CN108267104A - A kind of axial workpiece radius size measuring method based on binocular vision - Google Patents
A kind of axial workpiece radius size measuring method based on binocular vision Download PDFInfo
- Publication number
- CN108267104A CN108267104A CN201810057642.3A CN201810057642A CN108267104A CN 108267104 A CN108267104 A CN 108267104A CN 201810057642 A CN201810057642 A CN 201810057642A CN 108267104 A CN108267104 A CN 108267104A
- Authority
- CN
- China
- Prior art keywords
- axial workpiece
- plane
- oab
- ocd
- images
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B21/00—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant
- G01B21/10—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring diameters
Abstract
The invention discloses a kind of axial workpiece radius size measuring methods based on binocular vision.The left and right cameras of binocular vision system is demarcated respectively, obtains internal reference, outer ginseng and the distortion parameter of left and right cameras, then calculates the projection matrix of left and right cameras respectively；Axial workpiece is placed in the public visual field of left and right cameras, is taken pictures by left and right cameras to axial workpiece and obtains the two images of left images respectively, to two images correction process；Left images after correction are carried out with processing and obtains respective axis profile；The radius of axial workpiece is obtained using the axis profile processing of left images.The method of the present invention can effectively ask for large range of spatial axes radius, high certainty of measurement, as a result reliably；It can test simultaneously to the central axes of spatial axes and radius size reconstructed results, reduce cost.
Description
Technical field
The invention belongs to advanced field of measuring technique, relate to a kind of axial workpiece radius size based on binocular vision and survey
Amount method is particularly suitable for the Algorithms of Robots Navigation System of non-contact industrial detection and view-based access control model.
Background technology
Axial workpiece is seen everywhere in commercial Application, and the radius size of axial workpiece is accurately measured in industrial detection
Have great importance.Especially in Modern Manufacturing Technology, Automated assembly technology gradually replaces manual skill and judgement
Power carries out complicated assembly manipulation to improve efficiency, ensures the quality and stability of product.During component assembly, axis hole dress
With being the working condition that is frequently encountered, when manipulator carries out crawl axial workpiece and is assembled, it is necessary to accurate to measure
Go out the radius size of axial workpiece, could rationally control the opening angle of mechanical hand and avoid colliding and generating between part
Defect, and then smoothly complete fittage.
With the development of machine vision technique, relevant research and application test are carried out both at home and abroad at present, by machine
Device vision system is introduced into axis hole dimensional measurement, but most of researchs at present concentrate on space circular hole and its elliptical aperture
It is relatively fewer to survey quantifier elimination for shaft part size for identification and parameter measurement.Cui Yan equality people have studied a kind of based on double
The measuring method of revolving body object space 3 d pose visually felt, this method can be in the case of without Feature Points Matching
Realize the measurement of revolving body 3 d pose, but due to uneven illumination in the high reflective and practical application of Axle Surface
Problem will lead to accuracy decline, and this kind of method using this kind of method in the sub-pix linear equation for extracting image planes busbar
The pose of revolving body can only be measured and radius size can not be measured.Sun et al. is in " shaft diameter measurement
A kind of axis class measuring method based on image procossing is proposed in a using adigital image " texts, it is this to be regarded based on monocular
The measuring method felt principle and be detached from solid geometry principle necessarily excessively relies on picture quality and its treatment effect, lacks good
Stability, and this method needs to carry out as priori using the axis class size of known diameter to reach higher precision
It re-scales, application scenario has certain restrictions.In addition, the target workpiece axis computational methods that Xi'an University of Technology Zhang Kai proposes
Due to being needed in image processing process using gray value threshold value and RGB color threshold value so that using common B/W camera
In the case of may None- identified, carry out calculating failure.
In conclusion it proposes a kind of without manpower intervention and method that axial workpiece radius size can be accurately measured
With larger application value.
Invention content
In view of the above-mentioned deficiencies in the prior art, it is an object of the present invention to propose a kind of axial workpiece radius based on binocular vision
Dimension measurement method can accurately calculate the central axes pose of space shaft-like workpiece and axis radius, and precision is high, speed is fast, if
The testing model of meter and experimental method are simple and practical, cost-effective, improve efficiency, are provided for the work of binocular vision proof of algorithm
A kind of new approaches.
The step of above-mentioned purpose of the present invention passes through following technical proposals is realized：
1) left and right cameras of binocular vision system is demarcated respectively according to Zhang Zhengyou standardizations, by left and right cameras
Binocular vision system is formed, obtains internal reference, outer ginseng and the distortion parameter of left and right cameras；According to internal reference obtained by calibrating and outer ginseng
Calculate the projection matrix of left and right cameras；
2) axial workpiece is placed in the public visual field of left and right cameras, axial workpiece is clapped by left and right cameras
According to the two images (left image and right image) for obtaining left images respectively, gaussian filtering, gray scale are carried out successively to two images
Conversion and threshold process, the radial distortion parameter matrix of the left and right cameras then obtained using step 1) carry out left images
Correction process；
3) left images after correction are carried out with processing and obtains respective axis profile；
4) radius for obtaining axial workpiece is handled using the axis profile of left images.
Inner parameter, distortion parameter and the projection matrix for the left and right cameras that the step 1) obtains include left video camera
Intrinsic Matrix Al, left video camera radial distortion parameter matrix Kl, left video camera projection matrix Ml, right video camera it is interior
Parameter matrix Ar, right video camera radial distortion parameter matrix KrWith the projection matrix M of right video camerar。
The step 3) is specially：Contour detecting is carried out, then will detect to the left images after correction and template image
Left images in all profiles respectively with template image detection obtain template contours matched, obtain left images in
Respectively with the matched profile of template contours, and be used as axis profile, i.e., profile corresponding with axial workpiece；
Have one and only one and the matched rectangle frame of axial workpiece in the template image.Rectangle frame and axial workpiece
Match on size and shape, specific implementation rectangle frame is placed in the centre of template image.
The step 4) is specially：
4.1) the axis profile in left images is approached with minimum rotation boundary rectangle, extraction obtains the length of each axis profile
Side, the long side of two axis profiles, which amounts to, in left images four long side ll1、ll2、lr1、lr2, ll1、ll2Left image is represented respectively
Two long sides of axis profile, lr1、lr2Two long sides of right image axis profile are represented respectively；
4.2) it is calculated using the following formula through left and right cameras center and four tangent with the axis profile of axial workpiece
Space plane SOAB、SOCD、S0′GH、S0′IJ, and then obtain the normal vector N of four space planesOAB、NOCD、N0′GH、N0′IJ：
ll1MlSOAB=0,ll2MlSOcD=0,lr1MrS0′GH=0,lr2MrS0′IJ=0
In formula, ll1、ll2Two long sides of left image axis profile, l are represented respectivelyr1、lr2Right image centre shaft wheel is represented respectively
Two wide long sides；Ml、MrThe projection matrix of left and right cameras is represented respectively；SOAB、SOCDIt is represented respectively through left camera center
And the two spaces plane tangent with two long sides of the axis profile of axial workpiece respectively, S0′GH、S0′IJIt represents to pass through right camera shooting respectively
Machine center and two spaces plane tangent with two long sides of the axis profile of axial workpiece respectively；
4.3) according to space plane SOAB、SOCDAnd its respective normal vector NOAB、NOCDCalculate space plane SOABIt is put down with space
Face SOCDBetween space angle-bisecting plane Sl, according to space plane S0′GH、S0′IJAnd its respective normal vector N0′GH、N0′IJIt calculates
Space plane S0′GHWith space plane S0′IJBetween space angle-bisecting plane Sr, take two spaces angle-bisecting plane SlWith SrFriendship
Central axes of the line as axial workpiece；
4.4) any point p (x on central axes are calculated using following formula0, y0, z0) respectively to four space plane SOAB、SOCD、
S0′GH、S0′IJVertical range li, take radius of the average value of four vertical ranges as required axial workpiece：
In formula, i=1, l when 2,3,4iRepresent p points to four space plane S respectivelyOAB、SOCD、S0＇GH、S0′IJDistance,
ai,bi,ci,diFour space plane S are represented respectivelyOAB、SOCD、S0′GH、S0′IJFirst, second, third, fourth system of corresponding equation
Number, x0、y0、z0For the three-dimensional coordinate at any point on central axes, common selection x0=0.
The present invention also proposed a kind of new testing model in implementing, and the model radius is it is known that and can to central axes progress
Depending on change, the fitting of this space line, reconstructed results and the method for the present invention acquired results are compared, verify this method radius ruler
The validity and accuracy of very little measurement result.
Compared with the conventional method, the beneficial effects of the invention are as follows：
Energy accurately measure of the invention obtains the radius of space shaft-like workpiece, can effectively ask for large range of space
Axis radius, high certainty of measurement, as a result reliably, method simple practical are cost-effective.And pass through the testing model of designed, designed to this
Method is verified, can be tested simultaneously to the central axes of spatial axes and radius size reconstructed results, be avoided high price
Monitor station reduces cost.
Meanwhile this method have the advantages that it is contactless, the occasion that can not be measured with conventional method have it is very high should
With value, it is particularly suitable for the Algorithms of Robots Navigation System of non-contact industrial detection and view-based access control model.
Description of the drawings
Fig. 1 is the method for the present invention principle schematic；
Fig. 2 is the method for the present invention flow diagram；
Fig. 3 is the new model verification mode schematic diagram of embodiment.
Specific embodiment
In order to better understand the present invention, make detailed retouch to technical scheme of the present invention with reference to the accompanying drawings and examples
It states.
It is Binocular Stereo Vision System as shown in Figure 1.OlXlYlZlAnd OrXrYrZrRespectively left and right cameras coordinate system,
olulvlAnd orurvrLeft images coordinate system respectively as unit of pixel, OwXwYwZwFor world coordinate system, wherein Z axis refers to
Camera coordinate system origin O to the leftl。
EF represents the central axes of axial workpiece in Fig. 1, and abcd represents wheel of the axial workpiece in left video camera imaging plane
Exterior feature, ghij represent profile of the axial workpiece in right video camera imaging plane.
The implementation steps of the method for the present invention are described in detail below：
1. pair left and right cameras utilizes Zhang Zhengyou standardizations (A Flexible New Technique for Camera
Calibration.Zhengyou Zhang, December, 2,1998.) the Intrinsic Matrix A of left video camera, is determinedl, it is left
The outer parameter matrix R of video cameralAnd Tl, left video camera radial distortion parameter matrix Kl, right video camera Intrinsic Matrix Ar、
The outer parameter matrix R of right video camerarAnd Tr, right video camera radial distortion parameter matrix Kr；And calculate the corresponding throwing of left video camera
Shadow matrix Ml, the corresponding projection matrix M of right video camerar.Wherein, the form of Intrinsic Matrix is：
Wherein, αlAnd βlThe effective focal length of left video camera x-axis direction and the focal length in y-axis direction, u are represented respectivelyolAnd volTable
Show the principal point coordinate of left video camera imaging plane, γlIt represents left camera coordinates axis tilt parameters, is ideally 0；αrWith
βrThe effective focal length of right video camera x-axis direction and the focal length in y-axis direction, u are represented respectivelyoAnd vorRepresent right video camera imaging plane
Principal point coordinate, γrIt represents right camera coordinates axis tilt parameters, is ideally 0.
Camera calibration is with result of calculation in this example：
Kl=[- 00114-00676-14004]
Kr=[- 00253-0.1129-03821]
2. binocular vision system is placed near axial workpiece to be detected, it is ensured that the axial workpiece is in left and right cameras
Public view field in the range of, while make that background is simple as possible, the axis direction of axial workpiece is made to be parallel to left and right camera shooting as far as possible
The baseline of the line of machine coordinate origin, i.e. binocular vision system.Axial workpiece is shot simultaneously using left and right cameras, so as to make
The image that a width includes axial workpiece image is obtained in left video camera, correspondingly, a width is also obtained in right video camera and includes axis class
The image of part image.Utilize the radial distortion parameter matrix K of left video cameralDistortion correction is carried out to left image, is free of
There is the left image of distortion information, be denoted as planel.Meanwhile utilize the radial distortion parameter matrix K of right video camerarTo right image into
Line distortion is corrected, and is obtained not containing the right image of distortion information, is denoted as planer。
Specifically correcting process is：To the image on the left side, if certain includes the picture point of distortion information as unit of pixel
Image coordinate system under coordinate beIts normalized image coordinate isThey are corresponding without distortion information
Image point coordinates be respectively (u, v) and (x, y).According to document (D.C.Brown, Close-range camera
calibration,Photogram-metric Engineering,37(8):855-866,1971), have：
Utilize changes in coordinates formula：
Wherein, KlFor the radial distortion parameter matrix of left video camera, AlFor the Intrinsic Matrix of video camera, can pass through
The monocular calibration of video camera determines.
It can obtain：
Since above equation is Nonlinear System of Equations, in order to simplify solution procedure, above-mentioned equation group can be approximately：
Distortion correction can be carried out to the picture point of each on left images, using two formulas above so as to not contained
The image plane of distortion informationl.For the image on the right, antidote is identical with the antidote of left image, no longer superfluous
It states.
3. the left image plane after pair correctionlWith right image planerAdaptive threshold is carried out by image binaryzation, specifically
Adaptive threshold using following methods calculate：
If variable t rounding numerical value (totally 256 gray values) according to this in the intensity value ranges (0~255), each value will be left
Image is divided into background and prospect two parts, while calculates following two formula：
U=w0*u0+w1*u1
G=w0*(u-u0)2+w1*(u-u1)2
Wherein, w0The ratio of entire image, u are accounted for for image background pixels point0For the average gray of image background pixels point,
w1The ratio of entire image, u are accounted for for foreground pixel point1For the average gray of foreground pixel point, u represents the average ash of entire image
Degree, result of calculation g represent the variance of foreground and background gray value of image.Compare 256 g values of gained, g value maximum variations per hours t
Value for optimal threshold, image binaryzation segmentation is carried out according to optimal threshold.
Then contour detecting is carried out, and all profiles detected are matched with template contours, it is similar to calculate matching
Score is spent, the profile of target axis in left images is obtained according to score height；Since the axis direction of axial workpiece is substantially parallel
In the line of left and right cameras coordinate origin, it is known that image of the axis on the imaging plane of left and right is similar to rectangle, therefore this literary grace
The axis profile matched in left images is approached with minimum rotation boundary rectangle, carries out that left image plane is calculatedlAnd right figure
As planerThe side l of 4 axis directions of upper axis profilel1、ll2、lr1、lr2, can also using the method for minimum rotation boundary rectangle
It makes up image outline caused by since Axle Surface bloom and uneven illumination are even and divides error.
The l of this example calculationl1、ll2、lr1、lr2It is worth and is：
ll1：[463.23004,-1358.9934,847808]
ll2：[463.23004,-1358.9935,292788.81]
lr1：[459.90479,-1310.1235,987763.63]
lr2：[459.90479,-1310.1235,432691.72]
4. according to left image planelWith right image planerThe profile side l of upper 4 axis directionsl1、ll2、lr1、lr2And
Left video camera projection matrix MlWith right video camera projection matrix MrCalculate by left and right cameras center and with space axial workpiece side
4 tangent plane S of faceOAB、SOCD、S0′GH、S0′IJ。
Pictures of the busbar AB and CD of spatial axes class part in left video camera imaging plane is ab and cd in known Fig. 1, female
Pictures of the line GH and IJ in right video camera imaging plane is gh and ij, then plane SOAB、SOCD、S0′GH、S0′IJUnder world coordinate system
Equation be：
ll1/MlSOAB=0, ll2MlSOCD=0, lr1/MrS0′GH=0,lr2MrS0′IJ=0
The normal vector N of 4 space planes is obtained simultaneouslyOAB、NOCD、N0′GH、N0′IJ。
It is calculated in this example：
SOAB：[1744445.6,-5117738.5,235642.83,0]
SOCD：[1744445.6,-5117738.5,-319376.47,0]
S0′GH：[1731923.3,-4933702.5,415048.59,-1.0369749e+008]
S0′IJ：[1731923.3,-4933702.5,-140023.33,-1.0369749e+008]
NOAB：[0.32232851,-0.94562596,0.043540712]
NOCD：[0.32207313,-0.94487667,-0.058965769]
S0′GH：[0.33018529,-0.94059366,0.07912761]
S0′IJ：[0.33110517,-0.94321412,-0.026769344]
5. by basic geometrical principle, by space plane SOAB、SOCDAnd its corresponding normal vector NOAB、NOCDIt can be calculated
SOAB、SOCDSpace angle-bisecting plane Sl；According to empty plane S0′GH、S0′IJAnd its corresponding normal vector N0′GH、N0′IJCalculate S0′GH、
S0′IJSpace angle-bisecting plane Sr；Then two bisecting plane SlWith SrIntersection be spatial axes central axes.
What is calculated in this example obtains：
Sl：[0.64440167,-1.8905027,-0.015425056,0]
Sr：[0.66129047,-1.8838078,0.052358266,-39.594223]
6. calculate p (x in any point on central axes respectively using following formula0, y0, z0) to 4 tangent plane SOAB、SOCD、S0′GH、
S0′IJVertical range, take four vertical ranges average value be required axial workpiece radius：
In formula, i=1, when 2,3,4, liRepresent p points to four space plane S respectivelyOAB、SOCD、S0′GH、S0′IJDistance,
ai,bi,ci,diFour space plane S are represented respectivelyOAB、SOCD、S0′GH、S0′IJThe coefficient of corresponding equation, x0、y0、z0For central axes
The three-dimensional coordinate at upper any point.
In this example, x is chosen0=0, the distance that p point 4 planes of distance are calculated is respectively：29.9645mm、
29.8936mm, 30.0243mm, 30.4308mm, average value 30.0783mm, error 0.26%.
The present embodiment finally designs a kind of testing model, as shown in figure 3, the modelling is I and II two parts.I portion
It is divided into one section of radius for 30mm, length is the optical axis of 180mm, and effect is to this section of optical axis by method proposed by the invention
Radius measurement is carried out, and compared with real radius, examines the accuracy of measuring method proposed by the invention.Part ii is one section
The a quarter of optical axis, length 100mm identical with part i light shaft coaxle and radius, this part of centering axis of model
It is visualized, by the fitting result to visualization central axes with method proposed by the invention in part i optical axis
Shaft centerline measurement result is compared, and can verify that the method for the present invention asks for the accuracy of central axes in the process.
To the fitting result of testing model visible line and measurement result of the present invention such as the following table 1 (space in the present embodiment
Straight line is expressed as the intersection of two spaces plane)：
Table 1
| Plane 1 | Plane 2 | Axis direction vector | |
| Fitting result | [0.6511,-1.8910,-0.0155,0] | [0.6673,-1.8333,0.0576,-39.9524] | [-0.1303,-0.0478,0.0345] |
| Algorithm is rebuild | [0.6544,-1.8905,-0.0154,0] | [0.6613,-1.8838,0.0524,-39.5942] | [-0.1280,-0.0439,0.0362] |
The reconstructed results of the present embodiment pair radius are with real radius comparing result：
Table 2
| Reconstructed value | Actual value | Error | Error ratio | |
| Axial workpiece | 30.0783mm | 30.0000mm | 0.0783mm | 0.26% |
It can thus be seen that the proposed axial workpiece radius measurement method based on binocular vision can reach compared with
High precision, the radius size to realize axial workpiece, which measures, realizes that automation provides guarantee.
Claims (5)
1. a kind of axial workpiece radius size measuring method based on binocular vision, it is characterised in that comprise the steps of：
1) left and right cameras of binocular vision system is demarcated respectively according to Zhang Zhengyou standardizations, obtains left and right cameras
Internal reference, outer ginseng and distortion parameter；The projection matrix of left and right cameras is calculated according to internal reference obtained by calibrating and outer ginseng；
2) axial workpiece is placed in the public visual field of left and right cameras, axial workpiece take pictures by left and right cameras point
Not Huo get left images two images, gaussian filtering, gradation conversion and threshold process, Ran Houli are carried out successively to two images
The radial distortion parameter matrix of the left and right cameras obtained with step 1) carries out correction process to left images；
3) left images after correction are carried out with processing and obtains respective axis profile；
4) radius for obtaining axial workpiece is handled using the axis profile of left images.
2. a kind of axial workpiece radius size measuring method based on binocular vision according to claim 1, feature exist
In：Inner parameter, distortion parameter and the projection matrix for the left and right cameras that the step 1) obtains include the interior of left video camera
Parameter matrix Al, left video camera radial distortion parameter matrix Kl, left video camera projection matrix Ml, right video camera intrinsic parameter
Matrix Ar, right video camera radial distortion parameter matrix KrWith the projection matrix M of right video camerar。
3. a kind of axial workpiece radius size measuring method based on binocular vision according to claim 1, feature exist
In：The step 3) is specially：Contour detecting, then the left and right that will be detected are carried out to the left images after correction and template image
The template contours that all profiles in image obtain respectively with template image detection are matched, obtain in left images respectively with
The matched profile of template contours, and it is used as axis profile.
4. a kind of axial workpiece radius size measuring method based on binocular vision according to claim 3, feature exist
In：Have one and only one and the matched rectangle frame of axial workpiece in the template image.
5. a kind of axial workpiece radius size measuring method based on binocular vision according to claim 1, feature exist
In：The step 4) is specially：
4.1) the axis profile in left images is approached with minimum rotation boundary rectangle, extraction obtains the long side of each axis profile, left
The long side of two axis profiles, which amounts to, in right image four long side ll1、ll2、lr1、lr2, ll1、ll2Left image centre shaft wheel is represented respectively
Two wide long sides, lr1、lr\Two long sides of right image axis profile are represented respectively；
4.2) it is calculated using the following formula through left and right cameras center and four spaces tangent with the axis profile of axial workpiece
Plane SOAB、SOCD、S0′GH、S0′IJ, and then obtain the normal vector N of four space planesOAB、NOCD、N0′GH、N0′IJ：
ll1MlSOAB=0, ll2MlSOCD=0, lr1MrS0′GH=0, lr2MrS0′IJ=0
In formula, ll1、ll2Two long sides of left image axis profile, l are represented respectivelyr1、lr2Right image axis profile is represented respectively
Two long sides；Ml、MrThe projection matrix of left and right cameras is represented respectively；SOAB、SOCDIt is represented respectively through left camera center and divided
The not two spaces plane tangent with two long sides of the axis profile of axial workpiece, S0 ＇ GH、S0 ＇ IJIt is represented respectively by right video camera
Heart difference and the two spaces plane tangent with two long sides of axis profile of axial workpiece；
4.3) according to space plane SOAB、SOCDAnd its respective normal vector NOAB、NOCDCalculate space plane SOABAnd space plane
SOCDBetween space angle-bisecting plane Sl, according to space plane S0′GH、S0′IJAnd its respective normal vector S0′GH、S0′IJIt calculates empty
Between plane S0′GHWith space plane S0′IJBetween space angle-bisecting plane Sr, take two spaces angle-bisecting plane SlWith SrIntersection
Central axes as axial workpiece；
4.4) any point p (x on central axes are calculated using following formula0, y0, z0) respectively to four space plane SOAB、SOCD、SO′GH、
SO′IJVertical range li, take radius of the average value of four vertical ranges as required axial workpiece：
In formula, i=1, l when 2,3,4iRepresent p points to four space plane S respectivelyOAB、SOCD、S0′GH、S0′IJDistance, ai,
bi,ci,diFour space plane S are represented respectivelyOAB、SOCD、S0′GH、S0′IJFirst, second, third, fourth coefficient of corresponding equation,
x0、y0、z0Three-dimensional coordinate for any point on central axes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810057642.3A CN108267104A (en) | 2018-01-22 | 2018-01-22 | A kind of axial workpiece radius size measuring method based on binocular vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810057642.3A CN108267104A (en) | 2018-01-22 | 2018-01-22 | A kind of axial workpiece radius size measuring method based on binocular vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108267104A true CN108267104A (en) | 2018-07-10 |
Family
ID=62776241
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810057642.3A Pending CN108267104A (en) | 2018-01-22 | 2018-01-22 | A kind of axial workpiece radius size measuring method based on binocular vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108267104A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110796695A (en) * | 2019-10-24 | 2020-02-14 | 深圳市瑞源祥橡塑制品有限公司 | Food cooking size obtaining method and device, computer equipment and storage medium |
| CN111445431A (en) * | 2018-12-28 | 2020-07-24 | Tcl集团股份有限公司 | Image segmentation method, terminal equipment and computer readable storage medium |
| CN114842091A (en) * | 2022-04-29 | 2022-08-02 | 广东工业大学 | Binocular egg size assembly line measuring method |
| CN116071365A (en) * | 2023-03-29 | 2023-05-05 | 季华实验室 | Part detection method, device, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020029127A1 (en) * | 2000-07-19 | 2002-03-07 | Asahi Kogaku Kogyo Kabushiki Kaisha | Method and apparatus for measuring 3-D information |
| CN1439091A (en) * | 2000-06-28 | 2003-08-27 | 捷装技术公司 | Method and apparatus for measuring vehicle wheel scrub radius |
| CN101093160A (en) * | 2007-07-12 | 2007-12-26 | 上海交通大学 | Method for measuring geometric parameters of spatial circle based on technique of binocular stereoscopic vision |
| CN104180763A (en) * | 2013-05-24 | 2014-12-03 | 南开大学 | Non-contact measurement apparatus of inner and outer diameters of large-diameter circular ring type component |
| CN106996748A (en) * | 2017-03-16 | 2017-08-01 | 南京工业大学 | A kind of wheel footpath measuring method based on binocular vision |
-
2018
- 2018-01-22 CN CN201810057642.3A patent/CN108267104A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1439091A (en) * | 2000-06-28 | 2003-08-27 | 捷装技术公司 | Method and apparatus for measuring vehicle wheel scrub radius |
| US20020029127A1 (en) * | 2000-07-19 | 2002-03-07 | Asahi Kogaku Kogyo Kabushiki Kaisha | Method and apparatus for measuring 3-D information |
| CN101093160A (en) * | 2007-07-12 | 2007-12-26 | 上海交通大学 | Method for measuring geometric parameters of spatial circle based on technique of binocular stereoscopic vision |
| CN104180763A (en) * | 2013-05-24 | 2014-12-03 | 南开大学 | Non-contact measurement apparatus of inner and outer diameters of large-diameter circular ring type component |
| CN106996748A (en) * | 2017-03-16 | 2017-08-01 | 南京工业大学 | A kind of wheel footpath measuring method based on binocular vision |
Non-Patent Citations (5)
| Title |
|---|
| 崔彦平等: "回转体目标空间三维姿态测量方法研究", 《传感技术学报》 * |
| 祁晓玲: "基于双目视觉的零件多尺寸测量研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 罗庆生等: "《仿生四足机器人技术》", 30 April 2016, 北京理工大学出版社 * |
| 莫德举等: "《数字图像处理》", 28 February 2015, 西安电子科技大学出版社 * |
| 龚声蓉等: "《数字图像处理与分析》", 31 May 2014, 清华大学出版社 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111445431A (en) * | 2018-12-28 | 2020-07-24 | Tcl集团股份有限公司 | Image segmentation method, terminal equipment and computer readable storage medium |
| CN111445431B (en) * | 2018-12-28 | 2023-10-20 | Tcl科技集团股份有限公司 | Image segmentation method, terminal equipment and computer readable storage medium |
| CN110796695A (en) * | 2019-10-24 | 2020-02-14 | 深圳市瑞源祥橡塑制品有限公司 | Food cooking size obtaining method and device, computer equipment and storage medium |
| CN110796695B (en) * | 2019-10-24 | 2022-04-05 | 深圳市瑞源祥橡塑制品有限公司 | Food cooking size obtaining method and device, computer equipment and storage medium |
| CN114842091A (en) * | 2022-04-29 | 2022-08-02 | 广东工业大学 | Binocular egg size assembly line measuring method |
| CN116071365A (en) * | 2023-03-29 | 2023-05-05 | 季华实验室 | Part detection method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108267104A (en) | A kind of axial workpiece radius size measuring method based on binocular vision | |
| CN108053450B (en) | High-precision binocular camera calibration method based on multiple constraints | |
| CN109827502B (en) | High-precision calibration method for line-structured light vision sensor for calibration point image compensation | |
| CN103471531B (en) | The online non-contact measurement method of axial workpiece linearity | |
| CN102353340B (en) | Cylinder-cover blank machining-size identifying method and device | |
| CN104835144B (en) | The method for solving camera intrinsic parameter using the picture and orthogonality of the centre of sphere of a ball | |
| CN102107179B (en) | Method for controlling single-layer leather gluing based on binocular vision | |
| CN103616016B (en) | Based on the pose vision measuring method of dotted line assemblage characteristic | |
| CN108335332A (en) | A kind of axial workpiece central axes measurement method based on binocular vision | |
| CN106650701B (en) | Binocular vision-based obstacle detection method and device in indoor shadow environment | |
| CN104913739B (en) | Visual measurement method and device for eccentricity of crank throw of crankshaft | |
| CN110378969B (en) | Convergent binocular camera calibration method based on 3D geometric constraint | |
| CN107588721A (en) | The measuring method and system of a kind of more sizes of part based on binocular vision | |
| CN112614098B (en) | Blank positioning and machining allowance analysis method based on augmented reality | |
| CN106996748A (en) | A kind of wheel footpath measuring method based on binocular vision | |
| CN104778716B (en) | Lorry compartment volume measuring method based on single image | |
| CN107220999A (en) | The research of workpiece circular arc Edge Feature Points matching process | |
| CN108154536A (en) | The camera calibration method of two dimensional surface iteration | |
| CN108917640A (en) | A kind of laser blind hole depth detection method and its system | |
| CN111008602B (en) | Scribing feature extraction method combining two-dimensional vision and three-dimensional vision for small-curvature thin-wall part | |
| CN106813569A (en) | A kind of automobile tire 3-D positioning method based on line-structured light | |
| CN109506629B (en) | Method for calibrating rotation center of underwater nuclear fuel assembly detection device | |
| CN113610929B (en) | Combined calibration method of camera and multi-line laser | |
| Wei et al. | Indoor mobile robot obstacle detection based on linear structured light vision system | |
| CN108180825A (en) | A kind of identification of cuboid object dimensional and localization method based on line-structured light |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180710 |
|
| WD01 | Invention patent application deemed withdrawn after publication |