CN104751458A - Calibration angle point detection method based on 180-degree rotating operator - Google Patents
Calibration angle point detection method based on 180-degree rotating operator Download PDFInfo
- Publication number
- CN104751458A CN104751458A CN201510127733.6A CN201510127733A CN104751458A CN 104751458 A CN104751458 A CN 104751458A CN 201510127733 A CN201510127733 A CN 201510127733A CN 104751458 A CN104751458 A CN 104751458A
- Authority
- CN
- China
- Prior art keywords
- point
- template
- rotation
- image
- detection 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.)
- Granted
Links
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a calibration angle point detection method based on a 180-degree rotating operator. The method comprises the steps of (1) acquiring a calibration image I to be treated; (2) determining gray level variation value I; (2) determining gray level variation degree Z1; (3) determining 180-degree rotating overlap ratio Z2; (4) extracting angle points of the image. According to the method, a die plate based on the 180-degree rotating operator is designed according to the rotating symmetry of patterns surrounding checkerboard angle points on three surfaces of a calibration block, so as to achieve the efficient detection for the angle points of the calibrating block; the experiment data and result analysis show that the method is high in accuracy and stability in angle point detection, applicable to the general calibration image and multi-surface calibration image, and has the same effect on the calibration image with a certain of inclination degree and deformation.
Description
Technical field
The present invention relates to the image processing field in surface-mounting equipment, particularly a kind of method of carrying out the accurate angle point detected in camera calibration fast based on 180 ° of rotation operators.
Background technology
Camera calibration is the important component part in machine vision and image procossing, and its precision determines the performance of whole three-dimension measuring system under many circumstances.Manufacture in series equipment at precise electronic, surface-mounting equipment is used to equipment PCB being carried out to components and parts attachment.Therefore, the importance of change system degree of accuracy is self-evident.Generally, be utilize cross-hatch pattern picture as uncalibrated image, angle point is wherein exactly the point that brightness of image change differs greatly with adjoint point intensity of variation.Corner Detection is the important step of camera calibration.By extracting the corner location information on image, can determine in three-dimension measuring system, the relation of information between picture planimetric coordinates and space coordinates of the every bit of three-dimensional body, thus obtain the inside and outside parameter of video camera, and then determine its locus.
The approach of camera calibration is according to camera model, is solved the model parameter of video camera by the image coordinate of known features point.In image, often some pixel is all obtained by transmission projection mode, corresponding to the ray that optical centre and scene point are formed, how to determine that the equation of this ray in scene coordinate system is exactly camera calibration problem to be solved.In calibration process, need inner parameter and the external parameter of determining video camera.In three-dimension measuring system, according to projective geometry and video camera pin-hole model, the formula extrapolating the transformation relation between scene world coordinate system and pixel coordinate system is as follows.
Wherein (X
wi, Y
wi, Z
wi, 1) and be the world coordinates of i-th point in space, (u
i, v
i, 1) and be the image coordinate of i-th; m
ijfor the i-th row jth column element of projection matrix M.
By by the three-dimensional coordinate of known angle point a large amount of in calibrating block and their pixel coordinates on video camera, projection matrix M can be solved.As can be seen from the above equation, the accuracy of detection of angle point directly determines the computational accuracy of camera parameters.
At present, the Corner Detection based on cross-hatch pattern picture mainly contains two kinds of modes: a kind of is the method manually obtained, and is clicked the position obtaining angle point one by one by mouse; Another kind is the method automatically detected, such as, utilize Harris operator, Susan operator etc. to obtain the corner location of image.The positional information of manual acquisition angle point, Problems existing has: first need manual intervention.Have impact on the speed in camera calibration image processing process, and have no idea to realize dynamic calibration; Secondly, the accuracy of detection of angle point is unstable, to a certain extent also can be relevant with the experience of operator etc.And in automatic testing method, although use Harris operator, Susan operator etc. can realize automatic Calibration process, also there will be precision instability, the situations such as pseudo-angle point, especially in the cross-hatch pattern picture tilted, and then have impact on the precision of whole camera calibration.
Summary of the invention
Fundamental purpose of the present invention is to overcome the shortcoming of prior art with not enough, provides a kind of demarcation angular-point detection method based on 180 ° of rotation operators, compared to existing angular-point detection method have practical, precision is high, fireballing feature.
In order to achieve the above object, the present invention is by the following technical solutions:
Based on a demarcation angular-point detection method for 180 ° of rotation operators, comprise the steps:
(1) obtain pending uncalibrated image I: in three-dimension measuring system, calibrating block is positioned over fixed position, regulate the brightness of light source, obtain uncalibrated image by video camera shooting;
(2) grey scale change degree Z1 is judged: to each point I (i on image, j) scan one by one, set up with pixel I (i, j) size centered by is the square rotation operator template W of n × n, utilize the method asking for gray scale mean square deviation to calculate the smooth situation of image in operator template, i.e. grey scale change degree Z1;
(3) judge that 180 ° rotate registration Z2: judge grey scale change degree Z1 and after extracting edge and angle point region, for qualified pixel I (i, j), calculate black and white gray scales in its rotation operator template W, carry out black and white gray scale in need exchange, produce new template, the template that this is new carries out the function of contact ratio calculating again, namely after 180 ° of rotations being carried out to rotation operator template W, obtain rotary template W0, ask for the average Z2 of the absolute value sum of each element in both matrix of differences;
(4) angle point of image is extracted: after judging grey scale change degree Z1 by rotation operator template and rotating registration Z2, obtain out the connected domain often locating angle point region, the point that interior registration is the highest, is the angle point of image.
Preferably, step (1) is before utilizing rotation operator process, and be first 5 × 5 to imaging importing template, width is the 2-d gaussian filters device of 1, and filter out impurities noise.
Preferably, the function g (i, j) of described 2-d gaussian filters device,
wherein
for template center
σ is width, is also smoothness.
Preferably, in step (1), described three-dimension measuring system comprises a projector, a camera system and a calibrating block.
Preferably, in step (2), calculate the mean square deviation function Z of grey scale change degree Z1
1(i, j), for:
In formula,
for the average gray of pixel in template W, n is the width of window W.
Preferably, in step (3), judge whether grey scale change degree Z1 meets predetermined threshold value T1, select threshold value T1 to be 0.1, judge Z
1whether (i, j) meets Z
1(i, j) >T1, if can meet, then prove with current pixel point I (i, j) the rotation operator template centered by is in marginal point or corner location and non-planar regions, and its grey scale change is comparatively large, continues to calculate its function of contact ratio value Z2 process; If can not meet, without the need to process, skip.
Preferably, in step (3), before calculating 180 ° of rotation registration Z2, judge black and white gray scales, template total area S=n × n, white portion area is S1, selects predetermined threshold value e=(n × n-1)/2, then account for area ratio α=S1/S,
Wherein W ' (i, j) is the rotation operator template after the exchange of black and white gray scale.
Preferably, the function Z that 180 ° rotate registration Z2 is calculated
2(i, j),
in formula, n is the width of window W, and (x, y) is the transfer point in window, and I (i-x, j+y) is the corresponding point after I (i+x, j-y) point rotates 180 ° centered by I (i, j).
Preferably, judge that whether rotate registration Z2 meets predetermined threshold value T2, selects threshold value T2 to be no more than 0.1, judges Z
2whether (i, j) meets Z
2(i, j) >T2, if can meet, then prove that the symmetry of the rotation operator template centered by current pixel point I (i, j) is enough, registration is higher, pixel I (i, j) is in angle point regional location, can accurately extract its position, otherwise then without the need to process, skip.
Preferably, by the Z of step (2) gained
1the Z of (i, j) and step (3) gained
2(i, j), obtains the residing approximate fuzzy region of angle point, utilizes eight neighborhood to obtain out connected domain, then superposes evaluation algorithm and filter out the point that in connected domain, coincidence angle value Z2 is the highest, is the angle point of image.
Compared with prior art, tool has the following advantages and beneficial effect in the present invention:
(1) the present invention detects angle point by 180 ° of rotational transforms, accelerates detection speed, and process is simple, workable.
(2) the present invention has unchangeability to rotational transform, and effectively can remove the interference of pseudo-angle point and noise, improves accuracy and the stability of algorithm.
(3) the present invention can not only be applicable to general scaling board image, is also applicable to the calibrating block image of multiple, has good effect equally for there being the uncalibrated image of certain degree of tilt and distortion.
(4) the present invention can meet needs of expected design, and compares with some other automatic detection algorithm popular at present, and its applicability is wider, and degree of accuracy is better, and stability is higher.
Accompanying drawing explanation
Fig. 1 is the structural representation of detection system of the present invention;
Fig. 2 is the process flow diagram of detection method;
Fig. 3 is the schematic diagram of rotation operator of the present invention;
Fig. 4 is the centrosymmetric schematic diagram of rotation operator of the present invention.
Embodiment
Below in conjunction with embodiment and accompanying drawing, the present invention is described in further detail, but embodiments of the present invention are not limited thereto.
As shown in Figure 1, the detection system of the demarcation angular-point detection method based on 180 ° of rotation operators of the present invention, comprises the calibrating block 4 on placement platform 3, and projector 2 as light source, can gather image by video camera 1.In normal calibration process, usually will gather the scaling board image being more than or equal to 2, and scaling board must can not be placed at same plane.So, first is complex operation, and second, in the process changing scaling board, can cause certain influence to measuring accuracy unavoidably.Here the calibrating block used, the cube be made up of at least 3 such scaling board faces.As shown in Figure 1.Use calibrating block only to need to take pictures once, in same figure, carry out algorithm process, therefore more convenient.
As shown in Figure 2, be the overall flow figure of a kind of angular-point detection method of the present invention, its concrete operation steps is as follows:
(1) obtaining pending uncalibrated image I: having in the three-dimension measuring system shown in Fig. 1, calibrating block is positioned over fixed position, regulating the brightness of light source, obtain uncalibrated image I by video camera shooting.Before utilizing rotation operator process, be first 5 × 5 to imaging importing template, width is the 2-d gaussian filters device of 1, and filter out impurities noise;
(2) judge grey scale change degree Z1: scan one by one each point I (i, j) on image, the size set up centered by pixel I (i, j) is the square rotation operator template W of n × n.Utilize the method asking for gray scale mean square deviation to calculate the smooth situation of image in operator template, i.e. grey scale change degree Z1.
As shown in Figure 3, the principle schematic of a kind of rotation operator designed for the present invention.For the every bit I (i, j) of image, the template centered by this point is referred to as W.W can be circular also can be square, and select square template here, if the width of template is n, then the number of pixels in template is n × n.In order to the accuracy of the accuracy that calculates and detection, the width n of W should be less than a tessellated length of side.The value of n is odd number, and this ensures that thering template at each point value of computation process is all integer.
When template W is in region a, image is smooth, and gray variance value is very little, is not therefore marginal point and angle point.When template W is in region b, its 180 ° of postrotational registrations are higher, are desirable angle points.And c, although d place image is uneven, also have certain symmetry, its symmetry about central point is lower.Like this, we just accurately can determine the position at angle point place according to the 180 ° of postrotational registrations calculated.
Need afterwards effectively to reject the flat site in image, extract marginal point and angle point region.Because in the template at the pixel place of flat site, the mean square deviation of pixel grey scale is smaller, so the mean square deviation response of design rotation operator is as the gray variance of reflection surrounding pixel gray-value variation severe degree, flat site is rejected with this, its formula expression, namely calculates the mean square deviation function Z of grey scale change degree Z1
1(i, j) is as follows
In formula,
for the average gray of pixel in template W, n is the width of window W.
Judge whether grey scale change degree Z1 meets predetermined threshold value T1.Threshold value T1 is selected to be approximately 0.1.Judge Z
1whether (i, j) meets Z
1(i, j) >T1, if can meet, then prove with current pixel point I (i, j) the rotation operator template centered by is in marginal point or corner location and non-planar regions, and its grey scale change is comparatively large, continues to calculate its function of contact ratio value Z2 process.If can not meet, without the need to process, this is non-angle point.
(3) judge that 180 ° rotate registration Z2: after judging grey scale change degree Z1, before calculating 180 ° of rotation registration Z2, for qualified pixel I (i, j), calculate black and white gray scales in its rotation operator template W, carry out black and white gray scale in need exchange, produce new template.This is because in the calibrating block image tilted, the directly above the function of contact ratio of calculating, the template of same degree of tilt, on the high side or black part is on the high side for white portion, its result of calculation also has larger difference.
Therefore in calculating degree of integration functional procedure, Rule of judgment is added: if in the template of rotation operator, the area of white portion accounts for the more than half of the total area, then black and white part is carried out grayvalue transition.The template that this is new carries out the function of contact ratio calculating again, after namely 180 ° of rotations being carried out to rotation operator template W, obtains rotary template W0, ask for the average Z2 of the absolute value sum of each element in both matrix of differences.
Template total area S=n × n, white portion area is S1, selects predetermined threshold value e=(n × n-1)/2.Then account for area ratio α=S1/S.Meet following situation then to exchange.
Wherein W ' (i, j) is the rotation operator template after the exchange of black and white gray scale.
As shown in Figure 4, be the centrosymmetric schematic diagram of rotation operator of the present invention.Be A1 (i+x, j-y) for certain pixel A (i+x, j-y) in template about the point that central point I (i, j) is symmetrical.The registration response of definition rotation operator is the mean value of the gray scale difference of two squares absolute value of every a pair pixel symmetrical about central point I (i, j) in template W, then the expression Z of the function of contact ratio
2(i, j) is as follows:
In formula, n is the width of window W, and (x, y) is the transfer point in window.I (i-x, j+y) is the corresponding point after I (i+x, j-y) point rotates 180 ° centered by I (i, j).The function of contact ratio calculated value Z2 of the feature angle point on uncalibrated image is less; And frontier point and noise etc., due to asymmetry, grey scale pixel value is large, and another side grey scale pixel value is little, so its Z2 is larger.On image, the function of contact ratio calculated value Z2 of certain 1 I (i, j) namely, the reflection of the spatial symmetry of pixel grey scale distribution within the scope of the wicket centered by this pixel.
Judge whether rotate registration Z2 meets predetermined threshold value T2.Threshold value T2 is selected to be no more than 0.1.Judge Z
2whether (i, j) meets Z
2(i, j) >T2, if can meet, then prove that the symmetry of the rotation operator template centered by current pixel point I (i, j) is enough, registration is higher, pixel I (i, j) is in angle point regional location, can accurately extract its position.Otherwise then without the need to process, belong to non-angle point.
(4) angle point of image is extracted: by the schematic diagram of the rotation operator of Fig. 4, visible this is with pixel I (i, j) rotation operator template W (square matrices of a n × n) centered by, after carrying out 180 ° of rotations, the new rotary template W0 obtained, both subtract each other again, ask for the average of the absolute value sum of each element in matrix of differences, i.e. the function of contact ratio value Z2.
After judging grey scale change degree Z1 by rotation operator template and rotating registration Z2, after obtaining out the connected domain often locating angle point region, then extract the angle point in each region respectively.Next eight neighborhood calculating is carried out to whole image, obtain out the connected domain of each angle point region.The point that interior registration is the highest, is the angle point of image.If the pixel number in the connected domain extracted in previous step is l, as l<2 or l>8, the pixel in this connected domain is noise or marginal point, is removed; If 1<l<9, then filter out the point that in connected domain, coincidence angle value Z2 is the highest, be the angle point of image.So far, the Corner Detection of uncalibrated image completes.
Above-described embodiment is the present invention's preferably embodiment; but embodiments of the present invention are not restricted to the described embodiments; change, the modification done under other any does not deviate from Spirit Essence of the present invention and principle, substitute, combine, simplify; all should be the substitute mode of equivalence, be included within protection scope of the present invention.
Claims (10)
1., based on a demarcation angular-point detection method for 180 ° of rotation operators, it is characterized in that, comprise the steps:
(1) obtain pending uncalibrated image I: in three-dimension measuring system, calibrating block is positioned over fixed position, regulate the brightness of light source, obtain uncalibrated image by video camera shooting;
(2) grey scale change degree Z1 is judged: to each point I (i on image, j) scan one by one, set up with pixel I (i, j) size centered by is the square rotation operator template W of n × n, utilize the method asking for gray scale mean square deviation to calculate the smooth situation of image in operator template, i.e. grey scale change degree Z1;
(3) judge that 180 ° rotate registration Z2: judge grey scale change degree Z1 and after extracting edge and angle point region, for qualified pixel I (i, j), calculate black and white gray scales in its rotation operator template W, carry out black and white gray scale in need exchange, produce new template, the template that this is new carries out the function of contact ratio calculating again, namely after 180 ° of rotations being carried out to rotation operator template W, obtain rotary template W0, ask for the average Z2 of the absolute value sum of each element in both matrix of differences;
(4) angle point of image is extracted: after judging grey scale change degree Z1 by rotation operator template and rotating registration Z2, obtain out the connected domain often locating angle point region, the point that interior registration is the highest, is the angle point of image.
2. the demarcation angular-point detection method based on 180 ° of rotation operators according to claim 1, it is characterized in that, step (1), before utilizing rotation operator process, is first 5 × 5 to imaging importing template, width is the 2-d gaussian filters device of 1, and filter out impurities noise.
3. the demarcation angular-point detection method based on 180 ° of rotation operators according to claim 2, is characterized in that, the function g (i, j) of described 2-d gaussian filters device,
wherein
for template center
σ is width, is also smoothness.
4. the demarcation angular-point detection method based on 180 ° of rotation operators according to claim 1, is characterized in that, in step (1), described three-dimension measuring system comprises a projector, a camera system and a calibrating block.
5. the demarcation angular-point detection method based on 180 ° of rotation operators according to claim 1, is characterized in that, in step (2), calculates the mean square deviation function Z of grey scale change degree Z1
1(i, j), for:
In formula,
for the average gray of pixel in template W, n is the width of window W.
6. the demarcation angular-point detection method based on 180 ° of rotation operators according to claim 5, is characterized in that, in step (3), judges whether grey scale change degree Z1 meets predetermined threshold value T1, selects threshold value T1 to be 0.1, judges Z
1whether (i, j) meets Z
1(i, j) >T1, if can meet, then prove with current pixel point I (i, j) the rotation operator template centered by is in marginal point or corner location and non-planar regions, and its grey scale change is comparatively large, continues to calculate its function of contact ratio value Z2 process; If can not meet, without the need to process, skip.
7. the demarcation angular-point detection method based on 180 ° of rotation operators according to claim 1, it is characterized in that, in step (3), before calculating 180 ° of rotation registration Z2, judge black and white gray scales, template total area S=n × n, white portion area is S1, selects predetermined threshold value e=(n × n-1)/2, then account for area ratio α=S1/S
Wherein W ' (i, j) is the rotation operator template after the exchange of black and white gray scale.
8. the demarcation angular-point detection method based on 180 ° of rotation operators according to claim 1, is characterized in that, calculates the function Z that 180 ° rotate registration Z2
2(i, j),
in formula, n is the width of window W, and (x, y) is the transfer point in window, and I (i-x, j+y) is the corresponding point after I (i+x, j-y) point rotates 180 ° centered by I (i, j).
9. the demarcation angular-point detection method based on 180 ° of rotation operators according to claim 1, is characterized in that, judges that whether rotate registration Z2 meets predetermined threshold value T2, selects threshold value T2 to be no more than 0.1, judges Z
2whether (i, j) meets Z
2(i, j) >T2, if can meet, then prove that the symmetry of the rotation operator template centered by current pixel point I (i, j) is enough, registration is higher, pixel I (i, j) is in angle point regional location, can accurately extract its position, otherwise then without the need to process, skip.
10. the demarcation angular-point detection method based on 180 ° of rotation operators according to claim 1, is characterized in that, by the Z of step (2) gained
1the Z of (i, j) and step (3) gained
2(i, j), obtains the residing approximate fuzzy region of angle point, utilizes eight neighborhood to obtain out connected domain, then superposes evaluation algorithm and filter out the point that in connected domain, coincidence angle value Z2 is the highest, is the angle point of image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510127733.6A CN104751458B (en) | 2015-03-23 | 2015-03-23 | A kind of demarcation angular-point detection method based on 180 ° of rotation operators |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510127733.6A CN104751458B (en) | 2015-03-23 | 2015-03-23 | A kind of demarcation angular-point detection method based on 180 ° of rotation operators |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104751458A true CN104751458A (en) | 2015-07-01 |
| CN104751458B CN104751458B (en) | 2017-08-25 |
Family
ID=53591077
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510127733.6A Active CN104751458B (en) | 2015-03-23 | 2015-03-23 | A kind of demarcation angular-point detection method based on 180 ° of rotation operators |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104751458B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105551048A (en) * | 2015-12-21 | 2016-05-04 | 华南理工大学 | Space surface patch-based three-dimensional corner detection method |
| CN106023171A (en) * | 2016-05-12 | 2016-10-12 | 惠州学院 | Image corner detection method based on turning radius |
| CN106780611A (en) * | 2016-12-10 | 2017-05-31 | 广东文讯科技有限公司 | One kind uses intelligent terminal camera angular-point detection method |
| CN107941241A (en) * | 2017-10-10 | 2018-04-20 | 天津大学 | A kind of resolving power test target and its application method for aerophotogrammetry quality evaluation |
| CN109658372A (en) * | 2017-10-10 | 2019-04-19 | 凌云光技术集团有限责任公司 | A kind of image conformity appraisal procedure and device |
| CN113376170A (en) * | 2021-06-16 | 2021-09-10 | 博众精工科技股份有限公司 | Calibration method and calibration block of product appearance detection equipment |
| WO2022048617A1 (en) * | 2020-09-04 | 2022-03-10 | 深圳光峰科技股份有限公司 | Method, device, and system for recognizing projection position, and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101763632A (en) * | 2008-12-26 | 2010-06-30 | 华为技术有限公司 | Method for demarcating camera and device thereof |
| CN101980292A (en) * | 2010-01-25 | 2011-02-23 | 北京工业大学 | Regular octagonal template-based board camera intrinsic parameter calibration method |
| CN103198319A (en) * | 2013-04-11 | 2013-07-10 | 武汉大学 | Method of extraction of corner of blurred image in mine shaft environment |
| US20130287290A1 (en) * | 2012-04-30 | 2013-10-31 | The Boeing Company | Image registration of multimodal data using 3d geoarcs |
| WO2013182080A1 (en) * | 2012-06-08 | 2013-12-12 | 华为技术有限公司 | Parameter calibration method and device |
| CN103679720A (en) * | 2013-12-09 | 2014-03-26 | 北京理工大学 | Fast image registration method based on wavelet decomposition and Harris corner detection |
| CN103927750A (en) * | 2014-04-18 | 2014-07-16 | 上海理工大学 | Detection method of checkboard grid image angular point sub pixel |
| CN104331900A (en) * | 2014-11-25 | 2015-02-04 | 湖南科技大学 | Corner sub-pixel positioning method in CCD (charge coupled device) camera calibration |
-
2015
- 2015-03-23 CN CN201510127733.6A patent/CN104751458B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101763632A (en) * | 2008-12-26 | 2010-06-30 | 华为技术有限公司 | Method for demarcating camera and device thereof |
| CN101980292A (en) * | 2010-01-25 | 2011-02-23 | 北京工业大学 | Regular octagonal template-based board camera intrinsic parameter calibration method |
| US20130287290A1 (en) * | 2012-04-30 | 2013-10-31 | The Boeing Company | Image registration of multimodal data using 3d geoarcs |
| WO2013182080A1 (en) * | 2012-06-08 | 2013-12-12 | 华为技术有限公司 | Parameter calibration method and device |
| CN103198319A (en) * | 2013-04-11 | 2013-07-10 | 武汉大学 | Method of extraction of corner of blurred image in mine shaft environment |
| CN103679720A (en) * | 2013-12-09 | 2014-03-26 | 北京理工大学 | Fast image registration method based on wavelet decomposition and Harris corner detection |
| CN103927750A (en) * | 2014-04-18 | 2014-07-16 | 上海理工大学 | Detection method of checkboard grid image angular point sub pixel |
| CN104331900A (en) * | 2014-11-25 | 2015-02-04 | 湖南科技大学 | Corner sub-pixel positioning method in CCD (charge coupled device) camera calibration |
Non-Patent Citations (3)
| Title |
|---|
| 凌江: ""基于双旋转模板的黑白棋盘角点检测算法"", 《图形、图像与多媒体》 * |
| 戴士杰等: ""使用12 像素对称模板的棋盘格内角点检测"", 《红外与激光工程》 * |
| 杨幸芳等: ""用于摄像机标定的棋盘图像角点检测新算法"", 《仪器仪表学报》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105551048A (en) * | 2015-12-21 | 2016-05-04 | 华南理工大学 | Space surface patch-based three-dimensional corner detection method |
| CN106023171A (en) * | 2016-05-12 | 2016-10-12 | 惠州学院 | Image corner detection method based on turning radius |
| CN106023171B (en) * | 2016-05-12 | 2019-05-14 | 惠州学院 | A kind of image angular-point detection method based on turning radius |
| CN106780611A (en) * | 2016-12-10 | 2017-05-31 | 广东文讯科技有限公司 | One kind uses intelligent terminal camera angular-point detection method |
| CN107941241A (en) * | 2017-10-10 | 2018-04-20 | 天津大学 | A kind of resolving power test target and its application method for aerophotogrammetry quality evaluation |
| CN109658372A (en) * | 2017-10-10 | 2019-04-19 | 凌云光技术集团有限责任公司 | A kind of image conformity appraisal procedure and device |
| CN109658372B (en) * | 2017-10-10 | 2021-01-26 | 凌云光技术股份有限公司 | Image uniformity evaluation method and device |
| CN107941241B (en) * | 2017-10-10 | 2021-04-06 | 天津大学 | Resolution board for aerial photogrammetry quality evaluation and use method thereof |
| WO2022048617A1 (en) * | 2020-09-04 | 2022-03-10 | 深圳光峰科技股份有限公司 | Method, device, and system for recognizing projection position, and storage medium |
| CN113376170A (en) * | 2021-06-16 | 2021-09-10 | 博众精工科技股份有限公司 | Calibration method and calibration block of product appearance detection equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104751458B (en) | 2017-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104751458A (en) | Calibration angle point detection method based on 180-degree rotating operator | |
| Chen et al. | High-accuracy multi-camera reconstruction enhanced by adaptive point cloud correction algorithm | |
| CN103345755B (en) | A kind of Chessboard angular point sub-pixel extraction based on Harris operator | |
| CN112082512B (en) | Calibration optimization method and device for phase measurement deflection technique and computer equipment | |
| WO2017092631A1 (en) | Image distortion correction method for fisheye image, and calibration method for fisheye camera | |
| CN108876749A (en) | A kind of lens distortion calibration method of robust | |
| CN111080662A (en) | Lane line extraction method and device and computer equipment | |
| CN114494045B (en) | Large spur gear geometric parameter measurement system and method based on machine vision | |
| CN104899888B (en) | A kind of image sub-pixel edge detection method based on Legendre squares | |
| CN108007388A (en) | A kind of turntable angle high precision online measuring method based on machine vision | |
| CN103824275B (en) | Saddle dots structure and the system and method for determining its information are searched in the picture | |
| CN112270719B (en) | Camera calibration method, device and system | |
| CN109859226A (en) | A kind of detection method of the X-comers sub-pix of figure segmentation | |
| CN106296811A (en) | A kind of object three-dimensional reconstruction method based on single light-field camera | |
| CN103389037B (en) | A kind of illumination diffraction optical element geometric techniques parameter detection device and method | |
| CN111105452B (en) | Binocular vision-based high-low resolution fusion stereo matching method | |
| CN113012234B (en) | High-precision camera calibration method based on plane transformation | |
| CN113077459B (en) | Image definition detection method and device, electronic equipment and storage medium | |
| CN104574312A (en) | Method and device of calculating center of circle for target image | |
| CN109974618A (en) | The overall calibration method of multisensor vision measurement system | |
| CN111462246B (en) | Equipment calibration method of structured light measurement system | |
| CN105354816B (en) | A kind of electronic units fix method and device | |
| CN107230212B (en) | Vision-based mobile phone size measuring method and system | |
| Jung et al. | A novel 2.5 D pattern for extrinsic calibration of tof and camera fusion system | |
| CN113658279B (en) | Camera internal reference and external reference estimation method, device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |