CN105827998A - Image matting system and image matting method - Google Patents
Image matting system and image matting method Download PDFInfo
- Publication number
- CN105827998A CN105827998A CN201610230800.1A CN201610230800A CN105827998A CN 105827998 A CN105827998 A CN 105827998A CN 201610230800 A CN201610230800 A CN 201610230800A CN 105827998 A CN105827998 A CN 105827998A
- Authority
- CN
- China
- Prior art keywords
- image
- target
- color
- background
- target 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.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
- H04N5/272—Means for inserting a foreground image in a background image, i.e. inlay, outlay
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Processing Of Color Television Signals (AREA)
- Color Television Image Signal Generators (AREA)
- Image Processing (AREA)
Abstract
The invention relates to an image matting system and an image matting method. The image matting system includes a VGA camera, an image capture unit extracting a target image from a basic background image, an infrared camera and a repair unit which performs color repair on the target image. The image matting method includes the following specific steps: (a) the VGA camera is utilized to convert a natural state background that is shot into a YUV/RGB color, and a stored color value is used as a basic background; (b) a target is put in a camera framing range for image capturing, a basic background image is removed from an input image and a target image is extracted, and if the target image and a background are the same in color at the moment, the color in the target image is partially missing, and a target image correction step is entered at the moment; (c) the infrared camera is utilized to perform target shooting; and (d) a color range presented by the target is repaired and restored, thereby obtaining a corrected target image. The image matting system and image matting method do not need a blue box, and can realize convenient and rapid image matting processing of an image in a natural state background.
Description
Technical field
The present invention relates to scratch as technology, particularly without blue case as the stingy picture system of background and stingy image space method.
Background technology
" scratch as " word is to get from early stage television production.In television production in early days, scratch as needing expensive hardware supported, and very tight to the context request of shooting, need to shoot under specific lan settings, light requires the strictest.Hardware stunt of today can easily be accomplished, but price makes people inspire awe even from distance, and many medium and small units can not bear.
Additionally, for static images, under condition is limited, it is also required to utilize the background scratched as changing image, the most commonly uses manual operations, utilize the image processing softwares such as photoshop, the most not only waste time and energy, under efficient, and effect is widely different because of the level of staff, and quality is not fully up to expectations.For improving the quality and efficiency scratching picture, a kind of color background keying processing method occurs, if China Patent Publication No. is 102395007A color background video/picture keying processing method, comprise the steps: video/picture pretreatment: be set as rgb format by unified for the picture format of video/picture；Background colour simply filters: set background color value, background color amplitude of variation threshold value and the reflective color value of object filtered, and video/picture is progressively scanned pixel, it may be judged whether filter this pixel；Object edge colour mixture filters: set the edge colour mixture amplitude of variation threshold value that need to retain object, video/picture is progressively scanned pixel, carries out edge colour mixture and filter；Filter omission background colour: rotating video/picture, repeat up and down to carry out background colour omitting detection；Synthesis new images: the video/picture after being processed by stingy picture and new Background carry out synthesis process.Above-mentioned scratch as time need to use color background, such as the background of blue case etc, although the Quality advance scratching picture is many, however it is necessary that building background expends certain manpower and materials.
Summary of the invention
The technical problem to be solved is to provide a kind of stingy picture system and stingy image space method, can realize scratching as process easily and fast by the image under naturalness background.
For solving above-mentioned technical problem, the technical scheme is that a kind of stingy image space method, including target image extraction step and target image correction step；
Target image extraction step:
A the naturalness background transitions being filmed is become YUV/RGB color first with VGA photographic head by (), using the colour preserved as basic background；
B target is put into camera view scope and is carried out picture catching by (), remove basic background image extraction target image in the input image, if now target image is identical with background color, the color in target image will excalation, now target approach chart picture correction step；
Target image correction step:
C () utilizes infrared camera to carry out target shooting, identify image is a depth field, and the color of each of which pixel represents that object distance to photographic head, the color that target is different from background；
D color gamut that () is presented target carries out repairing reduction, obtains revised target image.
As improvement, described target image is character image, can be synthesized with virtual scene by the stingy picture of personage.
As improvement, the target image of correction is synthesized about virtual scene.
For solving above-mentioned technical problem, the present invention another solution is that
A kind of stingy picture system, including:
The naturalness background transitions being filmed is become YUV/RGB color the VGA photographic head preserved as basic background；
The image capture unit that target image is extracted from basic background image；
Target is shot the infrared camera in different colours with background；
Target image is carried out the reparation unit of color reparation.
Accompanying drawing explanation
Fig. 1 is flow chart of the present invention.
Detailed description of the invention
Below in conjunction with Figure of description, the invention will be further described.
A kind of personage scratches as system, including VGA photographic head, infrared camera, the image capture unit extracted from basic background image by target image, target image carries out color reparation repairs unit and the synthesis unit synthesized with virtual scene by target image.
The present invention utilizes Microsoft's Kinect video camera as the input acquisition camera of video, and built-in two photographic head of Kinect video camera, opticator includes two critical pieces: RF transmitter and infrared ray/VGA photographic head group.RF transmitter sends " laser " together and covers the visual range of whole Kinect video camera, and photographic head group receives reflection light and identifies personage.Infrared camera identification image is one " depth field " (DepthField), the color of each of which pixel represents that object distance to photographic head, the such as health close to photographic head is shiny red, green etc., and the object away from photographic head is then in lead.
As it is shown in figure 1, the idiographic flow scratching picture includes:
Target image extraction step:
A the naturalness background transitions being filmed is become YUV/RGB color (including brightness) first with VGA photographic head by (), and using the colour preserved as basic background；
B () then personage enters VGA photographic head viewfinder range and carries out character image seizure, No. 1 background image extraction personage is removed in No. 2 input pictures, if now figure and ground's color is identical, the color in personage will excalation, now system can enter image correction process；
Target image correction step:
C () utilizes infrared camera to carry out personage's shooting, that identify image is one " depth field " (DepthField), and the color of each of which pixel represents that object distance to photographic head.The such as health close to photographic head is bright green etc., and the object away from photographic head is then in lead；
D color gamut that () is presented character image carries out repairing reduction, obtains revised character image；
Scratch as synthesis step:
E () obtains revised character image after target image extraction and target image correction flow process, finally character image and intrasystem scene are synthesized, and completes without the stingy picture synthesis under blue case (and natural background).
Claims (4)
1. a stingy image space method, it is characterised in that: include target image extraction step and target image correction step；
Target image extraction step:
A the naturalness background transitions being filmed is become YUV/RGB color first with VGA photographic head by (), using the colour preserved as basic background；
B target is put into camera view scope and is carried out picture catching by (), remove basic background image extraction target image in the input image, if now target image is identical with background color, the color in target image will excalation, now target approach chart picture correction step；
Target image correction step:
C () utilizes infrared camera to carry out target shooting, identify image is a depth field, and the color of each of which pixel represents that object distance to photographic head, the color that target is different from background；
D color gamut that () is presented target carries out repairing reduction, obtains revised target image.
One the most according to claim 1 scratches image space method, it is characterised in that: described target image is character image.
One the most according to claim 1 scratches image space method, it is characterised in that: the target image of correction is synthesized about virtual scene.
4. scratch as system for one kind, it is characterised in that including:
The naturalness background transitions being filmed is become YUV/RGB color the VGA photographic head preserved as basic background；
The image capture unit that target image is extracted from basic background image；
Target is shot the infrared camera in different colours with background；
Target image is carried out the reparation unit of color reparation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610230800.1A CN105827998A (en) | 2016-04-14 | 2016-04-14 | Image matting system and image matting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610230800.1A CN105827998A (en) | 2016-04-14 | 2016-04-14 | Image matting system and image matting method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105827998A true CN105827998A (en) | 2016-08-03 |
Family
ID=56526880
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610230800.1A Pending CN105827998A (en) | 2016-04-14 | 2016-04-14 | Image matting system and image matting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105827998A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106412420A (en) * | 2016-08-25 | 2017-02-15 | 安徽华夏显示技术股份有限公司 | Interactive photographing implementation method |
| CN108307163A (en) * | 2018-02-07 | 2018-07-20 | 重庆虚拟实境科技有限公司 | Image processing method and device, computer installation and readable storage medium storing program for executing |
| CN108566521A (en) * | 2018-06-26 | 2018-09-21 | 蒋大武 | A kind of image synthesizing system for scratching picture based on natural image |
| CN111415367A (en) * | 2020-03-18 | 2020-07-14 | 北京七维视觉传媒科技有限公司 | Method and device for removing image background |
| CN114113104A (en) * | 2021-11-10 | 2022-03-01 | 厦门聚视智创科技有限公司 | Cell-phone back of body frame 3D face image device |
| CN116597129A (en) * | 2023-05-09 | 2023-08-15 | 深圳市松林湾科技有限公司 | Object detection method in image recognition |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101335841A (en) * | 2007-06-28 | 2008-12-31 | 索尼株式会社 | Image pickup device |
| US20120051631A1 (en) * | 2010-08-30 | 2012-03-01 | The Board Of Trustees Of The University Of Illinois | System for background subtraction with 3d camera |
| CN102760287A (en) * | 2011-04-29 | 2012-10-31 | 国际商业机器公司 | Color correction method for static cameras and apparatus thereof |
| US20130050453A1 (en) * | 2011-08-24 | 2013-02-28 | Fluke Corporation | Thermal imaging camera with range detection |
| CN103093471A (en) * | 2013-01-24 | 2013-05-08 | 青岛智目科技有限公司 | Foreground extraction method under complicated background |
| CN103108173A (en) * | 2013-03-05 | 2013-05-15 | 胡茂林 | Intelligent video monitoring system with privacy protection function |
| CN103544693A (en) * | 2013-04-11 | 2014-01-29 | Tcl集团股份有限公司 | Method and system for extracting foreground object |
| CN105229697A (en) * | 2013-04-15 | 2016-01-06 | 微软技术许可有限责任公司 | Multi-modal prospect background segmentation |
-
2016
- 2016-04-14 CN CN201610230800.1A patent/CN105827998A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101335841A (en) * | 2007-06-28 | 2008-12-31 | 索尼株式会社 | Image pickup device |
| US20120051631A1 (en) * | 2010-08-30 | 2012-03-01 | The Board Of Trustees Of The University Of Illinois | System for background subtraction with 3d camera |
| CN102760287A (en) * | 2011-04-29 | 2012-10-31 | 国际商业机器公司 | Color correction method for static cameras and apparatus thereof |
| US20130050453A1 (en) * | 2011-08-24 | 2013-02-28 | Fluke Corporation | Thermal imaging camera with range detection |
| CN103093471A (en) * | 2013-01-24 | 2013-05-08 | 青岛智目科技有限公司 | Foreground extraction method under complicated background |
| CN103108173A (en) * | 2013-03-05 | 2013-05-15 | 胡茂林 | Intelligent video monitoring system with privacy protection function |
| CN103544693A (en) * | 2013-04-11 | 2014-01-29 | Tcl集团股份有限公司 | Method and system for extracting foreground object |
| CN105229697A (en) * | 2013-04-15 | 2016-01-06 | 微软技术许可有限责任公司 | Multi-modal prospect background segmentation |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106412420A (en) * | 2016-08-25 | 2017-02-15 | 安徽华夏显示技术股份有限公司 | Interactive photographing implementation method |
| CN106412420B (en) * | 2016-08-25 | 2019-05-03 | 安徽华夏显示技术股份有限公司 | It is a kind of to interact implementation method of taking pictures |
| CN108307163A (en) * | 2018-02-07 | 2018-07-20 | 重庆虚拟实境科技有限公司 | Image processing method and device, computer installation and readable storage medium storing program for executing |
| CN108307163B (en) * | 2018-02-07 | 2019-11-19 | 重庆虚拟实境科技有限公司 | Image processing method and device, computer installation and readable storage medium storing program for executing |
| CN108566521A (en) * | 2018-06-26 | 2018-09-21 | 蒋大武 | A kind of image synthesizing system for scratching picture based on natural image |
| CN111415367A (en) * | 2020-03-18 | 2020-07-14 | 北京七维视觉传媒科技有限公司 | Method and device for removing image background |
| CN114113104A (en) * | 2021-11-10 | 2022-03-01 | 厦门聚视智创科技有限公司 | Cell-phone back of body frame 3D face image device |
| CN116597129A (en) * | 2023-05-09 | 2023-08-15 | 深圳市松林湾科技有限公司 | Object detection method in image recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105827998A (en) | Image matting system and image matting method | |
| CN103997631B (en) | A kind of LED pointwise position contour extraction method based on camera shooting and system | |
| WO2013185449A1 (en) | Image enhancement method, image enhancement device and display device | |
| CN108717691B (en) | Image fusion method and device, electronic equipment and medium | |
| CN106204459A (en) | The method of image visibility reparation and image processing apparatus thereof | |
| CN112396999B (en) | Abnormal display block detection method, display screen fault detection method and equipment thereof | |
| CN106570850B (en) | A kind of image interfusion method | |
| CN106534683B (en) | Intelligent camera replaces the method and its system of Background in real time | |
| WO2005067316A3 (en) | Method and apparatus for capturing images using a color laser projection display | |
| CN107272234A (en) | A kind of detection method and system based on lcd panel test picture | |
| CN104639923A (en) | Method and device for processing image data, and terminal | |
| CN107404647A (en) | Camera lens condition detection method and device | |
| CN106534817A (en) | Image-identification-based automatic geometric correction method for curved surface projection | |
| CN111107330B (en) | Color cast correction method for Lab space | |
| CN107169973A (en) | The background removal and synthetic method and device of a kind of image | |
| CN104766307A (en) | Picture processing method and device | |
| CN106506939A (en) | A kind of image collecting device and acquisition method | |
| CN105989583B (en) | A kind of image defogging method | |
| CN111277764B (en) | 4K real-time video panorama stitching method based on GPU acceleration | |
| US7973977B2 (en) | System and method for removing semi-transparent artifacts from digital images caused by contaminants in the camera's optical path | |
| CN102395007B (en) | Single-colour background video/picture keying processing method | |
| JP2002328096A (en) | Program, method, and system for detecting crack defect generated on structure | |
| CN107454318A (en) | Image processing method, device, mobile terminal and computer-readable recording medium | |
| CN107277369A (en) | Image processing method, device, computer-readable recording medium and computer equipment | |
| CN108898566B (en) | Low-illumination color video enhancement method using space-time illumination map |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160803 |
|
| RJ01 | Rejection of invention patent application after publication |