CN104105006B - A kind of method of video image processing and system - Google Patents
A kind of method of video image processing and system Download PDFInfo
- Publication number
- CN104105006B CN104105006B CN201410352578.3A CN201410352578A CN104105006B CN 104105006 B CN104105006 B CN 104105006B CN 201410352578 A CN201410352578 A CN 201410352578A CN 104105006 B CN104105006 B CN 104105006B
- Authority
- CN
- China
- Prior art keywords
- roi
- quality control
- control strategies
- vedio data
- splitting schemes
- 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.)
- Active
Links
Abstract
The invention discloses a kind of method of video image processing and system.This method includes:ROI calculation servers determine the ROI and non-ROI of image in vedio data based on setting rule;ROI calculation servers are by the ROI splitting schemes of the vedio data, and vedio data, there is provided at least one encoder server;Encoder server obtains code requirement and ROI Quality Control Strategies, and selects ROI splitting schemes and ROI Quality Control Strategies according to code requirement;Coded treatment is carried out to vedio data according to the ROI splitting schemes of selection and ROI Quality Control Strategies.The invention provides a kind of architecture mode for calculating ROI and separately being run with Video coding.Different code requirements can preferably be tackled with flexible assembling ROI splitting schemes and ROI Quality Control Strategies.By the separately operation of ROI calculating and coding so that vedio data ROI splitting schemes need not compute repeatedly, and save ROI computing resources, improve operation efficiency, ensure real-time transmission video frequency program.
Description
Technical field
The present embodiments relate to video processing technique, more particularly to a kind of method of video image processing and system.
Background technology
With the development of video technique and broadcasting media technology, the propagation of vedio data is shared turns into people's work
With Information Sharing means indispensable in life.
In face of the vedio data of magnanimity, in order to reduce transmission code rate, it usually needs in data source to video figure
As being compressed the processing such as coding.Compression certain loss can be caused to the quality of video image, it is difficult to take into account transmission code rate with
Relation between video quality.Meanwhile also can for the same vedio data that same data source provides, different recipients
There are different quality requirements and transmittability limitation, this also proposes higher requirement for the processing procedure of vedio data.
So, if it is possible to the flexible demands of video quality, transmission code rate and different recipients are taken into account well, are turned into
One of need to solve the problems, such as in video image processing technology.
The content of the invention
The present invention provides a kind of method of video image processing and system, to optimize video image processing technology, improves its spirit
Activity.
In a first aspect, the embodiments of the invention provide a kind of method of video image processing, including:
Region of interest ROI calculation server determines in vedio data the ROI of image and non-based on setting rule
ROI;
The ROI calculation servers are by the ROI division sides of the vedio data, and the vedio data
Case, there is provided at least one encoder server;
The encoder server obtains code requirement and ROI Quality Control Strategies, and selects institute according to the code requirement
State ROI splitting schemes and ROI Quality Control Strategies;
The encoder server is according to the ROI splitting schemes and ROI Quality Control Strategies of selection to the video figure
As data carry out coded treatment.
Second aspect, the embodiment of the present invention additionally provide a kind of video image processing system, including region of interest ROI meter
Server and at least one encoder server are calculated, wherein:
The ROI calculation servers include ROI determining modules and data providing module, and the ROI determining modules are used for base
The ROI and non-ROI of image in vedio data are determined in setting rule, the data providing module is used for the video figure
As data, and the ROI splitting schemes of the vedio data, there is provided at least one encoder server;
Each encoder server, is interacted with the ROI calculation servers, including strategy selection module and image are compiled
Code module, the strategy selection module is used to obtain code requirement and ROI Quality Control Strategies, and is selected according to the code requirement
The ROI splitting schemes and ROI Quality Control Strategies are selected, described image coding module is used to divide according to the ROI of selection
Scheme and ROI Quality Control Strategies carry out coded treatment to the vedio data.
The embodiments of the invention provide a kind of architecture mode for calculating ROI and separately being run with Video coding.Utilize the mould
Formula, the operator for manipulating each encoder server can be with flexible assembling ROI splitting schemes and ROI Quality Control Strategies, can be preferably
Tackle different code requirements.By the separately operation of ROI calculating and coding so that vedio data ROI splitting schemes need not
Compute repeatedly, save ROI computing resources, improve operation efficiency, ensure real-time transmission video frequency program.
Brief description of the drawings
Fig. 1 is a kind of flow chart for method of video image processing that the embodiment of the present invention one provides;
The configuration diagram for the video image processing system that Fig. 2 is applicable by the embodiment of the present invention;
Fig. 3 is a kind of configuration diagram for video image processing system that the embodiment of the present invention two provides.
Embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention, rather than limitation of the invention.It also should be noted that in order to just
Part related to the present invention rather than entire infrastructure are illustrate only in description, accompanying drawing.
Embodiment one
Fig. 1 is a kind of flow chart for method of video image processing that the embodiment of the present invention one provides, and the present embodiment is applicable
Area-of-interest (Region of Interesting, abbreviation ROI) is carried out in the vedio data for providing data source to calculate
With the situation of coded treatment, this method is performed by video image processing system, and the system takes as shown in Fig. 2 being calculated including ROI
Business device 210 and at least one encoder server 220, two kinds of servers are preferably physically independently arranged, but can also be physically
It is integrated among a server, realizes the logic function of two kinds of servers respectively.
This method specifically comprises the following steps:
Step 110, ROI calculation servers determine the ROI and non-ROI of image in vedio data based on setting rule;
Above-mentioned steps are used to determine the ROI of image and non-ROI in vedio data, can be to the whole in video or
Part two field picture, it is determined by frame or batch determination is carried out to multiple image, ultimately formed in vedio data
The ROI splitting schemes of image.Setting rule can have a variety of ways of realization, for example, the side that can pass through man-machine interaction by user
ROI in formula manual markings image.Or view-based access control model attention mechanism, calculate spy in image by establishing visual attention model
The significance of sign, the region in image where conspicuousness higher feature is then extracted, as ROI.The significance is picture in image
Some feature of element and the contrast effect of other pixel character pairs in its surrounding environment.
Preferably, being additionally provided in the embodiment of the present invention, a kind of determination method is more succinct, and amount of calculation it is small ROI it is true
Set pattern then, i.e., described ROI calculation servers, intermediate region, human face region is carried out in the vedio data for image
And/or caption area identification, using the region recognized as the ROI, remaining area is as non-ROI.Above-mentioned technical proposal exists
When determining ROI, the mode that fixed ROI region is combined with floating ROI region is employed.Intermediate region can be set as fixation
ROI region, per can be using fixed intermediate region as ROI region in frame.Human face region, caption area are also set up as floating
Dynamic ROI region, i.e., carry out the targeted identification of face and captions in each frame, it is determined that the ROI region for change of floating.The operation
In scheme, three class regions are defined as ROI region, both specified without man-machine interactively, institute is succinct in a deterministic manner, while three classes
Region substantially covers the position that people pays close attention to, so ROI determination is more accurate, to the amount of calculation of region recognition
It is smaller.Certainly, target area can be not limited to above-mentioned three class, can also determine the target of other targeted features according to demand
Region.For example, it is also possible to mobile object region can also be regard as people as the ROI region floated, the face of cartoon character
Face is identified, such as mammoth in Ice Age etc..The image that the identification of mobile object can associate front and rear several frames comes
It is determined that.
Step 120, the ROI calculation servers are by the vedio data, and the ROI of the vedio data
Splitting scheme, there is provided at least one encoder server;
ROI splitting schemes can be represented by various ways, such as be taken with modes such as area coordinate, pixel coordinates to coding
ROI and non-ROI dividing conditions in device notification image of being engaged in.The mark of vedio data, such as program number can be specifically provided,
To represent vedio data, then frame number and corresponding ROI splitting schemes are provided, to determine the ROI dividing conditions of each two field picture.
When setting rule is different, to same image, it is possible to produce one or more ROI splitting schemes.
Step 130, the encoder server obtain code requirement and ROI Quality Control Strategies, and according to the coding need
Ask the selection ROI splitting schemes and ROI Quality Control Strategies;
For any one encoder server, it can be according to itself situation or the situation of video image recipient
To determine code requirement.For example, the encoder server may need to provide high definition, SD or smooth picture, or may its biography
Defeated bandwidth, which changes, to be needed to adjust encoding rate etc..Encoding scheme can be determined by above-mentioned factor.ROI Quality Control Strategies are to use
In being determined on the basis of ROI splitting schemes to the strategy of the quality treatment how to be distinguished of ROI and non-ROI.The control strategy
For one or more, specified by third party effector, or be pre-configured with encoder server a variety of, can also calculated by ROI
Server is specified.Encoder server can select ROI splitting schemes and corresponding ROI Quality Control Strategies according to code requirement.
Step 140, the encoder server are according to the ROI splitting schemes and ROI Quality Control Strategies of selection to institute
State vedio data and carry out coded treatment.
Preferably, in the ROI Quality Control Strategies, picture quality is higher than the place of the non-ROI after the processing of the ROI
Picture quality after reason.Generally, ROI is the region that people's emphasis can be paid close attention to, so controllable ROI picture quality is higher than non-ROI
Picture quality, such as so that ROI definition is high, rather than ROI more fuzzy etc..The typical body of control of the picture quality
On present compression quality, i.e., described encoder server is according to the ROI splitting schemes and ROI Quality Control Strategies of selection to institute
The operation that vedio data carries out coded treatment is stated, is specifically as follows:The encoder server is drawn according to the ROI of selection
Offshoot program and ROI Quality Control Strategies, the ROI is compressed using the first compression algorithm, second is used to the non-ROI
Compression algorithm is compressed, wherein, the image impairment rate of first compression algorithm is less than the image of second compression algorithm
Loss late.Such as QP (printable character quotes coding, Quoted-printable) method can be used to be compressed coding, and control
Make in this Lossy Compression Algorithm and damage parameter, to realize different picture quality, then ROI Quality Control Strategies are QP differences
Strategy.
The embodiments of the invention provide a kind of architecture mode for calculating ROI and separately being run with Video coding.Utilize the mould
Formula, the operator for manipulating each encoder server can be with flexible assembling ROI splitting schemes and ROI Quality Control Strategies, can be preferably
Tackle different code requirements.By the separately operation of ROI calculating and coding so that vedio data ROI splitting schemes need not
Compute repeatedly, save ROI computing resources, improve operation efficiency, ensure real-time transmission video frequency program., should in practical application
Scheme can realize the road program of real-time Transmission 70 in 1 road 38M digital bandwidth.
Embodiment two
Fig. 3 is a kind of configuration diagram for video image processing system that the embodiment of the present invention two provides, and the system includes
ROI calculation servers 210 and at least one encoder server 220, Fig. 3 show the situation for including an encoder server 220,
Fig. 2 show the situation for including multiple encoder servers 220.The ROI calculation servers 210 and the encoder server 220
Physically it is independently arranged, data interaction is carried out by wired or wireless way.
The architecture mode of the system is not limited to shown in Fig. 2 and Fig. 3, can also there is a variety of implementations, for example, ROI is counted
Calculating server and the encoder server can also be physically integrated and be arranged in a server, realize its logic work(respectively
Energy.The quantity of ROI calculation servers can be multiple, with each encoder server in interactive connection relation the more, so as to
ROI is calculated and carries out distributed treatment.
The ROI calculation servers 210 include ROI determining modules 211 and data providing module 212, and the ROI determines mould
Block 211 is used for the ROI and non-ROI that image in vedio data is determined based on setting rule, and the data providing module 212 is used
In by the ROI splitting schemes of the vedio data, and the vedio data, there is provided at least one encoding service
Device 220;
Each encoder server 220, interacts with the ROI calculation servers 210, including strategy selection module
221 and image coding module 222, the strategy selection module 221 is used to obtain code requirement and ROI Quality Control Strategies, and
The ROI splitting schemes and ROI Quality Control Strategies, described image coding module 222 is selected to be used for according to the code requirement
Coded treatment is carried out to the vedio data according to the ROI splitting schemes of selection and ROI Quality Control Strategies.
On the basis of such scheme, in the preferable ROI Quality Control Strategies, picture quality after the processing of the ROI
Picture quality after processing higher than the non-ROI.
The strategy selection module 221 is particularly used in ROI splitting schemes and ROI the quality control plan according to selection
Slightly, the ROI is compressed using the first compression algorithm, the non-ROI is compressed using the second compression algorithm, its
In, the image impairment rate of first compression algorithm is less than the image impairment rate of second compression algorithm.
The ROI determining modules 211 be particularly used in the vedio data for image carry out intermediate region,
Human face region and/or subtitle region identification, using the region recognized as the ROI, remaining area is as non-ROI.
The said goods can perform the method that any embodiment of the present invention is provided, and possess the corresponding functional module of execution method
And beneficial effect.
The embodiments of the invention provide a kind of architecture mode for calculating ROI and separately being run with Video coding.Utilize the mould
Formula, the operator for manipulating each encoder server can be with flexible assembling ROI splitting schemes and ROI Quality Control Strategies, can be preferably
Tackle different code requirements.By the separately operation of ROI calculating and coding so that vedio data ROI splitting schemes need not
Compute repeatedly, save ROI computing resources, improve operation efficiency, ensure real-time transmission video frequency program.
Pay attention to, above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art various obvious changes,
Readjust and substitute without departing from protection scope of the present invention.Therefore, although being carried out by above example to the present invention
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
Other more equivalent embodiments can be included, and the scope of the present invention is determined by scope of the appended claims.
Claims (9)
- A kind of 1. method of video image processing, it is characterised in that including:Region of interest ROI calculation server determines the ROI and non-ROI of image in vedio data based on setting rule, its In, the quantity of the ROI calculation servers is multiple;The ROI calculation servers carry the ROI splitting schemes of the vedio data, and the vedio data Supply at least one encoder server;The encoder server obtains code requirement and ROI Quality Control Strategies, and is counted according to the code requirement from multiple ROI Calculate and ROI splitting schemes are selected in multiple ROI splitting schemes that server provides and are selected from multiple ROI Quality Control Strategies ROI Quality Control Strategies, to realize flexible assembling ROI splitting schemes and ROI Quality Control Strategies;The encoder server enters according to the ROI splitting schemes and ROI Quality Control Strategies of selection to the vedio data Row coded treatment.
- 2. according to the method for claim 1, it is characterised in that:In the ROI Quality Control Strategies, the processing of the ROI Picture quality after processing of the picture quality higher than the non-ROI afterwards.
- 3. according to the method for claim 2, it is characterised in that the encoder server divides according to the ROI of selection Scheme and ROI Quality Control Strategies carry out coded treatment to the vedio data to be included:The encoder server is according to the ROI splitting schemes and ROI Quality Control Strategies of selection, to the ROI using the One compression algorithm is compressed, and the non-ROI is compressed using the second compression algorithm, wherein, first compression algorithm Image impairment rate be less than second compression algorithm image impairment rate.
- 4. according to any described methods of claim 1-3, it is characterised in that the ROI calculation servers are based on setting rule Determine that the ROI of image and non-ROI include in vedio data:The ROI calculation servers, in the vedio data for image carry out intermediate region, human face region and/or Subtitle region identifies that, using the region recognized as the ROI, remaining area is as non-ROI.
- 5. a kind of video image processing system, it is characterised in that including multiple semi-cylindrical hills ROI calculation servers and at least one Individual encoder server, wherein:The ROI calculation servers include ROI determining modules and data providing module, and the ROI determining modules are used to be based on setting Set pattern then determines the ROI and non-ROI of image in vedio data, and the data providing module is used for the video image number According to, and the ROI splitting schemes of the vedio data, there is provided at least one encoder server;Each encoder server, interacts with the ROI calculation servers, including strategy selection module and Image Coding mould Block, the strategy selection module are used to obtain code requirement and ROI Quality Control Strategies, and according to the code requirement from multiple ROI splitting schemes are selected in multiple ROI splitting schemes that ROI calculation servers provide and from multiple ROI Quality Control Strategies Middle selection ROI Quality Control Strategies, to realize flexible assembling ROI splitting schemes and ROI Quality Control Strategies, described image coding Module is used to carry out coded treatment to the vedio data according to the ROI splitting schemes and ROI Quality Control Strategies of selection.
- 6. system according to claim 5, it is characterised in that in the ROI Quality Control Strategies, the processing of the ROI Picture quality after processing of the picture quality higher than the non-ROI afterwards.
- 7. system according to claim 6, it is characterised in that the strategy selection module is specifically used for the institute according to selection ROI splitting schemes and ROI Quality Control Strategies are stated, the ROI is compressed using the first compression algorithm, to the non-ROI It is compressed using the second compression algorithm, wherein, the image impairment rate of first compression algorithm is calculated less than the described second compression The image impairment rate of method.
- 8. according to any described systems of claim 5-7, it is characterised in that the ROI determining modules are specifically used for described In vedio data for image carry out intermediate region, human face region and/or subtitle region identification, using the region recognized as The ROI, remaining area is as non-ROI.
- 9. system according to claim 6, it is characterised in that the ROI calculation servers and the encoding service implements It is independently arranged in reason, data interaction is carried out by wired or wireless way.
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 CN104105006A (en) | 2014-10-15 |
CN104105006B true 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) |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20170042431A (en) * | 2015-10-08 | 2017-04-19 | 삼성전자주식회사 | Electronic device configured to non-uniformly encode/decode image data according to display shape |
US9864925B2 (en) | 2016-02-15 | 2018-01-09 | 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 |
CN108076113B (en) * | 2016-11-15 | 2021-04-16 | 同方威视技术股份有限公司 | Method, server and system for operating security check 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 |
CN107318023B (en) * | 2017-06-21 | 2020-12-22 | 西安万像电子科技有限公司 | Image frame compression method and device |
CN110636294B (en) * | 2019-09-27 | 2024-04-09 | 腾讯科技(深圳)有限公司 | Video decoding method and device, and video encoding method and device |
CN112995488B (en) * | 2019-12-12 | 2023-04-18 | 深圳富泰宏精密工业有限公司 | High-resolution video image processing method and device and electronic equipment |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100739785B1 (en) * | 2006-01-09 | 2007-07-13 | 삼성전자주식회사 | Method and apparatus for encoding, decoding image based on region of interest |
US9036693B2 (en) * | 2009-01-08 | 2015-05-19 | Sri International | Method and system for providing region-of-interest video compression |
CN103442225B (en) * | 2013-07-26 | 2016-05-25 | 清华大学 | Remote sensing images transmission system under the finite rate upgrading based on database on-line study |
-
2014
- 2014-07-23 CN CN201410352578.3A patent/CN104105006B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN104105006A (en) | 2014-10-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104105006B (en) | A kind of method of video image processing and system | |
US10706631B2 (en) | Image generation based on brain activity monitoring | |
CN115278195B (en) | Zero position time delay | |
EP3316589B1 (en) | Video synchronization device and video synchronization method | |
CN104641632B (en) | metadata for depth filtering | |
US20180144212A1 (en) | Method and device for generating an image representative of a cluster of images | |
CN102510508B (en) | Detection-type stereo picture adjusting device and method | |
CN105408838A (en) | Dynamic GPU feature adjustment based on user-observed screen area | |
CN104756491A (en) | Depth map generation from a monoscopic image based on combined depth cues | |
KR20150065847A (en) | System and method for processing visual information for event detection | |
WO2017066346A1 (en) | Method and apparatus for optimizing video streaming for virtual reality | |
CN108040245A (en) | Methods of exhibiting, system and the device of 3-D view | |
CN103544441A (en) | Moving image generation device | |
EP3349453A1 (en) | Video encoding | |
CN110166796A (en) | Processing method, device, computer-readable medium and the electronic equipment of video frame | |
CN110225342B (en) | Video coding bit distribution system and method based on semantic distortion measurement | |
CN103929640A (en) | Techniques For Managing Video Streaming | |
CN102541314B (en) | Information processing equipment and method | |
CN107293162A (en) | Move teaching auxiliary and device, terminal device | |
CN108875589B (en) | Video detection method for road area | |
CN113315927B (en) | Video processing method and device, electronic equipment and storage medium | |
US11348338B2 (en) | Methods and systems for crowd motion summarization via tracklet based human localization | |
US20180322689A1 (en) | Visualization and rendering of images to enhance depth perception | |
CN117455753A (en) | Special effect template generation method, special effect generation device and storage medium | |
CN116091292B (en) | Data processing method and related device |
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 |