CN103475826A - Video matting and synthesis method - Google Patents
Video matting and synthesis method Download PDFInfo
- Publication number
- CN103475826A CN103475826A CN2013104484095A CN201310448409A CN103475826A CN 103475826 A CN103475826 A CN 103475826A CN 2013104484095 A CN2013104484095 A CN 2013104484095A CN 201310448409 A CN201310448409 A CN 201310448409A CN 103475826 A CN103475826 A CN 103475826A
- Authority
- CN
- China
- Prior art keywords
- video
- pixel
- value
- background
- synthetic method
- 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
Abstract
The invention relates to a video matting and synthesis method. According to the method, firstly, background videos are shot, a pure-color curtain background is built, and a first video comprising foreground images located in front of the pure-color curtain background is shot; then, matting processing is conducted on the first video to obtain the foreground images; synthesis of the foreground images and the background video is carried out; finally, edge detection and smoothing are conducted on the video formed after synthesis. According to the technical scheme, edge detection and smoothing technologies are adopted to conduct smoothing on edge sawteeth, caused by image matting, of synthesis vide images, and the video matting and synthesis method can be applied to real-time and post video processing. Furthermore, the video matting and synthesis method can be adopted for carrying out parallel processing on each pixel of frame images captured through a camera in a GPU quickly.
Description
Technical field
The invention belongs to technical field of video processing, particularly a kind of video keying synthetic method.
Background technology
In technical field of video processing, usually can apply to the video keying technology.So-called video keying technology, refer to the personage in a video or other prospects, scratch as technology and crawl out by intelligence, and embedding is synthesized in another virtual or scene background that other are actual.Main effect is to make to watch the user of video to feel that personage in video is in synthetic scene of later stage, and can further make personage and scene background that interaction is arranged.For example, in guide's training project, by lecturer's real-time image scratching embedding are synthesized in the video image background of tourist attractions, so just allow the student feel that the lecturer is the explanation training of carrying out tourist attractions in tourist attractions on the spot in person.
It is that the personage that video camera is taken carries out real-time image scratching that the video keying technology mainly needs the problem solved in practice, and synthesized with the video background provided, finally by rim detection and smoothing technique, to scratching picture, with the synthetic character contour edge sawtooth caused, carry out smoothing processing.In prior art, each pixel of the two field picture that camera is captured is at the CPU(central processing unit) process of carrying out computing is for each image by Pixel calcualting, and speed is slower.
Summary of the invention
Technical problem to be solved by this invention is to provide a kind of video processing technique, particularly a kind of video keying synthetic method.
The objective of the invention is to be achieved through the following technical solutions:
A kind of video keying synthetic method said method comprising the steps of:
Step a. shooting background video;
Step b. sets up pure color curtain background, takes and comprises the first video in the foreground image in described pure color curtain background the place ahead;
Step c is scratched figure to described the first video and is processed, and obtains described foreground image;
Steps d. synthetic described foreground image and described background video;
Step e. carries out rim detection to described synthetic video;
Step f. carries out smoothing processing to the edge of described synthetic video.
In technical scheme of the present invention, described pure color curtain is three primary colors look curtain.
In technical scheme of the present invention, described pure color curtain is blue curtain.
In technical scheme of the present invention, described step b further comprises:
Step b1. calculates the frequency that each value of redgreenblue of the first two field picture of described the first video occurs, obtains the RGB value of frequency of occurrences maximum;
Step b2. processes frame by frame to described the first video, draws the transparence value of each each pixel of two field picture.
In technical scheme of the present invention, described step b2 specifically comprises: the RGB value of establishing described frequency maximum is R
h, G
h, B
h, the RGB of pixel to be asked is respectively r, g, b, establishes vector (R
h, G
h, B
h) with (r, g, b) angle be θ, have:
cosθ = (R
h*r+G
h*g+B
h*b)/(
)
If the value of cos θ is less than preset value, judge that described pixel is as foreground pixel, transparence value is 1;
If the value of cos θ is not less than preset value, have:
Transparence value=(255-(blue channel value-(red color channel value+green channel value)/2))/255
Transparent transparence value is 0 fully.
In technical scheme of the present invention, the composite formula of described steps d is:
Composograph=foreground image * transparence value+background video * (1-transparence value).
In technical scheme of the present invention, described step e specifically comprises: if the pixel that the existing transparence value of the neighboring pixel of pixel is 1, it is not 1 pixel that transparence value is arranged again, judges that described pixel is as edge pixel.
In technical scheme of the present invention, described step f specifically comprises: will be centered by described edge pixel point, and the color-values of the pixel in the square scope of K*K size is added up, and to make arithmetic average, the new color-values as described edge pixel.
Technical scheme of the present invention utilizes rim detection and smoothing technique to carry out smoothing processing to the edge sawtooth of scratching as the video composograph caused, and can be applied to video and process in real time and post-processed.In addition, each pixel of the two field picture that the present invention can capture camera is in the GPU(graphic process unit) carry out parallel processing, processing speed is very fast.
The accompanying drawing explanation
The flow chart that Fig. 1 is video keying synthetic method of the present invention.
Embodiment
In order to make purpose of the present invention, technical scheme and advantage clearer, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
Refer to Fig. 1, video keying synthetic method of the present invention mainly comprises the following steps:
Step S101: shooting background video;
Step S102: set up pure color curtain background, take and comprise the first video in the foreground image in this pure color curtain background the place ahead.
As a rule, above-mentioned pure color curtain background adopts RGB three primary colors look curtain, in order to realize in scratching nomography.Wherein, blue or green curtain is because differ larger with people's the colour of skin, and is widely used.In better embodiment of the present invention, this pure color curtain background is blue curtain background.After setting up blue curtain background, as required, with camera, take portrait or other prospects in this indigo plant curtain background the place ahead.
Step S103: above-mentioned the first video is scratched to figure and process, obtain foreground image.
The detailed process of scratching the figure processing is: at first, the first two field picture of the first video is carried out to the histogram calculation of RGB, calculate the frequency that trichromatic each value of RGB (RGB) (0-255) occurs, the RGB value that obtains frequency of occurrences maximum (is made as R
h, G
h, B
h).The ratio shared due to blue curtain in video is very large, and in fact above-mentioned information meaned the information of blue curtain.
Then, the first video is processed frame by frame, drawn the transparence value (establishing this value for alpha) of each each pixel of two field picture.Each pixel for every two field picture has three passages of RGB (RGB), if the first video is taken by blue curtain background, when scratching figure, the RGB that establishes pixel to be asked is respectively r, g, b, by (R
h, G
h, B
h) and (r, g, b) regard two vectors as, establishing its angle is θ, has:
cosθ = (R
h*r+G
h*g+B
h*b)/(
)
If the value of cos θ is less than certain threshold values, illustrate that this pixel and background differ larger, judge that this pixel is as foreground pixel, transparency is for fully opaque, and alpha is 1.
If the value of cos θ is not less than certain threshold values, the transparency of this pixel depends on the mean value of red green passage and the gap between blue channel, and this pixel of the larger explanation of gap is closer to Lan Muse, and the transparency of this pixel is higher.Have:
Alpha=(255-(blue channel value-(red color channel value+green channel value)/2))/255
Transparent alpha is 0 fully.
Step S104: above-mentioned foreground image and above-mentioned background video are synthesized.
The synthetic formula of foreground image and background video is:
Composograph=foreground image * alpha+ background video * (1-alpha)
Step S105: synthetic video is carried out to rim detection;
Because scratch the edge of the foreground image after figure, sawtooth is arranged, sawtooth is carried out to smooth operation and edge pixel need to first be detected), carry out following the detection for each pixel and judge whether it is edge pixel.
The algorithm of Edge detected is: if the pixel of the existing alpha=1 of the neighboring pixel of pixel (the square scope of K*K size) has again the pixel of alpha ≠ 1, judge that this pixel is edge pixel.
Step S106: the edge to synthetic video carries out smoothing processing.
Get centered by edge pixel point, the pixel in the square scope of K*K size carries out level and smooth computing.For example, the K value is got 9 o'clock, is about to around this edge pixel point interior 81 pixel color values of 9*9 square scope and adds up that to make arithmetic average, the new color-values as this edge pixel.
Technical scheme of the present invention utilizes rim detection and smoothing technique to carry out smoothing processing to the edge sawtooth of scratching as the video composograph caused, and can be applied to video and process in real time and post-processed.In addition, each pixel of the two field picture that the present invention can capture camera is in the GPU(graphic process unit) carry out parallel processing, processing speed is very fast.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, all any modifications of doing within the spirit and principles in the present invention, be equal to and replace and improvement etc., within all should being included in protection scope of the present invention.
Claims (8)
1. a video keying synthetic method, is characterized in that, said method comprising the steps of:
Step a. shooting background video;
Step b. sets up pure color curtain background, takes and comprises the first video in the foreground image in described pure color curtain background the place ahead;
Step c is scratched figure to described the first video and is processed, and obtains described foreground image;
Steps d. synthetic described foreground image and described background video;
Step e. carries out rim detection to described synthetic video;
Step f. carries out smoothing processing to the edge of described synthetic video.
2. video keying synthetic method as claimed in claim 1, is characterized in that, described pure color curtain is three primary colors look curtain.
3. video keying synthetic method as claimed in claim 2, is characterized in that, described pure color curtain is blue curtain.
4. video keying synthetic method as claimed in claim 1, is characterized in that, described step b further comprises:
Step b1. calculates the frequency that each value of redgreenblue of the first two field picture of described the first video occurs, obtains the RGB value of frequency of occurrences maximum;
Step b2. processes frame by frame to described the first video, draws the transparence value of each each pixel of two field picture.
5. video keying synthetic method as claimed in claim 1, is characterized in that, described step b2 specifically comprises: the RGB value of establishing described frequency maximum is R
h, G
h, B
h, the RGB of pixel to be asked is respectively r, g, b, establishes vector (R
h, G
h, B
h) with (r, g, b) angle be θ, have:
cosθ = (R
h*r+G
h*g+B
h*b)/(
)
If the value of cos θ is less than preset value, judge that described pixel is as foreground pixel, transparence value is 1;
If the value of cos θ is not less than preset value, have:
Transparence value=(255-(blue channel value-(red color channel value+green channel value)/2))/255
Transparent transparence value is 0 fully.
6. video keying synthetic method as claimed in claim 1, is characterized in that, the composite formula of described steps d is:
Composograph=foreground image * transparence value+background video * (1-transparence value).
7. video keying synthetic method as claimed in claim 1, is characterized in that, described step e specifically comprises: if the pixel that the existing transparence value of the neighboring pixel of pixel is 1, it is not 1 pixel that transparence value is arranged again, judges that described pixel is as edge pixel.
8. video keying synthetic method as claimed in claim 7, it is characterized in that, described step f specifically comprises: will be centered by described edge pixel point, and the color-values of the pixel in the square scope of K*K size is added up, and to make arithmetic average, the new color-values as described edge pixel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013104484095A CN103475826A (en) | 2013-09-27 | 2013-09-27 | Video matting and synthesis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013104484095A CN103475826A (en) | 2013-09-27 | 2013-09-27 | Video matting and synthesis method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103475826A true CN103475826A (en) | 2013-12-25 |
Family
ID=49800508
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2013104484095A Pending CN103475826A (en) | 2013-09-27 | 2013-09-27 | Video matting and synthesis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103475826A (en) |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104050700A (en) * | 2014-06-13 | 2014-09-17 | 北京奥普科星技术有限公司 | Image synthetic method and device |
| CN104539853A (en) * | 2015-01-05 | 2015-04-22 | 锦池媒体科技（北京）有限公司 | Image synthesis method |
| CN104780296A (en) * | 2015-04-02 | 2015-07-15 | 上海东方传媒技术有限公司 | Video synthesis system and method for virtual remote interview |
| CN104902189A (en) * | 2015-06-24 | 2015-09-09 | 小米科技有限责任公司 | Picture processing method and picture processing device |
| CN104954670A (en) * | 2015-04-30 | 2015-09-30 | 努比亚技术有限公司 | Photographing method and device |
| CN105096355A (en) * | 2014-05-08 | 2015-11-25 | 腾讯科技（深圳）有限公司 | Image processing method and system |
| CN105100646A (en) * | 2015-08-31 | 2015-11-25 | 北京奇艺世纪科技有限公司 | Video processing method and device |
| CN105407254A (en) * | 2015-11-19 | 2016-03-16 | 广州玖的数码科技有限公司 | Real-time video and image synthesis method, real-time video and image synthesis device and global shooting equipment |
| CN105516562A (en) * | 2015-12-13 | 2016-04-20 | 重庆绿氧环保科技有限公司 | Product shooting device and quick image matting method |
| CN105654471A (en) * | 2015-12-24 | 2016-06-08 | 武汉鸿瑞达信息技术有限公司 | Augmented reality AR system applied to internet video live broadcast and method thereof |
| CN105678724A (en) * | 2015-12-29 | 2016-06-15 | 北京奇艺世纪科技有限公司 | Background replacing method and apparatus for images |
| WO2017113873A1 (en) * | 2015-12-28 | 2017-07-06 | 努比亚技术有限公司 | Image synthesizing method, device and computer storage medium |
| US9781400B2 (en) | 2015-03-09 | 2017-10-03 | Huawei Technologies Co., Ltd. | Image processing method and apparatus |
| CN107707843A (en) * | 2016-08-09 | 2018-02-16 | 深圳泰和创邦文化传媒有限公司 | A kind of Video Composition and the method for imprinting |
| CN107730433A (en) * | 2017-09-28 | 2018-02-23 | 努比亚技术有限公司 | One kind shooting processing method, terminal and computer-readable recording medium |
| CN108109100A (en) * | 2017-12-19 | 2018-06-01 | 维沃移动通信有限公司 | A kind of image processing method, mobile terminal |
| CN108256497A (en) * | 2018-02-01 | 2018-07-06 | 北京中税网控股股份有限公司 | A kind of method of video image processing and device |
| CN108282612A (en) * | 2018-01-12 | 2018-07-13 | 广州市百果园信息技术有限公司 | Method for processing video frequency and computer storage media, terminal |
| CN108566521A (en) * | 2018-06-26 | 2018-09-21 | 蒋大武 | A kind of image synthesizing system for scratching picture based on natural image |
| CN109936710A (en) * | 2019-03-13 | 2019-06-25 | 深圳市瑞云科技有限公司 | A kind of production method of the short-sighted frequency of embedded background based on the rendering of CG cloud |
| CN111105358A (en) * | 2018-10-26 | 2020-05-05 | 阿里巴巴集团控股有限公司 | Image processing method and device |
| CN111402181A (en) * | 2020-03-13 | 2020-07-10 | 北京奇艺世纪科技有限公司 | Image fusion method and device and computer readable storage medium |
| CN111586296A (en) * | 2020-04-27 | 2020-08-25 | 北京小米移动软件有限公司 | Image capturing method, image capturing apparatus, and storage medium |
| CN111818276A (en) * | 2020-06-30 | 2020-10-23 | 西安宏源视讯设备有限责任公司 | Method, device and storage medium for realizing interaction of different-place same-scene programs |
| CN114173059A (en) * | 2021-12-09 | 2022-03-11 | 广州阿凡提电子科技有限公司 | Video editing system, method and device |
| CN115393238A (en) * | 2022-08-23 | 2022-11-25 | 广州呗呗科技有限公司 | Image synthesis system and method based on virtual reality technology |
| CN115941920A (en) * | 2022-11-23 | 2023-04-07 | 马凯翔 | Naked eye 3D video generation method, device, equipment and storage medium |
| CN116546180A (en) * | 2022-11-21 | 2023-08-04 | 马凯翔 | Naked eye suspension 3D video generation method, device, equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1547131A (en) * | 2003-12-03 | 2004-11-17 | 谭日辉 | Virtual reality interactive control system |
| CN101098475A (en) * | 2007-07-10 | 2008-01-02 | 浙江大学 | Interactive time-space accordant video matting method in digital video processing |
| CN101500091A (en) * | 2008-10-16 | 2009-08-05 | 黄福宝 | Character synthesizing method with two paths of video effects |
| CN101588459A (en) * | 2009-06-26 | 2009-11-25 | 北京交通大学 | A kind of video keying processing method |
| CN101783889A (en) * | 2010-02-05 | 2010-07-21 | 北京水晶石数字科技有限公司 | Real-time matting and video monitoring and collecting method |
| CN102305769A (en) * | 2011-06-09 | 2012-01-04 | 天津大学 | Multispectral sectional drawing method applied to Chinese ancient painting repair |
-
2013
- 2013-09-27 CN CN2013104484095A patent/CN103475826A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1547131A (en) * | 2003-12-03 | 2004-11-17 | 谭日辉 | Virtual reality interactive control system |
| CN101098475A (en) * | 2007-07-10 | 2008-01-02 | 浙江大学 | Interactive time-space accordant video matting method in digital video processing |
| CN101500091A (en) * | 2008-10-16 | 2009-08-05 | 黄福宝 | Character synthesizing method with two paths of video effects |
| CN101588459A (en) * | 2009-06-26 | 2009-11-25 | 北京交通大学 | A kind of video keying processing method |
| CN101783889A (en) * | 2010-02-05 | 2010-07-21 | 北京水晶石数字科技有限公司 | Real-time matting and video monitoring and collecting method |
| CN102305769A (en) * | 2011-06-09 | 2012-01-04 | 天津大学 | Multispectral sectional drawing method applied to Chinese ancient painting repair |
Non-Patent Citations (2)
| Title |
|---|
| 张展鹏、朱青松、谢耀钦: "数字抠像的最新研究进展", 《自动化学报》 * |
| 林生佑、潘瑞芳、杜辉、石教英: "数字抠图技术综述", 《计算机辅助设计与图形学学报》 * |
Cited By (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105096355A (en) * | 2014-05-08 | 2015-11-25 | 腾讯科技（深圳）有限公司 | Image processing method and system |
| CN104050700A (en) * | 2014-06-13 | 2014-09-17 | 北京奥普科星技术有限公司 | Image synthetic method and device |
| CN104539853A (en) * | 2015-01-05 | 2015-04-22 | 锦池媒体科技（北京）有限公司 | Image synthesis method |
| US9781400B2 (en) | 2015-03-09 | 2017-10-03 | Huawei Technologies Co., Ltd. | Image processing method and apparatus |
| CN104780296A (en) * | 2015-04-02 | 2015-07-15 | 上海东方传媒技术有限公司 | Video synthesis system and method for virtual remote interview |
| CN104954670A (en) * | 2015-04-30 | 2015-09-30 | 努比亚技术有限公司 | Photographing method and device |
| CN104954670B (en) * | 2015-04-30 | 2018-09-04 | 努比亚技术有限公司 | Photographic method and device |
| CN104902189A (en) * | 2015-06-24 | 2015-09-09 | 小米科技有限责任公司 | Picture processing method and picture processing device |
| CN105100646A (en) * | 2015-08-31 | 2015-11-25 | 北京奇艺世纪科技有限公司 | Video processing method and device |
| CN105100646B (en) * | 2015-08-31 | 2018-09-11 | 北京奇艺世纪科技有限公司 | Method for processing video frequency and device |
| CN105407254A (en) * | 2015-11-19 | 2016-03-16 | 广州玖的数码科技有限公司 | Real-time video and image synthesis method, real-time video and image synthesis device and global shooting equipment |
| CN105516562A (en) * | 2015-12-13 | 2016-04-20 | 重庆绿氧环保科技有限公司 | Product shooting device and quick image matting method |
| CN105654471A (en) * | 2015-12-24 | 2016-06-08 | 武汉鸿瑞达信息技术有限公司 | Augmented reality AR system applied to internet video live broadcast and method thereof |
| CN105654471B (en) * | 2015-12-24 | 2019-04-09 | 武汉鸿瑞达信息技术有限公司 | Augmented reality AR system and method applied to internet video live streaming |
| WO2017113873A1 (en) * | 2015-12-28 | 2017-07-06 | 努比亚技术有限公司 | Image synthesizing method, device and computer storage medium |
| CN105678724A (en) * | 2015-12-29 | 2016-06-15 | 北京奇艺世纪科技有限公司 | Background replacing method and apparatus for images |
| CN107707843A (en) * | 2016-08-09 | 2018-02-16 | 深圳泰和创邦文化传媒有限公司 | A kind of Video Composition and the method for imprinting |
| CN107730433A (en) * | 2017-09-28 | 2018-02-23 | 努比亚技术有限公司 | One kind shooting processing method, terminal and computer-readable recording medium |
| CN108109100B (en) * | 2017-12-19 | 2019-11-22 | 维沃移动通信有限公司 | A kind of image processing method, mobile terminal |
| CN108109100A (en) * | 2017-12-19 | 2018-06-01 | 维沃移动通信有限公司 | A kind of image processing method, mobile terminal |
| CN108282612B (en) * | 2018-01-12 | 2021-11-19 | 广州市百果园信息技术有限公司 | Video processing method, computer storage medium and terminal |
| CN108282612A (en) * | 2018-01-12 | 2018-07-13 | 广州市百果园信息技术有限公司 | Method for processing video frequency and computer storage media, terminal |
| CN108256497A (en) * | 2018-02-01 | 2018-07-06 | 北京中税网控股股份有限公司 | A kind of method of video image processing and device |
| CN108566521A (en) * | 2018-06-26 | 2018-09-21 | 蒋大武 | A kind of image synthesizing system for scratching picture based on natural image |
| CN111105358A (en) * | 2018-10-26 | 2020-05-05 | 阿里巴巴集团控股有限公司 | Image processing method and device |
| CN111105358B (en) * | 2018-10-26 | 2023-06-09 | 阿里巴巴集团控股有限公司 | Image processing method and device |
| CN109936710A (en) * | 2019-03-13 | 2019-06-25 | 深圳市瑞云科技有限公司 | A kind of production method of the short-sighted frequency of embedded background based on the rendering of CG cloud |
| CN111402181A (en) * | 2020-03-13 | 2020-07-10 | 北京奇艺世纪科技有限公司 | Image fusion method and device and computer readable storage medium |
| US11252341B2 (en) | 2020-04-27 | 2022-02-15 | Beijing Xiaomi Mobile Software Co., Ltd. | Method and device for shooting image, and storage medium |
| CN111586296A (en) * | 2020-04-27 | 2020-08-25 | 北京小米移动软件有限公司 | Image capturing method, image capturing apparatus, and storage medium |
| CN111818276A (en) * | 2020-06-30 | 2020-10-23 | 西安宏源视讯设备有限责任公司 | Method, device and storage medium for realizing interaction of different-place same-scene programs |
| CN114173059A (en) * | 2021-12-09 | 2022-03-11 | 广州阿凡提电子科技有限公司 | Video editing system, method and device |
| CN115393238A (en) * | 2022-08-23 | 2022-11-25 | 广州呗呗科技有限公司 | Image synthesis system and method based on virtual reality technology |
| CN116546180A (en) * | 2022-11-21 | 2023-08-04 | 马凯翔 | Naked eye suspension 3D video generation method, device, equipment and storage medium |
| CN116546180B (en) * | 2022-11-21 | 2024-02-23 | 马凯翔 | Naked eye suspension 3D video generation method, device, equipment and storage medium |
| CN115941920A (en) * | 2022-11-23 | 2023-04-07 | 马凯翔 | Naked eye 3D video generation method, device, equipment and storage medium |
| CN115941920B (en) * | 2022-11-23 | 2023-11-10 | 马凯翔 | Naked eye 3D video generation method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103475826A (en) | Video matting and synthesis method | |
| CN104200470B (en) | Blue screen image-matting method | |
| CN105654471B (en) | Augmented reality AR system and method applied to internet video live streaming | |
| CN104282002B (en) | A kind of quick beauty method of digital picture | |
| CN106530309B (en) | A kind of video matting method and system based on mobile platform | |
| CN104299220B (en) | A kind of method that cavity in Kinect depth image carries out real-time filling | |
| CN105976337B (en) | A kind of image defogging method based on intermediate value guiding filtering | |
| CN103440674B (en) | A kind of rapid generation of digital picture wax crayon specially good effect | |
| US20140176548A1 (en) | Facial image enhancement for video communication | |
| CN103955918A (en) | Full-automatic fine image matting device and method | |
| CN106570838A (en) | Image brightness optimization method and device | |
| CN105959510B (en) | A kind of video rapid defogging method | |
| US11778154B2 (en) | Low latency chroma keying embedded in a head-mounted display for mixed reality | |
| CN104679242A (en) | Hand gesture segmentation method based on monocular vision complicated background | |
| CN106530265A (en) | Adaptive image fusion method based on chromaticity coordinates | |
| CN107087104B (en) | The image treatment method of facial area and the electronic device for using the method | |
| CN104392425B (en) | A kind of image enchancing method of the adjust automatically contrast based on face | |
| CN107360344A (en) | Monitor video rapid defogging method | |
| CN106951891A (en) | Spot detection method and apparatus | |
| CN104680518B (en) | A kind of blue screen image cutting method based on colourity Overflow handling | |
| CN107527325A (en) | A kind of monocular underweater vision Enhancement Method preferential based on dark | |
| CN106504216B (en) | Single image to the fog method based on Variation Model | |
| CN112348736B (en) | Method, storage medium, device and system for removing black eye | |
| CN106447606A (en) | Rapid real-time video beautifying method | |
| CN106548490B (en) | A kind of illumination-insensitive quick stereo matching process based on Local Linear Model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20131225 |
|
| WD01 | Invention patent application deemed withdrawn after publication |