CN103927760A - Automatic stereoscopic vision color calibration system - Google Patents
Automatic stereoscopic vision color calibration system Download PDFInfo
- Publication number
- CN103927760A CN103927760A CN201410181444.XA CN201410181444A CN103927760A CN 103927760 A CN103927760 A CN 103927760A CN 201410181444 A CN201410181444 A CN 201410181444A CN 103927760 A CN103927760 A CN 103927760A
- Authority
- CN
- China
- Prior art keywords
- right view
- pixel
- sheet
- left view
- feature pixel
- 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
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000000034 method Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 abstract description 9
- 238000003384 imaging method Methods 0.000 abstract description 8
- 230000004075 alteration Effects 0.000 abstract description 4
- 230000007613 environmental effect Effects 0.000 abstract 1
- 230000000007 visual effect Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 239000000284 extract Substances 0.000 description 4
- 238000013507 mapping Methods 0.000 description 4
- 238000012913 prioritisation Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 210000003128 head Anatomy 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 210000001525 retina Anatomy 0.000 description 1
- 230000035807 sensation Effects 0.000 description 1
Landscapes
- Processing Or Creating Images (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
Abstract
The invention provides an automatic stereoscopic vision color calibration system. A plurality of sets of characteristic pixel point pairs are extracted from a left view piece and a right view piece, the characteristic pixel point pairs are utilized for solving RGB three-channel chromatic aberration parameters, and finally the RGB three-channel chromatic aberration parameters are utilized for adjusting RGB values of pixel points in the right view piece. The color of the right view piece can be adjusted, the color of the left view piece and the color of the right view piece tend to be consistent, and the problem that in an existing robot stereoscopic vision system, imaging matching effects are poor due to the color difference between the left view piece and the right view piece. A calibration board is not required to be additionally set, the left view piece and the right view piece which are obtained in any environment and any time can be processed in real time, and the environmental adaptivity is achieved.
Description
Technical field
The present invention relates to picture processing field, particularly a kind of stereoscopic vision auto color calibration system.
Background technology
Modern machines people's technology has obtained develop rapidly under the promotion of artificial intelligence, computer technology and sensor technology, wherein, mobile robot has mobility and ability of self control because of it, and variation can conform, be widely used in logistics, the fields such as detection, service.For mobile robot, stereoscopic vision airmanship is core technology.At present, mobile robot's stereoscopic vision airmanship is based on human stereo vision system made.People's stereoscopic sensation is to set up like this: eyes are watched object attentively simultaneously, and eyes sight line intersects at a bit, is blinkpunkt, and the luminous point reflecting back into retina from blinkpunkt is corresponding, and this two signal of naming a person for a particular job proceeds to the picture that brain visual center synthesizes a complete object.Not only seen this point clearly, and this point the and around distance between object, the degree of depth, convex-concave etc. can be distinguished out.So, conventionally mobile apparatus head part is provided with two cameras in left and right, be used for simulating people's eyes, when two of left and right, camera is taken object simultaneously, left side camera is taken and is obtained left view sheet, and right side camera is taken and obtained right view sheet, and mobile robot's central processing element is put the parallax in left view sheet and right view sheet by computer memory, obtain the three-dimensional coordinate of this object, this object is positioned.
But, when the camera of diverse location setting is taken same object, conventionally all there is certain difference in the left view sheet and the color in right view sheet that obtain, this difference may be catoptrical difference in the difference of camera self, object, and the reasons such as difference of camera parameters setting cause.The difference of color in left view sheet and right view sheet in robot stereo vision, cause mobile robot when in esse certain physical points in location, cannot accurately obtain by the color of left view sheet and right view sheet this physical points imaging point in left view sheet and right view sheet respectively, make the matching effect of mobile robot's stereo vision system bad.
Summary of the invention
For above shortcomings in prior art, the invention provides and a kind ofly can carry out to left view sheet and right view sheet the stereoscopic vision auto color calibration system of color calibration, in order to the left view sheet of the stereo visual system collection to mobile robot and the color distortion of right view sheet, adjusted, solve mobile robot's stereo visual system easily because left and right view color distortion causes the not good problem of imaging matching effect, in order to help mobile robot better to carry out object identification.
For solving the problems of the technologies described above, realize goal of the invention, the technical solution used in the present invention is as follows:
A stereoscopic vision auto color calibration system, comprises picture load module, unique point processing module, picture adjustment module; Described picture load module is used for inputting left view sheet and right view sheet; Described unique point processing module is for extracting many stack features pixel pair from left view sheet and right view sheet, the left view feature pixel of every stack features pixel centering and right view feature pixel represent Same Physical point, and according to the extracted left view feature pixel of each stack features pixel centering and the rgb value of right view feature pixel, calculate the RGB triple channel Chromaticity parameters of left view sheet and right view sheet; Described picture adjustment module utilizes RGB triple channel Chromaticity parameters to adjust the rgb value of each pixel in right view sheet, completes the color calibration to left view sheet and right view sheet.
As a kind of prioritization scheme of such scheme, in described unique point processing module, left view feature pixel and right view feature pixel are the unique point with shape facility.
As the another kind of prioritization scheme of such scheme, described unique point processing module utilizes SIFT conversion to extract left view feature pixel and right view feature pixel.
Further optimization as such scheme, described unique point processing module is according to the extracted left view feature pixel of each stack features pixel centering and the rgb value of right view feature pixel, set up color map relational expression, utilize least square method, the RGB triple channel Chromaticity parameters that calculates left view sheet and right view sheet, described color map relational expression is:
Wherein, (Rr, Gr, Br) be the rgb value of feature pixel centering right view feature pixel, (Rl, Gl, Bl) is the rgb value of this feature pixel centering left view feature pixel, (KR, BR), (KG, BG), (KB, BB) is respectively RGB triple channel Chromaticity parameters.
As the further optimization of such scheme, described picture adjustment module utilizes RGB triple channel Chromaticity parameters to adjust the rgb value of each pixel in right view sheet:
Wherein, (rr, gr, br) is the rgb value of adjusting pixel in front right view sheet, (rr ', gr ', br ') for adjusting the rgb value of this pixel in rear right view sheet.
Than prior art, tool of the present invention has the following advantages:
1, stereoscopic vision auto color calibration system provided by the invention, can adjust the color of right view sheet, left view sheet and right view sheet color are reached unanimity, solved in existing mobile robot's stereo visual system the not good problem of imaging matching effect causing due to the difference of color in left view sheet and right view sheet.
2, stereoscopic vision auto color calibration system provided by the invention, calculated amount is little, can adjust in real time online the difference of color in left view sheet and right view sheet, and real-time is good, guarantees the optimum matching effect of stereo visual system.
3, stereoscopic vision auto color calibration system provided by the invention, does not need additionally to arrange scaling board, can be to any environment, and left view sheet and right view sheet that random time obtains are processed in real time, have environment self-adaption.
Accompanying drawing explanation
The structured flowchart of the stereoscopic vision auto color calibration system that Fig. 1 is.
Two feature pixels pair of Fig. 2 for extracting.
Embodiment
Stereoscopic vision auto color calibration system provided by the invention, for mobile apparatus human stereo vision, mobile robot is provided with two cameras in left and right, for simulating people's eyes.When localization for Mobile Robot jobbie, two of left and right camera is taken this object simultaneously.The camera on the left side obtains left view sheet, and the camera on the right obtains right view sheet.
Stereoscopic vision auto color calibration system provided by the invention, as shown in Figure 1, comprises picture load module, unique point processing module, picture adjustment module, described picture load module is used for inputting left view sheet and right view sheet, described unique point processing module is for extracting many stack features pixel pair from left view sheet and right view sheet, the left view feature pixel of every stack features pixel centering and right view feature pixel represent Same Physical point, be that left view feature pixel refers to this physical points imaging point in left camera, right view feature pixel refers to this physical points imaging point in right camera, as shown in Figure 2, point a, point b is respectively left view feature pixel, point a ', point b ' is respectively right view feature pixel, its mid point a and some a ' are a stack features pixel pair, point b and some b ' are a stack features pixel pair.And according to the extracted left view feature pixel of each stack features pixel centering and the rgb value of right view feature pixel, calculate the RGB triple channel Chromaticity parameters of left view sheet and right view sheet; Described picture adjustment module utilizes RGB triple channel Chromaticity parameters to adjust the rgb value of each pixel in right view sheet, completes the color calibration to left view sheet and right view sheet.
Rgb color pattern is a kind of color standard of industry member, by variation and their stacks each other of red (R), green (G), blue (B) three Color Channels are obtained to color miscellaneous, RGB is the color that represents three passages of red, green, blue.What therefore, in picture, the color of each pixel was determined by the rgb value of this pixel.When want to adjust in picture color time, need to adjust the rgb value of each pixel in picture.
In order to reduce error, unique point processing module can be extracted 100 stack features pixels pair, and to this 100 stack features pixel to processing.Can find out, stereoscopic vision auto color calibration system provided by the invention, RGB triple channel Chromaticity parameters can reflect the rgb value of every stack features pixel centering left view feature pixel and the mapping relations between the rgb value of right view feature pixel.Like this, when adjusting the color of right view sheet, the rgb value of adjusting pixel in front right view sheet of take is standard, utilize RGB triple channel Chromaticity parameters, obtain the rgb value of adjusting this pixel in rear right view sheet, for adjusting the color of right view sheet, left view sheet and right view sheet color are reached unanimity, solved in existing robot stereo vision's system the not good problem of imaging matching effect causing due to the difference of color in left view sheet and right view sheet.In addition, the present invention does not need, according to actual conditions, scaling board is additionally set, unique point processing module acquiescence left view sheet is that scaling board is (when specifically apply, also can take right view sheet as scaling board), when mobile robot is at any environment, when the left view sheet that random time obtains and right view sheet, the present invention can adjust the color of right view sheet rapidly, the optimum matching effect that has guaranteed stereo visual system, has environment self-adaption.
As prioritization scheme of the present invention, described unique point processing module utilizes SIFT conversion to extract left view feature pixel and right view feature pixel.Described unique point processing module is according to the extracted left view feature pixel of each stack features pixel centering and the rgb value of right view feature pixel, set up color map relational expression, utilize least square method, the RGB triple channel Chromaticity parameters that calculates left view sheet and right view sheet, described color map relational expression is:
Wherein, (Rr, Gr, Br) be the rgb value of feature pixel centering right view feature pixel, (Rl, Gl, Bl) is the rgb value of this feature pixel centering left view feature pixel, (KR, BR), (KG, BG), (KB, BB) is respectively RGB triple channel Chromaticity parameters.
Described picture adjustment module utilizes RGB triple channel Chromaticity parameters to adjust the rgb value of each pixel in right view sheet:
Wherein, (rr, gr, br) is the rgb value of adjusting pixel in front right view sheet, (rr ', gr ', br ') for adjusting the rgb value of this pixel in rear right view sheet.
SIFT converts the (abbreviation of Scale-invariant feature transform, be yardstick invariant features conversion) be used for detecting and describe the locality feature in image, it finds extreme point in space scale, and extracts its position, yardstick, rotational invariants.The left view feature pixel and the right view feature pixel that utilize SIFT conversion to obtain are SIFT unique point, SIFT feature pixel has good robustness and stability for the difference of color, rgb value and the mapping relations between the rgb value of right view feature pixel of this category feature pixel centering left view feature pixel are more stable, more accurate to solving the RGB triple channel Chromaticity parameters obtaining according to this category feature pixel, when adjusting the color of right view sheet, make the right view sheet color of acquisition more accurate.As another kind of scheme, in described unique point processing module, left view feature pixel and right view feature pixel are the unique point with shape facility.Shape facility mainly can be divided into based on contour shape and based on region shape two classes, and the shape facility based on contour shape is to extract from profile, and the shape facility based on region shape is to extract from region shape.User can extract according to actual conditions the shape facility of certain type.No matter be to utilize SIFT unique point or Feature Points, the present invention only needs according to a small amount of feature pixel pair, just can calculate RGB triple channel Chromaticity parameters comparatively accurately, calculated amount is little, can adjust in real time online the difference of color in left view sheet and right view sheet, real-time is good, guarantees the optimum matching effect of stereo visual system.
When calculating color map relational expression (formula 1), utilize least square method can solve easily RGB triple channel Chromaticity parameters, error is minimum.In the present embodiment, (KR, BR), (KG, BG), (KB, BB) three groups of Chromaticity parameters have reflected respectively R, G, the three-channel aberration mapping relations of B.During concrete enforcement, from left view sheet and right view sheet, extract somely to feature pixel pair, add up respectively these feature pixel centering right view feature pixels at the value Rr of R passage, the value Gr of G passage, the value Br of B passage; Left view feature pixel is at the value Rl of R passage, the value Gl of G passage, the value Bl of B passage; By several feature pixel centering right view feature pixels at the value Rr of R passage and left view feature pixel at the value Rl of R passage, utilize least square method to solve (KR, BR); In like manner, solve (KG, BG), (KB, BB).Like this, (KR, the BR) of acquisition, (KG, BG), (KB, BB) can stably reflect the three-channel aberration mapping relations of RGB in left view sheet and right view sheet.When adjusting the color of right view sheet, obtain the rgb value (rr, gr, br) of adjusting pixel in front right view sheet, according to formula 2 calculate adjust after in right view sheet this pixel rgb value (rr ', gr ', br '), by (rr ', gr ', br ') adjust the color of this pixel in right view sheet, left view sheet and right view sheet color are reached unanimity, error is minimum.
In sum, stereoscopic vision auto color calibration system provided by the invention, from left view sheet and right view sheet, extract many stack features pixel pair, and utilize these feature pixels to resolving RGB triple channel Chromaticity parameters, finally, utilize RGB triple channel Chromaticity parameters to adjust the rgb value of each pixel in right view sheet.Can adjust the color of right view sheet, left view sheet and right view sheet color are reached unanimity, solve in existing robot stereo vision's system, the not good problem of imaging matching effect causing due to the difference of color in left view sheet and right view sheet.Do not need additionally to arrange scaling board, can be to any environment, left view sheet and right view sheet that random time obtains are processed in real time, have environment self-adaption.
Finally explanation is, above embodiment is only unrestricted in order to technical scheme of the present invention to be described, although the present invention is had been described in detail with reference to preferred embodiment, those of ordinary skill in the art is to be understood that, can modify or be equal to replacement technical scheme of the present invention, and not departing from aim and the scope of technical solution of the present invention, it all should be encompassed in the middle of claim scope of the present invention.
Claims (5)
1. a stereoscopic vision auto color calibration system, is characterized in that, comprises picture load module, unique point processing module, picture adjustment module; Described picture load module is used for inputting left view sheet and right view sheet; Described unique point processing module is for extracting many stack features pixel pair from left view sheet and right view sheet, the left view feature pixel of every stack features pixel centering and right view feature pixel represent Same Physical point, and according to the extracted left view feature pixel of each stack features pixel centering and the rgb value of right view feature pixel, calculate the RGB triple channel Chromaticity parameters of left view sheet and right view sheet; Described picture adjustment module utilizes RGB triple channel Chromaticity parameters to adjust the rgb value of each pixel in right view sheet, completes the color calibration to left view sheet and right view sheet.
2. stereoscopic vision auto color calibration system as claimed in claim 1, is characterized in that, in described unique point processing module, left view feature pixel and right view feature pixel are the unique point with shape facility.
3. stereoscopic vision auto color calibration system as claimed in claim 1, is characterized in that, described unique point processing module utilizes SIFT conversion to extract left view feature pixel and right view feature pixel.
4. stereoscopic vision auto color calibration system as claimed in claim 1, it is characterized in that, described unique point processing module is according to the extracted left view feature pixel of each stack features pixel centering and the rgb value of right view feature pixel, set up color map relational expression, utilize least square method, the RGB triple channel Chromaticity parameters that calculates left view sheet and right view sheet, described color map relational expression is:
Wherein, (Rr, Gr, Br) be the rgb value of feature pixel centering right view feature pixel, (Rl, Gl, Bl) is the rgb value of this feature pixel centering left view feature pixel, (KR, BR), (KG, BG), (KB, BB) is respectively RGB triple channel Chromaticity parameters.
5. stereoscopic vision auto color calibration system as claimed in claim 4, is characterized in that, described picture adjustment module utilizes RGB triple channel Chromaticity parameters to adjust the rgb value of each pixel in right view sheet:
Wherein, (rr, gr, br) is the rgb value of adjusting pixel in front right view sheet, (rr ', gr ', br ') for adjusting the rgb value of this pixel in rear right view sheet.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410181444.XA CN103927760A (en) | 2014-04-30 | 2014-04-30 | Automatic stereoscopic vision color calibration system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410181444.XA CN103927760A (en) | 2014-04-30 | 2014-04-30 | Automatic stereoscopic vision color calibration system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103927760A true CN103927760A (en) | 2014-07-16 |
Family
ID=51145971
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410181444.XA Pending CN103927760A (en) | 2014-04-30 | 2014-04-30 | Automatic stereoscopic vision color calibration system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103927760A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111726600A (en) * | 2020-06-30 | 2020-09-29 | 深圳市精锋医疗科技有限公司 | Image processing method, device and storage medium for stereoscopic endoscope |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101799939A (en) * | 2010-04-02 | 2010-08-11 | 天津大学 | Rapid and self-adaptive generation algorithm of intermediate viewpoint based on left and right viewpoint images |
| CN102404595A (en) * | 2011-08-16 | 2012-04-04 | 上海交通大学 | Epipolar line correction method capable of providing 3D program shooting guidance |
| US20120242794A1 (en) * | 2011-03-24 | 2012-09-27 | Minwoo Park | Producing 3d images from captured 2d video |
| CN102905147A (en) * | 2012-09-03 | 2013-01-30 | 上海立体数码科技发展有限公司 | Three-dimensional image correction method and apparatus |
| CN103279973A (en) * | 2013-06-13 | 2013-09-04 | 清华大学 | Three-dimensional image matching system based on mixing and parallel |
-
2014
- 2014-04-30 CN CN201410181444.XA patent/CN103927760A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101799939A (en) * | 2010-04-02 | 2010-08-11 | 天津大学 | Rapid and self-adaptive generation algorithm of intermediate viewpoint based on left and right viewpoint images |
| US20120242794A1 (en) * | 2011-03-24 | 2012-09-27 | Minwoo Park | Producing 3d images from captured 2d video |
| CN102404595A (en) * | 2011-08-16 | 2012-04-04 | 上海交通大学 | Epipolar line correction method capable of providing 3D program shooting guidance |
| CN102905147A (en) * | 2012-09-03 | 2013-01-30 | 上海立体数码科技发展有限公司 | Three-dimensional image correction method and apparatus |
| CN103279973A (en) * | 2013-06-13 | 2013-09-04 | 清华大学 | Three-dimensional image matching system based on mixing and parallel |
Non-Patent Citations (1)
| Title |
|---|
| 孟凡阳 等: "多图像全景颜色特征分布线性变换不变性校正算法", 《信号处理》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111726600A (en) * | 2020-06-30 | 2020-09-29 | 深圳市精锋医疗科技有限公司 | Image processing method, device and storage medium for stereoscopic endoscope |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103955920B (en) | Binocular vision obstacle detection method based on three-dimensional point cloud segmentation | |
| EP2194725B1 (en) | Method and apparatus for correcting a depth image | |
| US10165262B2 (en) | Image processing device and markers | |
| CN109211207B (en) | Screw identification and positioning device based on machine vision | |
| US20120162385A1 (en) | Apparatus and method for acquiring 3d depth information | |
| CN109035309A (en) | Pose method for registering between binocular camera and laser radar based on stereoscopic vision | |
| CN102595182A (en) | Stereo display equipment, and correction method, device and system thereof | |
| CN103384847B (en) | Method for determining, in a natural posture, at least one geometric/physiognomic parameter associated with the mounting of an ophthalmic lens in a spectacle frame | |
| CN106218409A (en) | A kind of can the bore hole 3D automobile instrument display packing of tracing of human eye and device | |
| AU2009311052A1 (en) | Motion detection method, apparatus and system | |
| CN114463303B (en) | Road target detection method based on fusion of binocular camera and laser radar | |
| CN106019264A (en) | Binocular vision based UAV (Unmanned Aerial Vehicle) danger vehicle distance identifying system and method | |
| CN110096999B (en) | Chessboard recognition method, chessboard recognition device, electronic equipment and storable medium | |
| CN104766309A (en) | Plane feature point navigation and positioning method and device | |
| CN102364953A (en) | Color correction method and device for stereo image | |
| KR20170127103A (en) | System and method for 3-dimensional calibration of camera and depth sensor, and calibration device and calibration jig thereof | |
| CN106488210B (en) | The correction parameter acquisition methods and device of stereoscopic display device | |
| KR20170014916A (en) | Method for calculating an object's coordinates in an image using single camera and gps | |
| CN110662012A (en) | Naked eye 3D display effect optimization drawing arranging method and system and electronic equipment | |
| GB2591959A (en) | Optics based multi-dimensional target and multiple object detection and tracking method | |
| CN112700484A (en) | Depth map colorization method based on monocular depth camera | |
| CN103925931A (en) | Automatic stereoscopic vision geometric calibration system | |
| CN109299696B (en) | Face detection method and device based on double cameras | |
| CN101980292B (en) | Regular octagonal template-based board camera intrinsic parameter calibration method | |
| CN110889874A (en) | Error evaluation method for calibration result of binocular camera |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| ASS | Succession or assignment of patent right |
Owner name: CHONGQING GLOBAL SIGHT HIGH TECHNOLOGY CO., LTD. Free format text: FORMER OWNER: CHONGQING GLOBAL SIGHT TECHNOLOGY CO., LTD. Effective date: 20150421 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| COR | Change of bibliographic data |
Free format text: CORRECT: ADDRESS; FROM: 400039 JIULONGPO, CHONGQING TO: 401133 BEIPEI, CHONGQING |
|
| TA01 | Transfer of patent application right |
Effective date of registration: 20150421 Address after: 401133 Chongqing District of Beibei city and high-tech Industrial Park Road No. 5, No. 137 of the Milky way Applicant after: CHONGQING GLOBAL SIGHT HIGH-TECHNOLOGY CO., LTD. Address before: Two road 400039 Chongqing Jiulongpo Branch Park No. 137 B block 7 layer 2-6 Applicant before: CHONGQING GLOBAL SIGHT TECHNOLOGY CO., LTD. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140716 |