CN103886578A - Color image background extraction processor - Google Patents
Color image background extraction processor Download PDFInfo
- Publication number
- CN103886578A CN103886578A CN201310611770.5A CN201310611770A CN103886578A CN 103886578 A CN103886578 A CN 103886578A CN 201310611770 A CN201310611770 A CN 201310611770A CN 103886578 A CN103886578 A CN 103886578A
- Authority
- CN
- China
- Prior art keywords
- standard deviation
- image background
- point
- obtaining
- coloured 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
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a color image background extraction processor, and aims at enhancing the effect of color image background extraction via improvement of a color image background extraction mode based on a mean value. The color image background extraction processor comprises four steps of image sequence sampling, obtaining of a central point, obtaining of a standard deviation and obtaining of the mean value. The realization method of the aforementioned steps is that the image sequence sampling step is executed via a camera. The step of obtaining of the central point is executed on the same pixel point of the acquired image sequence. After execution of the step of obtaining of the central point, the step of obtaining of the standard deviation is executed. Then sampling points whose deviation to the central point is greater than the standard deviation are eliminated. Finally, the step of obtaining of the mean value is executed on the rest pixel points and the mean value is outputted as a background value of the pixel points.
Description
Technical field
The present invention relates to coloured image background extracting field, more specifically a kind of the coloured image background extracting mode based on average is made to improved processor.
Background technology
Background extracting is in sequence of video images, to extract background.Background is exactly actionless scenery in scene.Because video camera is motionless, therefore the each pixel in image has a corresponding background value, and within a period of time, this value is more fixing.The target of background extracting is exactly according to sequence of video images, finds out the background value of every bit in image.The quality of the background image that this step extracts will directly have influence on the result of successive image treatment step.The present invention by disclosed be a kind of processor that extracts background image in the case of any information that there is no sport foreground, input is sequence of video images, every two field picture all comprises moving object and static scenery, output is the background image containing static scenery only.
The background extracting of coloured image, basic thought is that certain pixel in image is by time sample, to be compared to time of sport foreground long time of pixel as a setting for it, be that its likelihood ratio is as a setting large as the probability of prospect, and background and prospect have a great difference in color He in brightness.This be because, for fixed scene, moving object is in motion, it is written in water, we see most of time is all static background, therefore on image certain pixel as time of prospect time much shorter relatively as a setting; And moving object and static background have obvious difference on color, people can tell foreground object easily, even on a rest image.No matter which kind of method is all based on this thought.
Summary of the invention
For addressing the above problem, the invention discloses a kind of coloured image background extracting processor, object is by the improvement of the coloured image background extracting mode to based on average, promotes and extracts coloured image background effect.
The present invention takes following technical scheme to realize: a kind of coloured image background extracting processor, comprises image sequence sampling, centering point, asks standard deviation and average four steps; The implementation of above-mentioned steps is by camera carries out image sequential sampling step, same pixel to the image sequence collecting is carried out centering point step, after carrying out centering point step, standard deviation step is asked in execution, then with the difference of central point be greater than standard deviation sampled point remove, the last step of more remaining pixel execution being averaged, and this is worth to the background value output as this pixel.
Realization of the present invention also comprises following technical scheme:
Above-mentioned image sequence sampling step is in the time period, to have sampled by the fixing camera in position again.
Above-mentioned centering point step is exactly the implementation of averaging in the coloured image background extracting mode based on average, and formula is
n is N picture frame F
i, i=1,2 ... N.
The above-mentioned standard deviation step implementation of asking is
c=r, g, b represents three kinds of color components of red, green, blue of coloured image, X
0the central point of sample, i.e. mean value.
Advantage of the present invention and beneficial effect are embodied in the following aspects:
1. the present invention makes full use of all pixel element in image sequence.
2. use the present invention for the sequence of video images of 10 seconds through experiment, adopt the sampling rate of 2 frames per second, less than within 4 seconds, just obtaining outstanding background image.
Brief description of the drawings
Fig. 1 is execution step schematic diagram of the present invention.
Embodiment
Below in conjunction with Figure of description 1, enforcement of the present invention is further described:
The present invention takes following technical scheme to realize: a kind of coloured image background extracting processor, comprises image sequence sampling, centering point, asks standard deviation and average four steps; The implementation of above-mentioned steps is by camera carries out image sequential sampling step, same pixel to the image sequence collecting is carried out centering point step, after carrying out centering point step, standard deviation step is asked in execution, then with the difference of central point be greater than standard deviation sampled point remove, the last step of more remaining pixel execution being averaged, and this is worth to the background value output as this pixel.
Before averaging, be the pixel of background if can remove unlikely, obtain so the mean value coming and can more approach background.But, this time, prospect was not also known, how does is can simple and effectively obtain unlikely the pixel of background? the number of times occurring according to background is more than prospect, and foreground color is different with background, can know, for certain pixel, it can flock together by point in colored rgb space to the sampled point of time centered by background dot, and foreground point meeting decentering point is distant.Can think, it is background that the distance of the one-component decentering point of pixel color vector exceedes the point of standard deviation of this component unlikely, even background, larger noise has also superposeed.Standard deviation computing formula is
c=r, g, b represents three kinds of color components of red, green, blue of vector, X
0the central point of sample, i.e. mean value.Therefore, can improve the coloured image Algorithms for Background Extraction based on average: after averaging, ask standard deviation, then the sampled point that is greater than standard deviation with the difference of central point is removed, the mean value of the point under last complementation again, this value value as a setting.Improved implementation is as follows:
1) at a time between section sampling obtain N picture frame F
i, i=1,2 ... N, gathers an image sequence;
2) to each pixel (x, y):
A) centering point
B) ask standard deviation
c=r,g,b;
C) ask set
The mean value of middle all elements, this value is exactly required background B (x, y).
Utilize technical solutions according to the invention, or those skilled in the art being under the inspiration of technical solution of the present invention, designs similar technical scheme, and reaching above-mentioned technique effect, is all to fall into protection scope of the present invention.
Claims (4)
1. a coloured image background extracting processor, comprises image sequence sampling, centering point, asks standard deviation and average four steps; The implementation of above-mentioned steps is to carry out described image sequence sampling step by camera, the same pixel of the image sequence collecting is carried out to described centering point step, carry out described in carrying out after described centering point step and ask standard deviation step, then with the difference of central point be greater than standard deviation sampled point remove, last again by the step of averaging described in remaining pixel execution, and this is worth to the background value output as this pixel.
2. a kind of coloured image background extracting processor according to claim 1, is characterized in that: described image sequence sampling step is in the time period, to have sampled by the fixing camera in position again.
3. a kind of coloured image background extracting processor according to claim 1, is characterized in that: described centering point step is exactly the implementation of averaging in the coloured image background extracting mode based on average, and formula is
n is N picture frame F
i, i=1,2 ... N.
4. a kind of coloured image background extracting processor according to claim 1, is characterized in that: described in ask standard deviation step implementation to be
c=r, g, b represents three kinds of color components of red, green, blue of coloured image, X
0the central point of sample, i.e. mean value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310611770.5A CN103886578A (en) | 2013-11-26 | 2013-11-26 | Color image background extraction processor |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310611770.5A CN103886578A (en) | 2013-11-26 | 2013-11-26 | Color image background extraction processor |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103886578A true CN103886578A (en) | 2014-06-25 |
Family
ID=50955452
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310611770.5A Pending CN103886578A (en) | 2013-11-26 | 2013-11-26 | Color image background extraction processor |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103886578A (en) |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080002216A1 (en) * | 2001-06-11 | 2008-01-03 | Yuki Matsushima | Image processing apparatus, image processing method and information recording medium |
-
2013
- 2013-11-26 CN CN201310611770.5A patent/CN103886578A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080002216A1 (en) * | 2001-06-11 | 2008-01-03 | Yuki Matsushima | Image processing apparatus, image processing method and information recording medium |
Non-Patent Citations (1)
Title |
---|
郑志洵: ""运动目标检测与跟踪的研究与实现"", 《中国优秀博硕士学位论文全文数据库 (硕士) 信息科技辑》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103327220B (en) | With green channel for the denoising method guided on low-light (level) Bayer image | |
CN102077572A (en) | Method and apparatus for motion blur and ghosting prevention in imaging system | |
CN103578116A (en) | Apparatus and method for tracking object | |
CN105957030A (en) | Infrared thermal imaging system image detail enhancing and noise inhibiting method | |
KR20170017911A (en) | Methods and systems for color processing of digital images | |
CN103049888A (en) | Image/video demisting method based on combination of dark primary color of atmospheric scattered light | |
CN102063704B (en) | Airborne vision enhancement method and device | |
CN104021527B (en) | Rain and snow removal method in image | |
WO2017084391A1 (en) | Method and system for performing fluorescence processing on an image of a projector | |
CN105898111B (en) | A kind of video defogging method based on spectral clustering | |
EP3086553A1 (en) | Method and apparatus for image colorization | |
KR20080113526A (en) | Image processing apparatus and method thereof | |
CN106651811B (en) | A kind of simple lens imaging ambiguity removal method of luminance channel guiding | |
TWI376648B (en) | Method and device for keeping image background by multiple gauss models | |
CN104200447A (en) | Real-time low-light color image enhancement method and implementation method thereof | |
EP3046074A1 (en) | Method and apparatus for color correction in an alpha matting process | |
CN104732497A (en) | Image defogging method, FPGA and defogging system including FPGA | |
CN103997592A (en) | Method and system for video noise reduction | |
CN105046222A (en) | FPGA-based human face detection and tracking method | |
CN103313068A (en) | White balance corrected image processing method and device based on gray edge constraint gray world | |
CN107027017A (en) | A kind of method of adjustment, device, picture processing chip and the storage device of image white balance | |
CN208424534U (en) | The cartridge assemblies and imager of imager | |
CN111147924B (en) | Video enhancement processing method and system | |
TWI530913B (en) | Moving subject detecting system and method | |
CN106296626B (en) | A kind of night video enhancement method based on gradient fusion |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20140625 |