides the architecture mode of open shop.Utilize this pattern, the operator that manipulates each encoder server can flexible assembling ROI splitting scheme and ROI Quality Control Strategy, can better tackle different coding demands.By the calculating of ROI and a coding point open shop, make the vedio data ROI splitting scheme needn't double counting, save ROI computational resource, improve operation efficiency, ensure real-time transmission of video program.In practical application, this scheme can realize real-time Transmission 70 road programs in the digital bandwidth of 1 road 38M.
Embodiment bis-
The configuration diagram of a kind of video image processing system that Fig. 3 provides for the embodiment of the present invention two, this system comprises ROI calculation server 210 and at least one encoder server 220, Figure 3 shows that the situation that comprises an encoder server 220, Figure 2 shows that the situation that comprises multiple encoder servers 220.Described ROI calculation server 210 and described encoder server 220 be independent setting physically, carries out data interaction by wired or wireless mode.
The architecture mode of this system is not limited to, shown in Fig. 2 and Fig. 3, can also have multiple implementation, and for example, also integrated being arranged in a station server physically of ROI calculation server and described encoder server, realizes respectively its logic function.The quantity of ROI calculation server can be multiple, is mutual annexation the more with each encoder server, thereby ROI can be calculated and carries out distributed treatment.
Described ROI calculation server 210 comprises that ROI determination module 211 and data provide module 212, described ROI determination module 211 is for ROI and non-ROI based on setting the definite vedio data image of rule, described data provide module 212 for by described vedio data, and the ROI splitting scheme of described vedio data, offer at least one encoder server 220;
Each described encoder server 220, interact with described ROI calculation server 210, comprise policy selection module 221 and image coding module 222, described policy selection module 221 is for obtaining coding demand and ROI Quality Control Strategy, and select described ROI splitting scheme and ROI Quality Control Strategy according to described coding demand, described image coding module 222 for according to the described ROI splitting scheme of selecting and ROI Quality Control Strategy to the processing of encoding of described vedio data.
On such scheme basis, in preferred described ROI Quality Control Strategy, after the processing of described ROI picture quality higher than the processing of described non-ROI after picture quality.
Described policy selection module 221 specifically can be used for according to described ROI splitting scheme and the ROI Quality Control Strategy selected, adopt the first compression algorithm to compress to described ROI, adopt the second compression algorithm to compress to described non-ROI, wherein, the image impairment rate of described the first compression algorithm is lower than the image impairment rate of described the second compression algorithm.
Described ROI determination module 211 is specifically used in described vedio data and carries out zone line, human face region and/or subtitle region identification for image, and using the region recognizing as described ROI, remaining area is as non-ROI.
The said goods can be carried out the method that any embodiment of the present invention provides, and possesses the corresponding functional module of manner of execution and beneficial effect.
The embodiment of the present invention provides a kind of ROI is calculated with Video coding and divides the architecture mode of open shop.Utilize this pattern, the operator that manipulates each encoder server can flexible assembling ROI splitting scheme and ROI Quality Control Strategy, can better tackle different coding demands.By the calculating of ROI and a coding point open shop, make the vedio data ROI splitting scheme needn't double counting, save ROI computational resource, improve operation efficiency, ensure real-time transmission of video program.
Note, above are only preferred embodiment of the present invention and institute's application technology principle.Skilled person in the art will appreciate that and the invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art various obvious variations, readjust and substitute and can not depart from protection scope of the present invention.Therefore, although the present invention is described in further detail by above embodiment, the present invention is not limited only to above embodiment, in the situation that not departing from the present invention's design, can also comprise more other equivalent embodiment, and scope of the present invention is determined by appended claim scope.
Claims (9)
1. a method of video image processing, is characterized in that, comprising:
ROI and the non-ROI of region of interest ROI calculation server based on setting image in the definite vedio data of rule;
Described ROI calculation server is by described vedio data, and the ROI splitting scheme of described vedio data, offers at least one encoder server;
Described encoder server obtains coding demand and ROI Quality Control Strategy, and selects described ROI splitting scheme and ROI Quality Control Strategy according to described coding demand;
Described encoder server according to the described ROI splitting scheme of selecting and ROI Quality Control Strategy to the processing of encoding of described vedio data.
2. method according to claim 1, is characterized in that: in described ROI Quality Control Strategy, after the processing of described ROI picture quality higher than the processing of described non-ROI after picture quality.
3. method according to claim 2, is characterized in that, described encoder server according to select described ROI splitting scheme and ROI Quality Control Strategy to described vedio data encode processing comprise:
Described encoder server is according to described ROI splitting scheme and the ROI Quality Control Strategy selected, adopt the first compression algorithm to compress to described ROI, adopt the second compression algorithm to compress to described non-ROI, wherein, the image impairment rate of described the first compression algorithm is lower than the image impairment rate of described the second compression algorithm.
4. according to the arbitrary described method of claim 1-3, it is characterized in that, described ROI calculation server determines that based on setting rule ROI and the non-ROI of image in vedio data comprise:
Described ROI calculation server carries out zone line, human face region and/or subtitle region identification for image in described vedio data, and using the region recognizing as described ROI, remaining area is as non-ROI.
5. a video image processing system, is characterized in that, comprises region of interest ROI calculation server and at least one encoder server, wherein:
Described ROI calculation server comprises that ROI determination module and data provide module, described ROI determination module is for ROI and non-ROI based on setting the definite vedio data image of rule, described data provide module for by described vedio data, and the ROI splitting scheme of described vedio data, offer at least one encoder server;
Each described encoder server, interact with described ROI calculation server, comprise policy selection module and image coding module, described policy selection module is used for obtaining coding demand and ROI Quality Control Strategy, and select described ROI splitting scheme and ROI Quality Control Strategy according to described coding demand, described image coding module for according to the described ROI splitting scheme of selecting and ROI Quality Control Strategy to the processing of encoding of described vedio data.
6. system according to claim 5, is characterized in that, in described ROI Quality Control Strategy, after the processing of described ROI picture quality higher than the processing of described non-ROI after picture quality.
7. system according to claim 6, it is characterized in that, described policy selection module specifically for according to select described ROI splitting scheme and ROI Quality Control Strategy, adopt the first compression algorithm to compress to described ROI, adopt the second compression algorithm to compress to described non-ROI, wherein, the image impairment rate of described the first compression algorithm is lower than the image impairment rate of described the second compression algorithm.
8. according to the arbitrary described system of claim 5-7, it is characterized in that, described ROI determination module specifically for carrying out zone line, human face region and/or subtitle region identification for image in described vedio data, and using the region recognizing as described ROI, remaining area is as non-ROI.
9. system according to claim 6, is characterized in that, described ROI calculation server and described encoder server physically independently arrange, and carry out data interaction by wired or wireless mode.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410352578.3A CN104105006B (en) | 2014-07-23 | 2014-07-23 | A kind of method of video image processing and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410352578.3A CN104105006B (en) | 2014-07-23 | 2014-07-23 | A kind of method of video image processing and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104105006A true CN104105006A (en) | 2014-10-15 |
| CN104105006B CN104105006B (en) | 2017-12-26 |
Family
ID=51672758
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410352578.3A Active CN104105006B (en) | 2014-07-23 | 2014-07-23 | A kind of method of video image processing and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104105006B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106412563A (en) * | 2016-09-30 | 2017-02-15 | 珠海市魅族科技有限公司 | Image display method and apparatus |
| CN106550240A (en) * | 2016-12-09 | 2017-03-29 | 武汉斗鱼网络科技有限公司 | A kind of bandwidth conservation method and system |
| CN106572350A (en) * | 2015-10-08 | 2017-04-19 | 三星电子株式会社 | Electronic device configured to non-uniformly encode/decode image data according to display shape |
| CN108076113A (en) * | 2016-11-15 | 2018-05-25 | 同方威视技术股份有限公司 | For method, server and the system operated to safety inspection data |
| CN108700988A (en) * | 2016-02-15 | 2018-10-23 | 电子湾有限公司 | Digital picture is presented |
| WO2021057689A1 (en) * | 2019-09-27 | 2021-04-01 | 腾讯科技（深圳）有限公司 | Video decoding method and apparatus, video encoding method and apparatus, storage medium, and electronic device |
| CN112954355A (en) * | 2017-06-21 | 2021-06-11 | 西安万像电子科技有限公司 | Image frame processing method and device |
| CN112995488A (en) * | 2019-12-12 | 2021-06-18 | 深圳富泰宏精密工业有限公司 | High-resolution video image processing method and device and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101001372A (en) * | 2006-01-09 | 2007-07-18 | 三星电子株式会社 | Method and apparatus for encoding/decoding image based on region of interest |
| US20100172404A1 (en) * | 2009-01-08 | 2010-07-08 | Michael Anthony Isnardi | Method and System for Providing Region-of-Interest Video Compression |
| CN103442225A (en) * | 2013-07-26 | 2013-12-11 | 清华大学 | Remote sensing image transmission system based on database online learning update limited rate |
-
2014
- 2014-07-23 CN CN201410352578.3A patent/CN104105006B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101001372A (en) * | 2006-01-09 | 2007-07-18 | 三星电子株式会社 | Method and apparatus for encoding/decoding image based on region of interest |
| US20100172404A1 (en) * | 2009-01-08 | 2010-07-08 | Michael Anthony Isnardi | Method and System for Providing Region-of-Interest Video Compression |
| CN103442225A (en) * | 2013-07-26 | 2013-12-11 | 清华大学 | Remote sensing image transmission system based on database online learning update limited rate |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106572350A (en) * | 2015-10-08 | 2017-04-19 | 三星电子株式会社 | Electronic device configured to non-uniformly encode/decode image data according to display shape |
| CN108700988A (en) * | 2016-02-15 | 2018-10-23 | 电子湾有限公司 | Digital picture is presented |
| CN108700988B (en) * | 2016-02-15 | 2021-05-25 | 电子湾有限公司 | Digital image presentation |
| US11681745B2 (en) | 2016-02-15 | 2023-06-20 | Ebay Inc. | Digital image presentation |
| CN106412563A (en) * | 2016-09-30 | 2017-02-15 | 珠海市魅族科技有限公司 | Image display method and apparatus |
| CN108076113A (en) * | 2016-11-15 | 2018-05-25 | 同方威视技术股份有限公司 | For method, server and the system operated to safety inspection data |
| CN106550240A (en) * | 2016-12-09 | 2017-03-29 | 武汉斗鱼网络科技有限公司 | A kind of bandwidth conservation method and system |
| WO2018103243A1 (en) * | 2016-12-09 | 2018-06-14 | 武汉斗鱼网络科技有限公司 | Bandwidth conserving method, system, live-streaming terminal, and readable storage medium |
| CN112954355B (en) * | 2017-06-21 | 2022-12-09 | 西安万像电子科技有限公司 | Image frame processing method and device |
| CN112954355A (en) * | 2017-06-21 | 2021-06-11 | 西安万像电子科技有限公司 | Image frame processing method and device |
| CN113163202A (en) * | 2017-06-21 | 2021-07-23 | 西安万像电子科技有限公司 | Image frame compression method and device |
| CN113163202B (en) * | 2017-06-21 | 2022-10-18 | 西安万像电子科技有限公司 | Image frame compression method and device |
| WO2021057689A1 (en) * | 2019-09-27 | 2021-04-01 | 腾讯科技（深圳）有限公司 | Video decoding method and apparatus, video encoding method and apparatus, storage medium, and electronic device |
| CN112995488A (en) * | 2019-12-12 | 2021-06-18 | 深圳富泰宏精密工业有限公司 | High-resolution video image processing method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104105006B (en) | 2017-12-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104105006A (en) | Video image processing method and system | |
| US11153604B2 (en) | Image compression for digital reality | |
| EP3316589B1 (en) | Video synchronization device and video synchronization method | |
| CN105391972B (en) | Image communication apparatus, image transmission apparatus, and image reception apparatus | |
| KR102472971B1 (en) | Method, system, and computer program to optimize video encoding using artificial intelligence model | |
| CN103716643A (en) | System and method for improving video encoding using content information | |
| CN109698957A (en) | Image encoding method, calculates equipment and storage medium at device | |
| CN110166796A (en) | Processing method, device, computer-readable medium and the electronic equipment of video frame | |
| JP5950605B2 (en) | Image processing system and image processing method | |
| JP2009141815A (en) | Image encoding method, apparatus and program | |
| CN110418142A (en) | A kind of coding method based on video interested region, device, storage medium | |
| CN106921840B (en) | Face beautifying method, device and system in instant video | |
| US11006184B2 (en) | Enhanced distribution image system | |
| EP3515082B1 (en) | Server device for streaming video content and client device for receiving and rendering video content | |
| US20230108722A1 (en) | Allocating bit rate between video streams using machine learning | |
| CN115567712A (en) | Screen content video coding perception code rate control method and device based on just noticeable distortion by human eyes | |
| CN100385453C (en) | System and method for processing image data | |
| CN115278250A (en) | Low-bandwidth video transmission method and conference system | |
| CN112862842B (en) | Image data processing method and device, storage medium and electronic device | |
| US11350134B2 (en) | Encoding apparatus, image interpolating apparatus and encoding program | |
| CN116601958A (en) | Virtual viewpoint drawing, rendering and decoding methods and devices, equipment and storage medium | |
| CN110855989A (en) | Network video image coding method and device | |
| CN113678431A (en) | Image transmission/reception system, image transmission device, image reception device, image transmission/reception method, and program | |
| US11825066B2 (en) | Video reproduction apparatus, reproduction method, and program | |
| CN102075734B (en) | Video service implementation method and equipment and system thereof |
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 |