CN106791856A - A kind of method for video coding based on self adaptation area-of-interest - Google Patents
A kind of method for video coding based on self adaptation area-of-interest Download PDFInfo
- Publication number
- CN106791856A CN106791856A CN201611230835.1A CN201611230835A CN106791856A CN 106791856 A CN106791856 A CN 106791856A CN 201611230835 A CN201611230835 A CN 201611230835A CN 106791856 A CN106791856 A CN 106791856A
- Authority
- CN
- China
- Prior art keywords
- roi
- macro block
- image
- video coding
- self adaptation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
- H04N19/167—Position within a video image, e.g. region of interest [ROI]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/169—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
- H04N19/17—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object
- H04N19/176—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock
Abstract
The invention provides a kind of method for video coding based on self adaptation area-of-interest, comprise the following steps：Input picture is pre-processed and is extracted；Background modeling is carried out, ROI section is extracted；Compartmentalization treatment and region extension are carried out to ROI section；The image of extraction is reduced, the macro block of mark correspondence ROI；Set by ROI Qpdelta modules, H.265 completion encodes.Beneficial effect of the present invention：Encoded by extracting human eye region interested, the macro block of adaptive H .265 separates, and ROI region is accurate into macro block, forms irregular ROI region, effectively improves human eye observation's mass of video image, saves the network bandwidth and memory space.
Description
Technical field
The invention belongs to technical field of video monitoring, compiled more particularly, to a kind of video based on self adaptation area-of-interest
Code method.
Background technology
With the fast development of field of video monitoring, video resolution is constantly expanding, and 4K resolution ratio is gradually deep
Enter to monitoring trade, the expansion of resolution ratio will certainly bring great pressure, how improve the pressure of video code flow to the network bandwidth
Shrinkage is very urgent.
Human visual system (HVS) is not interested in all regions of image, thus can extract sense in image
The region of interest, optimizes coding, while the encoder bit rate of regions of non-interest is reduced, to reach reduction code check, lifting figure
As the purpose of quality.
Traditional area-of-interest (ROI) positioning strategy, burn into sharpening is typically carried out to original image, is filtered, is gone
Make an uproar, the pretreatment operation of a series of complex such as slant correction, but these strategies are highly prone to the dry of light luminance, irradiating angle etc.
Disturb, it is impossible to which good positioning is carried out to area-of-interest.
The content of the invention
In view of this, the present invention is directed to propose a kind of method for video coding based on self adaptation area-of-interest, to solve
The weak point of above mentioned problem, extracts human eye region interested and is encoded, effectively human eye observation's matter of lifting video image
Amount, saves the network bandwidth and memory space.
To reach above-mentioned purpose, the technical proposal of the invention is realized in this way：
A kind of method for video coding based on self adaptation area-of-interest, comprises the following steps：
I. input picture is pre-processed and is extracted；
II. background modeling is carried out, ROI section is extracted；
III. compartmentalization treatment and region extension are carried out to ROI section；
IV. the image of extraction is reduced, the macro block of mark correspondence ROI；
V. set by ROI Qpdelta modules, H.265 completion encodes.
Further, in the step I preprocessing process original image is filtered, gamma correction, by image resolution
The image that rate narrows down to after D1 sizes, and extraction is converted to gray level image.
Further, being detected by spatial domain skin texture detection and time domain residual in the step II carries out ROI extractions, spatial domain inspection
The Texture complication of each macro block is surveyed, complexity is asked for by the standard deviation of computing macro block, calculated value is more than probability statistics
Empirical value, labeled as ROI macro blocks；Tim e- domain detection is realized by asking for the residual sum operation vector of macro block, residual sum is transported
Dynamic vector constitutes Mathematical Modeling, and its value exceedes certain probable value and is labeled as ROI macro blocks.
Further, the macro block mark figure of the ROI is realized by the two-dimensional table of Boolean variable.
Further, marginal information is extracted by Canny rim detections in the step III, figure phase is marked with macro block
With it is rear, carry out expansion process.
Further, the step IV compares ROI macro blocks mark two-dimensional table according to real image resolution ratio
Example is amplified, and size is separated according to actual macro H.265, marks whether each macro block is area-of-interest.
Further, it is as follows to the setting steps of ROI Qpdelta modules in the step V：
A.ROI Qpdelta modules obtain the ROI credit ratings of setting and detect actual bit rate, and institute is controlled with actual bit rate
The macro block QP values for obtaining subtract the QP side-play amounts Qpdelta corresponding to grade；
B. the size of actual ROI is calculated according to ROI macro blocks mark figure, and divided by overall video image resolution ratio, is obtained
To ROI area grades, if ROI area grades are low, increase the QP values of corresponding grade, if ROI area grades are high, reduce correspondence
QP values；
C. the actual bit rate of N frames before image is obtained, according to code check grade, macro block QP values is adjusted, grade is low, increases macro block
QP values, grade is high then to reduce macro block QP values.
Relative to prior art, the method for video coding based on self adaptation area-of-interest of the present invention has following
Advantage：
Method for video coding based on the self adaptation area-of-interest of the present invention area interested by extracting human eye
Domain is encoded, and the macro block of adaptive H .265 separates, and ROI region is accurate into macro block, forms irregular ROI region, effectively
The human eye observation's mass for improving video image, save the network bandwidth and memory space.
Brief description of the drawings
The accompanying drawing for constituting a part of the invention is used for providing a further understanding of the present invention, schematic reality of the invention
Apply example and its illustrate, for explaining the present invention, not constitute inappropriate limitation of the present invention.In the accompanying drawings：
Fig. 1 is the control flow schematic diagram of the embodiment of the present invention；
Fig. 2 is the program flow diagram of the ROI Qpdelta setup modules described in the embodiment of the present invention.
Specific embodiment
It should be noted that in the case where not conflicting, the embodiment in the present invention and the feature in embodiment can phases
Mutually combination.
Describe the present invention in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
A kind of method for video coding based on self adaptation area-of-interest, as shown in figure 1, comprising the following steps：
I. input picture is pre-processed and is extracted；
II. background modeling is carried out, ROI section is extracted；
III. compartmentalization treatment and region extension are carried out to ROI section；
IV. the image of extraction is reduced, the macro block of mark correspondence ROI；
V. set by ROI Qpdelta modules, H.265 completion encodes.
The original image of detector collection is obtained in the step I, this original image passes through the basic pre- place of image
Reason, such as basic filtering, gamma correction operation, narrows down to D1 sizes, to reduce at successive image by image resolution ratio
The cost time of reason, after extracting image, gray level image is converted into, improves treatment effeciency.
The small figure for getting carried out in the step II detect that carrying out ROI carries by spatial domain skin texture detection and time domain residual
Take, the Texture complication of spatial filter each macro block, complexity is asked for by the standard deviation of computing macro block, and calculated value is more than
The empirical value of probability statistics, labeled as ROI macro blocks；Tim e- domain detection is realized by asking for the residual sum operation vector of macro block, incited somebody to action
Residual sum motion vector constitutes Mathematical Modeling, and its value exceedes certain probable value and is labeled as ROI macro blocks；Marked by macro block, it is determined that
The area-of-interest and background image of image.
The macro block mark figure of the ROI is realized by the two-dimensional table of Boolean variable.
ROI macro blocks mark figure typically will not compartmentalization, it may appear that interrupted discrete point, and area-of-interest is usually
The irregular overall region in edge, so needing to carry out intra-macroblock ROI marks, realizes the computing as expanded after Image erosion
Effect, carries out empty filling, and the ROI region mark based on macro block occurs that edge is omitted, therefore passes through in the step III
Canny rim detections extract marginal information, with macro block mark figure with it is rear, carry out expansion process, realize edge expansion, finally
Reaching the complete of area-of-interest scope includes.
In step I extract image be to original image reduce image, finally need by ROI mark image restoring be
Original image, therefore the step IV carries out ratio according to real image resolution ratio to described ROI macro blocks mark two-dimensional table
Amplify, size is separated according to actual macro H.265, mark whether each macro block is area-of-interest.
The QP side-play amounts (Qpdelta values) of ROI section are determined by following factor：The ROI credit ratings of setting；ROI
Region area accounts for the accounting of general image；The actual bit rate of N frames before image.The ROI image quality is divided into 6 grades, according to
The difference of grade, the value of side-play amount Qpdelta is different, and side-play amount Qpdelta values are bigger, and ROI region picture quality is better；
The ROI region size, directly affects overall picture quality, when area is excessive, because low QP values macro block accounting is excessive, is
Basic bit rate stabilization is kept, background area poor effect can be caused, make actual visual effect not good enough, therefore by detecting ROI areas
Domain accounting size adjusts the Qpdelta values of ROI region；Code check detection module is used for the reality of the preceding N frames for calculating present image
Gap between code check and setting code check, obtains the reserved code check of present frame, further according to code check grade, calculates the QP values of ROI region.
Therefore as shown in Fig. 2 as follows to the setting steps of ROI Qpdelta modules in the step V：ROI Qpdelta
Module obtains the ROI credit ratings of setting and detects actual bit rate, and grade is subtracted with the macro block QP ' values obtained by actual bit rate control
Corresponding QP side-play amounts Qpdelta；The size of actual ROI is calculated according to ROI macro blocks mark figure, and divided by overall video
Image resolution ratio, obtains ROI area grades, if ROI area grades are low, increases the QP values of corresponding grade, if ROI area grades
Height, then reduce corresponding QP values；The actual bit rate of N frames before acquisition image, according to code check grade, adjusts macro block QP values, and grade is low
Then increase macro block QP values, grade is high then to reduce macro block QP values.
Presently preferred embodiments of the present invention is the foregoing is only, is not intended to limit the invention, it is all in essence of the invention
Within god and principle, any modification, equivalent substitution and improvements made etc. should be included within the scope of the present invention.
Claims (7)
1. a kind of method for video coding based on self adaptation area-of-interest, it is characterised in that comprise the following steps：
I. input picture is pre-processed and is extracted；
II. background modeling is carried out, ROI section is extracted；
III. compartmentalization treatment and region extension are carried out to ROI section；
IV. the image of extraction is reduced, the macro block of mark correspondence ROI；
V. set by ROI Qpdelta modules, H.265 completion encodes.
2. a kind of method for video coding based on self adaptation area-of-interest according to claim 1, it is characterised in that：Institute
State preprocessing process in step I original image is filtered, gamma correction, image resolution ratio is narrowed down into D1 sizes, and carry
Image after taking is converted to gray level image.
3. a kind of method for video coding based on self adaptation area-of-interest according to claim 1, it is characterised in that：Institute
State and detected by spatial domain skin texture detection and time domain residual in step II and carry out ROI extractions, the texture of spatial filter each macro block
Complexity, complexity is asked for by the standard deviation of computing macro block, and calculated value is more than the empirical value of probability statistics, labeled as ROI
Macro block；Tim e- domain detection is realized by asking for the residual sum operation vector of macro block, by residual sum motion vector composition Mathematical Modeling,
Its value exceedes certain probable value and is labeled as ROI macro blocks.
4. a kind of method for video coding based on self adaptation area-of-interest according to claim 3, it is characterised in that：Institute
The macro block mark figure for stating ROI is realized by the two-dimensional table of Boolean variable.
5. a kind of method for video coding based on self adaptation area-of-interest according to claim 1, it is characterised in that：Institute
State and marginal information is extracted by Canny rim detections in step III, with macro block mark figure with it is rear, carry out expansion process.
6. a kind of method for video coding based on self adaptation area-of-interest according to claim 1, it is characterised in that：Institute
Step IV is stated according to real image resolution ratio, ROI macro blocks mark two-dimensional table carried out it is scaling, according to H.265
Actual macro separates size, marks whether each macro block is area-of-interest.
7. a kind of method for video coding based on self adaptation area-of-interest according to claim 1, it is characterised in that institute
State as follows to the setting steps of ROI Qpdelta modules in step V：
A.ROI Qpdelta modules obtain the ROI credit ratings of setting and detect actual bit rate, with obtained by actual bit rate control
Macro block QP values subtract the QP side-play amounts Qpdelta corresponding to grade；
B. the size of actual ROI is calculated according to ROI macro blocks mark figure, and divided by overall video image resolution ratio, obtains ROI
Area grades, if ROI area grades are low, increase the QP values of corresponding grade, if ROI area grades are high, reduce corresponding QP
Value；
C. the actual bit rate of N frames before image is obtained, according to code check grade, macro block QP values is adjusted, the low then increase macro block QP values of grade,
Grade is high then to reduce macro block QP values.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611230835.1A CN106791856A (en) | 2016-12-28 | 2016-12-28 | A kind of method for video coding based on self adaptation area-of-interest |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611230835.1A CN106791856A (en) | 2016-12-28 | 2016-12-28 | A kind of method for video coding based on self adaptation area-of-interest |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106791856A true CN106791856A (en) | 2017-05-31 |
Family
ID=58922333
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611230835.1A Pending CN106791856A (en) | 2016-12-28 | 2016-12-28 | A kind of method for video coding based on self adaptation area-of-interest |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106791856A (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109698957A (en) * | 2017-10-24 | 2019-04-30 | 腾讯科技（深圳）有限公司 | Image encoding method, calculates equipment and storage medium at device |
| CN110267037A (en) * | 2019-06-21 | 2019-09-20 | 腾讯科技（深圳）有限公司 | Method for video coding, device, electronic equipment and computer readable storage medium |
| CN110365985A (en) * | 2019-06-03 | 2019-10-22 | 西安万像电子科技有限公司 | Image processing method and device |
| CN110505481A (en) * | 2019-07-15 | 2019-11-26 | 杭州亿圣信息技术有限公司 | A method of it is monitored using eye movement and improves the low damage code efficiency of video POI |
| CN110545430A (en) * | 2018-05-28 | 2019-12-06 | 北京松果电子有限公司 | video transmission method and device |
| CN110769252A (en) * | 2019-11-01 | 2020-02-07 | 西安交通大学 | Method for improving coding quality by AI face detection |
| CN110856019A (en) * | 2019-11-20 | 2020-02-28 | 广州酷狗计算机科技有限公司 | Code rate allocation method, device, terminal and storage medium |
| CN111131825A (en) * | 2019-10-28 | 2020-05-08 | 华为技术有限公司 | Video processing method and related device |
| CN111918066A (en) * | 2020-09-08 | 2020-11-10 | 北京字节跳动网络技术有限公司 | Video encoding method, device, equipment and storage medium |
| WO2021073443A1 (en) * | 2019-10-14 | 2021-04-22 | 腾讯科技（深圳）有限公司 | Method and apparatus for detecting region of interest, electronic device, and readable storage medium |
| CN113573140A (en) * | 2021-07-09 | 2021-10-29 | 西安交通大学 | Code rate self-adaptive decision-making method supporting face detection and real-time super-resolution |
| US11166035B1 (en) | 2020-04-30 | 2021-11-02 | Wangsu Science and Technology Co., Ltd. | Method and device for transcoding video |
| WO2021217829A1 (en) * | 2020-04-30 | 2021-11-04 | 网宿科技股份有限公司 | Video transcoding method and device |
| CN114830626A (en) * | 2019-12-19 | 2022-07-29 | 富士胶片株式会社 | Imaging device, method for operating imaging device, program, and imaging system |
| WO2022213809A1 (en) * | 2021-04-07 | 2022-10-13 | 百果园技术(新加坡)有限公司 | Video coding method, apparatus and device, and storage medium |
| CN116600118A (en) * | 2023-07-18 | 2023-08-15 | 华洋通信科技股份有限公司 | Video acquisition parameter optimization method based on mixed characteristic multi-mode analysis |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040252903A1 (en) * | 2003-06-13 | 2004-12-16 | Chen Oscal T. -C. | Method of automatically determining the region of interest from an image |
| CN101309422A (en) * | 2008-06-23 | 2008-11-19 | 北京工业大学 | Macroblock level quantized parameter process method and apparatus |
| CN101534444A (en) * | 2009-04-20 | 2009-09-16 | 杭州华三通信技术有限公司 | Image processing method, system and device |
| CN101945275A (en) * | 2010-08-18 | 2011-01-12 | 镇江唐桥微电子有限公司 | Video coding method based on region of interest (ROI) |
| CN103002289A (en) * | 2013-01-08 | 2013-03-27 | 中国电子科技集团公司第三十八研究所 | Video constant quality coding device for monitoring application and coding method thereof |
| CN104065964A (en) * | 2014-06-19 | 2014-09-24 | 上海交通大学 | Coding-decoding method of region-of-interest information and video coding-decoding device |
| CN104427337A (en) * | 2013-08-21 | 2015-03-18 | 杭州海康威视数字技术股份有限公司 | Region of interest (ROI) video coding method and apparatus based on object detection |
-
2016
- 2016-12-28 CN CN201611230835.1A patent/CN106791856A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040252903A1 (en) * | 2003-06-13 | 2004-12-16 | Chen Oscal T. -C. | Method of automatically determining the region of interest from an image |
| CN101309422A (en) * | 2008-06-23 | 2008-11-19 | 北京工业大学 | Macroblock level quantized parameter process method and apparatus |
| CN101534444A (en) * | 2009-04-20 | 2009-09-16 | 杭州华三通信技术有限公司 | Image processing method, system and device |
| CN101945275A (en) * | 2010-08-18 | 2011-01-12 | 镇江唐桥微电子有限公司 | Video coding method based on region of interest (ROI) |
| CN103002289A (en) * | 2013-01-08 | 2013-03-27 | 中国电子科技集团公司第三十八研究所 | Video constant quality coding device for monitoring application and coding method thereof |
| CN104427337A (en) * | 2013-08-21 | 2015-03-18 | 杭州海康威视数字技术股份有限公司 | Region of interest (ROI) video coding method and apparatus based on object detection |
| CN104065964A (en) * | 2014-06-19 | 2014-09-24 | 上海交通大学 | Coding-decoding method of region-of-interest information and video coding-decoding device |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109698957A (en) * | 2017-10-24 | 2019-04-30 | 腾讯科技（深圳）有限公司 | Image encoding method, calculates equipment and storage medium at device |
| CN109698957B (en) * | 2017-10-24 | 2022-03-29 | 腾讯科技（深圳）有限公司 | Image coding method and device, computing equipment and storage medium |
| CN110545430A (en) * | 2018-05-28 | 2019-12-06 | 北京松果电子有限公司 | video transmission method and device |
| CN110365985A (en) * | 2019-06-03 | 2019-10-22 | 西安万像电子科技有限公司 | Image processing method and device |
| CN110267037A (en) * | 2019-06-21 | 2019-09-20 | 腾讯科技（深圳）有限公司 | Method for video coding, device, electronic equipment and computer readable storage medium |
| CN110505481A (en) * | 2019-07-15 | 2019-11-26 | 杭州亿圣信息技术有限公司 | A method of it is monitored using eye movement and improves the low damage code efficiency of video POI |
| CN110505481B (en) * | 2019-07-15 | 2021-06-01 | 杭州亿圣信息技术有限公司 | Method for improving low-loss coding efficiency of video POI (point of interest) by eye movement monitoring |
| WO2021073443A1 (en) * | 2019-10-14 | 2021-04-22 | 腾讯科技（深圳）有限公司 | Method and apparatus for detecting region of interest, electronic device, and readable storage medium |
| CN111131825A (en) * | 2019-10-28 | 2020-05-08 | 华为技术有限公司 | Video processing method and related device |
| CN110769252A (en) * | 2019-11-01 | 2020-02-07 | 西安交通大学 | Method for improving coding quality by AI face detection |
| CN110856019B (en) * | 2019-11-20 | 2021-11-12 | 广州酷狗计算机科技有限公司 | Code rate allocation method, device, terminal and storage medium |
| CN110856019A (en) * | 2019-11-20 | 2020-02-28 | 广州酷狗计算机科技有限公司 | Code rate allocation method, device, terminal and storage medium |
| CN114830626A (en) * | 2019-12-19 | 2022-07-29 | 富士胶片株式会社 | Imaging device, method for operating imaging device, program, and imaging system |
| US11166035B1 (en) | 2020-04-30 | 2021-11-02 | Wangsu Science and Technology Co., Ltd. | Method and device for transcoding video |
| WO2021217829A1 (en) * | 2020-04-30 | 2021-11-04 | 网宿科技股份有限公司 | Video transcoding method and device |
| CN111918066A (en) * | 2020-09-08 | 2020-11-10 | 北京字节跳动网络技术有限公司 | Video encoding method, device, equipment and storage medium |
| CN111918066B (en) * | 2020-09-08 | 2022-03-15 | 北京字节跳动网络技术有限公司 | Video encoding method, device, equipment and storage medium |
| WO2022213809A1 (en) * | 2021-04-07 | 2022-10-13 | 百果园技术(新加坡)有限公司 | Video coding method, apparatus and device, and storage medium |
| CN113573140A (en) * | 2021-07-09 | 2021-10-29 | 西安交通大学 | Code rate self-adaptive decision-making method supporting face detection and real-time super-resolution |
| CN113573140B (en) * | 2021-07-09 | 2022-05-03 | 西安交通大学 | Code rate self-adaptive decision-making method supporting face detection and real-time super-resolution |
| CN116600118A (en) * | 2023-07-18 | 2023-08-15 | 华洋通信科技股份有限公司 | Video acquisition parameter optimization method based on mixed characteristic multi-mode analysis |
| CN116600118B (en) * | 2023-07-18 | 2023-10-03 | 华洋通信科技股份有限公司 | Video acquisition parameter optimization method based on mixed characteristic multi-mode analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106791856A (en) | A kind of method for video coding based on self adaptation area-of-interest | |
| Wang et al. | An experiment-based review of low-light image enhancement methods | |
| CN106296612B (en) | A kind of stagewise monitor video sharpening system and method for image quality evaluation and weather conditions guidance | |
| CN103606132A (en) | Multiframe digital image denoising method based on space domain and time domain combination filtering | |
| CN101739549B (en) | Face detection method and system | |
| CN105516720B (en) | A kind of self-adaptation control method of monitor camera code stream | |
| CN105869174B (en) | A kind of Sky Scene image partition method | |
| CN105139391B (en) | A kind of haze weather traffic image edge detection method | |
| CN102169585A (en) | Method and device for detecting image color cast | |
| CN110276279B (en) | Method for detecting arbitrary-shape scene text based on image segmentation | |
| CN101976436A (en) | Pixel-level multi-focus image fusion method based on correction of differential image | |
| CN106446905A (en) | Surface crack texture extraction method based on fusion of seepage algorithm and adaptive Canny algorithm | |
| KR100887183B1 (en) | Preprocessing apparatus and method for illumination-invariant face recognition | |
| CN102903093A (en) | Poisson image fusion method based on chain code mask | |
| CN110533600A (en) | A kind of same/heterogeneous remote sensing image high-fidelity broad sense sky-spectrum fusion method | |
| CN105092597A (en) | Detection method for cracks on surface of hard-plastic material | |
| CN107273884A (en) | A kind of License Plate Identification method based on mobile terminal camera | |
| Bhuvaneswari et al. | Automatic Detection and Inpainting of Text Images | |
| US20170352170A1 (en) | Nearsighted camera object detection | |
| CN107909579A (en) | Product profile extraction method in vision-based detection | |
| CN114581433B (en) | Method and system for acquiring surface morphology detection image in metal ball cavity | |
| CN103065310A (en) | Hyperspectral image marginal information extraction method based on three-dimensional light spectrum angle statistic | |
| CN114212452B (en) | Coal flow detection method based on laser assistance and image processing and energy-saving control system | |
| WO2018098736A1 (en) | Remote sensing imaging-based cyanobacteria monitoring method and device | |
| CN103871084A (en) | Method for recognizing patterns of blueprint cloth |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170531 |
|
| RJ01 | Rejection of invention patent application after publication |