CN103247053A - Accurate part positioning method based on binocular microscopy stereo vision - Google Patents
Accurate part positioning method based on binocular microscopy stereo vision Download PDFInfo
- Publication number
- CN103247053A CN103247053A CN2013101822210A CN201310182221A CN103247053A CN 103247053 A CN103247053 A CN 103247053A CN 2013101822210 A CN2013101822210 A CN 2013101822210A CN 201310182221 A CN201310182221 A CN 201310182221A CN 103247053 A CN103247053 A CN 103247053A
- Authority
- CN
- China
- Prior art keywords
- point
- coordinate
- image
- parameter
- video camera
- 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
Images
Abstract
The invention discloses an accurate part positioning method based on binocular microscopy stereo vision, which belongs to the technical field of computer visual measuring and relates to an accurate precision part positioning method based on the binocular microscopy stereo vision. A binocular microscopy stereo vision system is adopted, two CCD (charge coupled device) cameras are adopted to acquire the images of the measured parts, the image information in the to-be-measured area on the measured part is amplified by a stereo microscope, a checkerboard calibrating board is adopted to calibrate the two CCD cameras, and a Harris corner point detecting algorithm and a sub-pixel extracting algorithm are adopted to extract feature points. The extracted feature points are subjected to the primary matching and correcting of matching point pairs, and the feature point image coordinates are inputted to a calibrated system to obtain the space actual coordinates of the feature points. The accurate part positioning method based on the binocular microscopy stereo vision solves the measuring difficult problems generated by the small size of the to-be-measured area, high positioning demand, non-contact and the like. The accurate positioning of the precision part is well finished by adopting the non-contact measuring method of the binocular microscopy stereo vision.
Description
Technical field
The invention belongs to the computer vision measurement technical field, particularly a kind of accurate positioning method of the precision component based on the binocular microscopic stereovision.
Background technology
Technique of binocular stereoscopic vision is by the processing mode of simulating human eyes, has the ability of obtaining the object under test depth information, and then can obtain the spatial positional information of testee, the advantage that has nondestructive measurement simultaneously again and measure has in real time obtained using widely in all trades and professions.Binocular microscopic stereovision technology is based upon on technique of binocular stereoscopic vision and the Stereo microscope technology, by about two ccd video cameras catch the image of two light paths of stereo microscope respectively, similar angle is poor when measuring with binocular vision by the image existence that catches, and can realize the three-dimensional measurement to target.Can accurately obtain the spatial positional information of impact point in the advantages such as binocular microscopic stereovision technology is untouchable in assurance, real-time.It can be applicable to aspects such as three-dimensional high-precision servocontrol, high precision space orientation and high precision three-dimensional measurement.The setting accuracy on work of part directly affects the machining precision of part, whether and it is available directly to influence processing parts for the precision component bearing accuracy, simultaneously the processing location at the accurate ultra part often requires non-contacting characteristics, arises at the historic moment based on the accurate positioning method of the precision component of binocular microscopic stereovision.
The patent of invention CN102567989A " based on the space-location method of binocular stereo vision " of the precious equality people application of the soup of University Of Chongqing is loaded down with trivial details at the camera calibration process that space orientation exists, the not high problem of bearing accuracy has proposed a kind of new space-location method based on binocular stereo vision, this method is by demarcating homography matrix and the distortion factor of trying to achieve video camera to video camera, obtain the theoretical coordinate of impact point again by calibration result, the actual coordinate of last combining target point calculates the volume coordinate of impact point.Yet, because binocular microscopic stereovision system has more complicated light path, depth of focus is little, the distortion factor is more, the visual field is narrow, and the camera marking method that adopts at present extensively all is based upon and realizes under the big visual field, so said method can not solve the accurate location based on the precision component of binocular microscopic stereovision.
Summary of the invention
The technical barrier that the present invention will solve is the defective that overcomes prior art, invent a kind of accurate positioning method of the precision component based on the binocular microscopic stereovision, solve because the measurement difficult problem that target area to be measured is little, problems such as positioning accuracy request is high, noncontact produce.Employing realizes the accurate location of precision component based on the binocular microscopic stereovision, widened the range of application of traditional space-location method based on binocular stereo vision, and improved the precision of measuring, it is little to have solved part to be measured zone, the positioning accuracy request height, the problem that is difficult to measure.
The technical solution adopted in the present invention is based on the accurate positioning method of the precision component of binocular microscopic stereovision, it is characterized in that, adopt binocular microscopic stereovision system, two ccd video cameras 2,2 ' the picture position information of gathering tested part 4 about utilization, stereo microscope 3 amplifies the picture position information of to be measured regional 6 on the tested part 4; Image after the amplification passes in the industrial control computer 9 through image pick-up card, adopt the higher gridiron pattern scaling board of precision to about two ccd video cameras demarcate; Adopt Harris Corner Detection Algorithm and sub-pix extraction algorithm to carry out the extraction of unique point to be measured; Unique point to be measured after extracting is carried out just coupling and the right correction of match point; The unique point image coordinate that has matched is input to the space actual coordinate that obtains unique point in the good system of demarcation; The concrete steps of measuring method are as follows:
(1) demarcation of two ccd video cameras about
About the demarcation of two ccd video cameras comprise camera intrinsic parameter and external parameters of cameras; Camera intrinsic parameter comprises scale factor α, β, principal point coordinate u
0, v
0, and vertical factor γ; In calibration process, need obtain five intrinsic parameters of video camera earlier, on the basis of trying to achieve the intrinsic parameter matrix, find the solution the external parameters of cameras matrix; Scale factor is spatial point after through the translation rotational transform, its coordinate in camera coordinate system and the scaling relation of its coordinate in image coordinate system, and the present invention is to the demarcation employing Zhang Shi camera calibration method of scale factor; The relation formula that can set up image coordinate system and world coordinate system according to the pin-hole model of video camera is:
Wherein: α and β are exactly the scale factor that needs demarcation, X
w, Y
w, Z
wBe the three dimensional space coordinate of 1 P in the space, u, v are the image coordinate of P point on image, and R, t have represented rotation and the translation matrix of camera coordinate system with respect to world coordinate system; If make X '
w=(X
w, Y
w, Z
w)
T,
Z
c=s, then
Wherein, H is also referred to as homography matrix, and has
H=K[r
1,r
2,t] (3)
Each position calibration plate image is independent corresponding homography matrix all, makes H=[h
1, h
2, h
3] then can be pushed away by following formula:
[h
1 h
2 h
3]=λK[r
1 r
2 t] (4)
Wherein, λ is scale factor arbitrarily, and K camera intrinsic parameter matrix is because of r
1And r
2Be unit orthogonal vector, i.e. r
1 Tr
1=r
2 Tr
2=1 and r
1 Tr
2=0:
h
1K
-TK
-1h
2=0 (6)
According to formula 5 formula 6, calculate the video camera scale factor of stereo microscope left and right sides light path; At the principal point coordinate, adopt change multiplying power method that the principal point of video camera is demarcated; The coordinate of any 1 P in camera coordinate system is x in the hypothesis space
1, y
1, z
1, under the situation of not considering nonlinear distortion and image coordinate verticality, the coordinate of the plane of delineation projection of this point is:
U wherein
1, v
1Be the image coordinate of this point, r is arbitrary enlargement ratio, u
0, v
0It is the principal point coordinate; R cancellation with in the formula can get straight-line equation:
Namely under any enlargement ratio, put x
1, y
1, z
1Image coordinate all on same straight line, and this straight line necessarily passes through video camera principal point u
0, v
0In order to ask for video camera principal point u
0, v
0Selected 12 points that on image projection plane, do not overlap, make these 12 points under different enlargement ratios, 0.7,1,2,2.4,3,5,5.8,8 carry out projection respectively, utilize least square method that 12 straight lines that obtain are carried out match, and be video camera principal point u with the intersecting point coordinate that least square method is asked for 12 straight lines
0, v
0The imaging precision influence is little because vertical factor γ is, therefore at the initial parameter timing signal, γ is made as 0, obtains the γ occurrence by optimization means; At external parameters of cameras rotation matrix R and translation matrix t; Known by formula 2, can be in the hope of video camera rotation matrix R=[r after having demarcated intrinsic parameter matrix K and homography matrix H
1, r
2, r
3] and translation vector t as follows:
r
1=λK
-1h
1
r
2=λK
-1h
2 (9)
r
3=r
1×r
2
t=λK
-1h
3
After the principal parameter of two ccd video cameras, next step is the optimization to principal parameter and distortion parameter about tentatively having demarcated; In order to simplify the optimization parameter, the present invention adopts the hypercomplex number method with rotation matrix
In nine unknown numbers be reduced to four, formula is as follows:
Calculate new rotation matrix from formula (10):
Because hypercomplex number q
1, q
2, q
3, q
4Quadratic sum equal one, so the parameter predigesting to be optimized of rotation matrix is three; Utilize the optimization algorithm that video camera principal parameter and distortion parameter are carried out global optimization as optimizing initial value two ccd video camera calibrating parameters values about having tried to achieve; To about the optimization of two ccd video camera principal parameters and distortion parameter be based on the maximal possibility estimation criterion, for given n m * n that the scaling board picture provides calibration point coordinate, about the optimization problem of two ccd video camera parameters express by the minimization problem of following formula:
Wherein j refers to j video camera participating in calculating, and i refers to i the point that j video camera obtains, X
iBe the spatial point coordinate of input, y
iBe the image coordinate that space i is ordered, C
jBe changeless camera parameters vector, its length is n
0, p
jBe the camera parameters vector that needs adjustment, its length is n
1, n
0+ n
1Be all parameter vector length of video camera, m
i(C
j, p
j, X
i) be the imaging equation of video camera; The present invention adopts the optimization problem that minimizes that solves following formula based on the light beam method of adjustment of LM algorithm; Utilize the light beam method of adjustment write optimizer the time about will providing, also to provide respective image coordinates some and three dimensional space coordinate point form and these three-dimensional coordinate points the calibrating parameters initial value of two ccd video cameras, therefore in order accurately to obtain the angular coordinate of high-accuracy scaling board in the space, whole visual field, adopt the feeding of numerically-controlled machine z axle to drive the method that microscope vertically moves; And adopt laser interferometer (measuring accuracy can reach 0.1um) that the z axle is measured the actual range that the z axle moves, guarantee that the z of institute's acquisition angle point coordinate point is to realistic accuracy; In the light beam method of adjustment, the Jacobian matrix that the iteration factor of optimization algorithm is made up of the first order derivative of iteration parameter constitutes, and therefore need introduce the Jacobian matrix of adjusting parameter in the equation to be imaged in computation process;
The light beam method of adjustment is formed iteration factor with the Jacobian matrix of its parameter to be adjusted, and model parameter is adjusted, and obtains making image error S (θ) to reach minimum model parameter optimum solution.
(2) extraction of provincial characteristics point to be measured
What the present invention is directed to that the extraction of provincial characteristics point to be measured adopts is the Harris Corner Detection Algorithm; Harris has proposed to replace with Gaussian function the algorithm of square region compute gradient, if the pixel coordinate of impact point is x, and y, its displacement in x direction and y direction is respectively u and v, and then the grey scale change of this impact point is represented by following formula:
Order
Then:
The eigenvalue of compute matrix M
1, λ
2If two eigenwerts are all bigger, illustrate that the value on two orthogonal directionss of gradation of image autocorrelation function of impact point is all bigger, then this point is unique point; After by the Harris algorithm unique point being carried out just extracting; Adopt sub-pix angle point extraction algorithm to extract the higher angular coordinate of precision; For desirable angle point, near the shade of gray direction of the pixel it is all perpendicular to the line of this point with desirable angle point; These characteristics can be with equation expression:
Wherein
Be the shade of gray direction of desirable angle point,
Vector points to the coordinate of desirable angle point for image origin,
Vector points near the coordinate of the arbitrary marginal point of desirable angle point for image origin; In fact, owing to be subjected to the influence of picture noise, formula (10) is all non-vanishing usually, it can be considered as error e, namely
In the neighborhood centered by angle point, all to be pressed following formula calculate, sum of errors is E, then
Wherein, i is i point in the neighborhood; Asking the point that makes sum of errors E minimum so namely is other angular coordinate of sub-pixel.
(3) solid of unique point coupling
Adopt normalization crossover algorithm (NCC) to realize the first coupling of unique point, with ccd video camera 2 clap picture as reference base picture, and with unique point p
lCentered by, construct a N*N(representative image pixel) topography's piece as masterplate figure T, and make masterplate figure T in the certain limit that includes unique point of image S to be matched, travel through, the subgraph note that search template covers is S
I, j, i, j are the pixel coordinate of subgraph central point in matching image S, calculate masterplate figure T and search subgraph S by using normalization crossover algorithm (NCC)
I, jBetween the normalized crosscorrelation coefficient, algorithm is as follows:
M wherein, n represents the coordinate of each pixel, E (S
I, j) and E (T) be respectively search subgraph S
I, jAverage gray with masterplate figure T; Cross-correlation coefficient R (i, value j) is more big, and the matching degree of then searching for subgraph and template figure is more high; (i after threshold value j), selects unique point p to set cross-correlation coefficient R
lThe candidate matches point; Use the NCC algorithm also needing after the first coupling to carry out utilizing outer limit constraint and distance restraint to come the unique point of mating proofreading and correct; By the fundamental matrix F of two ccd video cameras about using 8 algorithms of normalization that Longguet-Higgins proposes to calculate when the camera calibration, according to outer polar curve theory, to benchmark image unique point p
l, the outer polar curve l of correspondence in image S to be matched
rCan be expressed as:
l
r=F·p
l (20)
Just the candidate feature point of coupling is as if polar curve l outside
rNear can determine further that then this candidate feature point is match point; Add up each candidate feature point unique point in the distance of other unique points and the benchmark image at last and put equidistant number num to other unique points; The candidate feature point of correspondence then is the correct match point of unique point in the benchmark image during num maximal value.
(4) three-dimensional coordinate asks for
At first calculate the image coordinate value that unique point extracts through the sub-pix algorithm in the binocular image, and roughly estimate the estimated value of unique point in world coordinate system; In optimizer with about the corresponding Jacobian matrixs of two ccd video camera parameters be made as zero, calculate the Jacobian matrix equation that embeds in the iteration factor part about volume coordinate x, y, z at optimizer simultaneously; With optimize good about two ccd video camera parameters and unique point dot image coordinate figure and world coordinates estimated value input beam method of adjustment optimizer, just can the three-dimensional coordinate of spatial point be optimized, obtain the three-dimensional space measurement value of unique point, thereby finish the location of asking for and finally realizing unique point of three-dimensional coordinate point.
The invention has the beneficial effects as follows and solved that binocular micro-vision timing signal lens are many, the visual field is narrow, the depth of field is little, have certain enlargement ratio and included the technical difficulty of more distortion factor, realize the high-precision calibrating of binocular microscopic stereovision, thereby finished the accurate location of precision component.
Description of drawings
Figure 1 shows that the mounted cast figure based on the precision component location of binocular microscopic stereovision.Wherein, 1-provide the led light source of illumination, 2-left ccd video camera, 2 '-right ccd video camera, 3-stereo microscope, 4-workpiece to be measured for binocular microscopic stereovision system; 5-numerical control rotating platform can incline; 6-zone to be measured; 7-accurate digital control displacement platform; 8-lathe bed; 9-industrial control computer.
Figure 2 shows that the process flow diagram based on the precision component locating measurement method of binocular microscopic stereovision.
Figure 3 shows that based on the demarcation of the binocular microscopic stereovision of light beam adjustment Algorithm and the process flow diagram of asking for of three-dimensional coordinate point.
Embodiment
Be described in detail the specific embodiment of the present invention below in conjunction with technical scheme and accompanying drawing.Accompanying drawing 1 is the mounted cast figure based on the precision component location of binocular microscopic stereovision.Two ccd video cameras 2,2 ' were gathered the positional information in zone to be measured in the workpiece for measurement about this device passed through, and by the image coordinate system set up and the relation between the world coordinate system, found the three dimensional space coordinate of point to be measured namely to realize precision positioning.Its Unit Installation mode is as follows: bed piece 8 places ground; Accurate digital control displacement platform 7 is installed together by guide rail and bed piece, and it can satisfy in the calibration experiment the high precision translational of gridiron pattern scaling board and angle rotation demand; Can incline numerical control rotating platform 5 by on the T-slot that is bolted to cast iron platform; Workpiece for measurement 4 is installed on the numerical control rotating platform that can incline by unit clamp, its to be measured regional 6 visual field that is positioned at binocular microscopic stereovision system; Stereo microscope 3 is installed on the bed piece by the microscope anchor clamps of special use; Led light source 1 is fixed on the anchor clamps, and anchor clamps are connected on the lathe bed by bolt; About two ccd video cameras 2 and 2 ' be installed on the stereo microscope by being threaded; About the image that collects of two ccd video cameras be delivered to by 1394 image pick-up cards respectively and carry out view data in the industrial control computer 9 and handle.
Accompanying drawing 1 is one embodiment of the present of invention, two ccd video cameras 2,2 ' the picture position information of taking object under test about employing, about two ccd video cameras adopt is Olympus DP26 video camera, image resolution ratio: 2448*1920, picking rate: 7fps, chip size: 2/3 inch.What stereo microscope 3 adopted is the SZX-16 research grade stereo microscope that Olympus is produced.Zoom ratio: 0.7-11.5, operating distance: 60mm gathers image maximum field of view: 12.5mm * 16.6mm, gathers minimum visual field: the 0.76mm * 1.02mm of image.For realizing the demarcation of binocular microscopic stereovision system, what demarcate required scaling board employing is the CG-050-T-0.5 type substrate of glass gridiron pattern scaling board of producing in Shenzhen Kechuang epoch.This type scaling board grid size is 0.5mm * 0.5mm, and gridiron pattern pattern integral width is 51mm * 51mm, and manufacturing accuracy is 1 μ m, can satisfy the needs that stereo microscope is demarcated.
Accompanying drawing 2 has been represented the process flow diagram based on the precision component locating measurement method of binocular microscopic stereovision, two ccd video cameras 2 about the main flow process of precision positioning comprises, 2 ' demarcation, the extraction of binocular image characteristic point, the coupling of binocular image characteristic point and correction, the three-dimensional coordinate of binocular image characteristic point is asked for.Wherein, about the demarcation of two ccd video cameras be utilize high-accuracy gridiron pattern scaling board realize to about two ccd video cameras 2,2 ' principal parameter and distortion parameter find the solution, mainly comprise adopt the Zhang Shi standardization to the demarcation of scale factor, adopt and become the multiplying power method and realize the demarcation of principal point coordinate and adopt the light beam method of adjustment to the optimization of principal parameter, distortion parameter; The unique point of binocular image utilizes Harris Corner Detection Algorithm and sub-pix extraction algorithm to extract; The gauge point of binocular image coupling is to be undertaken just by the gauge point to the binocular image that coupling and the right correction of unique point realize, finally realizes asking for of three-dimensional coordinate point by the light beam method of adjustment.
Accompanying drawing 3 is depicted as based on the demarcation of the binocular microscopic stereovision of light beam adjustment Algorithm and the process flow diagram that three-dimensional coordinate point is asked for, image under the different multiplying that obtains by shooting uses and becomes the multiplying power method and obtain the principal point coordinate, image by 30 secondary various angles uses the Zhang Shi standardization to obtain scale factor, and the outer parameter of two ccd video cameras about asking for by acquired intrinsic parameter, with intrinsic parameter and the initial value of outer parameter as the optimization of light beam method of adjustment, and use laser interferometer to obtain high-precision three-dimensional dot matrix as the constraint condition of optimizing, Jacobian matrix with parameter to be adjusted is formed iteration factor, by the parameter after the light beam method of adjustment acquisition optimization, parameter after optimizing is brought into obtains final imaging model in the imaging model, at last imaging model, the image coordinate of tested point and three-dimensional coordinate estimated value are input to the 3 d space coordinate of asking for tested point in the program of light beam method of adjustment.
The concrete steps of measuring method are as follows:
(1) demarcation of two ccd video cameras about
The present invention adopts the relatively-stationary mode of video camera, the method for video camera being demarcated with precision machined gridiron pattern scaling board.Zhang Shi camera calibration method requires different scaling board pictures that bigger angular relationship is arranged, and best angle is 45 ° usually; And we are limited to the depth of field factor of stereo microscope, when scaling board and surface level angle above 20 °, many fuzzy angle points can appear in the visual field, for the scale factor that obtains video camera that can be stable, and the experimentation that Zhang Shi demarcates summarized, find that the scaling board picture number is more many, the scaling board picture number that is parallel to each other is more few, just get over the stable scale factor of trying to achieve video camera of energy, therefore to about two ccd video cameras 2, the concrete steps of the demarcation of 2 ' scale factor are as follows: the scaling board rotation is divided into along horizontal rotational shaft and vertical axes rotation dual mode, 40 ° of the each rotations of vertical axes rotation, just there are nine horizontal angle positions in scaling board like this.Carry out horizontal rotational shaft in each horizontal angle position, scaling board horizontal rotational shaft position is divided into+10 °, 0 °, 10 ° of three positions are at scaling board image of each position photographs.Whole calibration process to scale factor is taken 54 scaling board pictures altogether.At the principal point coordinate, consider that principal point is actually the intersection point of optical axis and CCD imaging surface, and when the microscope enlargement ratio changes, the principal point coordinate that the position of optical axis is actually constant video camera just remains constant, under any enlargement ratio, point (x
1, y
1, z
1) image coordinate all on same straight line, and this straight line necessarily passes through video camera principal point (u
0, v
0); Like this, n the spatial point that the projection on the plane of delineation does not overlap by carry out projection under different enlargement ratios, just can form the straight line that the n bar intersects at same point; The coordinate of this intersection point is exactly video camera principal point coordinate.Adopt and become the demarcation concrete operations step that the multiplying power method realizes the principal point coordinate: determine 12 points that on image projection plane, do not overlap, make these 12 points under different enlargement ratios, 0.7,1,2,2.4,3,5,5.8,8 carry out projection respectively, utilize 12 straight lines that intersect at a point of least square method to obtaining, ask for the intersecting point coordinate value.Outer parameter matrix utilizes formula 7 to find the solution having demarcated intrinsic parameter and homography matrix.Adopt internally outer process of demarcating Parameter Optimization of light beam method of adjustment: import imaging equation, spatial point image coordinate observed value, parameter initial value to be optimized in optimizer, the output of program is the calibrating parameters value that can make after the minimum optimization of S (θ) output.
In order to verify the precision of calibration result, utilize calibrated model parameter, the three dimensions point that scaling board is provided carries out three-dimensional reconstruction, obtains the measured value of three dimensions point.Compare analysis by the actual value with measured value and three dimensions point coordinate, come the stated accuracy of evaluating.Calibration result shows that under 1 multiplying power, the average stated accuracy of x direction, y direction, z direction is respectively: 2.3um, 1.4um, 7.9um; Under 2 multiplying powers, the average stated accuracy of x direction, y direction, z direction is respectively: 1.5um, 1.2um, 5.4um; Under 5 multiplying powers, the average stated accuracy of x direction, y direction, z direction is respectively: 0.7um, 0.5um, 3.2um.Calibration result shows that calibrated model parameter has higher horizontal reconstruction precision and vertically rebuilds precision preferably.
(2) extraction of unique point
To about two ccd video cameras 2 and the 2 ' picture that collects adopt the Harris Corner Detection Algorithm to carry out unique point X by using
1, X
2X
nJust extract, the Harris Corner Detection Algorithm is by computation of characteristic values λ
1, λ
2If two eigenwerts are all bigger, illustrate that the value on two orthogonal directionss of gradation of image autocorrelation function of impact point is all bigger, then this point is unique point.With the unique point X after extracting
1, X
2X
nCentered by, calculate the sum of errors E of each unique point respectively, asking the point that makes sum of errors E minimum namely is other corner location of sub-pixel.In this way, just can obtain the sub-pix angular coordinate on the basis that the Harris angle point extracts, improve the extraction precision of unique point.
(3) coupling of unique point
Adopt normalization crossover algorithm (NCC) to realize the first coupling of unique point, according to algorithmic formula (19), with ccd video camera 2 clap picture as reference base picture, and with unique point p
lCentered by, to construct topography's piece of a N*N as masterplate figure T, and make masterplate figure T in the certain limit that includes unique point of image S to be matched, travel through, the subgraph note that search template covers is S
I, j, i, j are the pixel coordinate of subgraph central point in matching image S, calculate masterplate figure T and search subgraph S by using normalization crossover algorithm (NCC)
I, jBetween the normalized crosscorrelation coefficient.Cross-correlation coefficient R (i, value j) is more big, and the matching degree of then searching for subgraph and template figure is more high.(i after threshold value j), selects unique point p to set cross-correlation coefficient R
lThe candidate matches point.Use the NCC algorithm also needing after the first coupling to carry out utilizing outer polar curve constraint and distance restraint to come the unique point of mating proofreading and correct; By the fundamental matrix F of two ccd video cameras about using 8 algorithms of normalization that Longguet-Higgins proposes to calculate when the camera calibration, according to outer polar curve theory, to benchmark image unique point p
l, use formula (20) calculates the unique point p in the benchmark image
lOuter polar position in image to be matched, just the candidate feature point of coupling is if can determine further that then this candidate feature point is match point near the polar curve outside.Be that further to proofread and correct match point by distance restraint right at last.Adopt normalization crossover algorithm (NCC) to carry out the first coupling of unique point, the unique point that outer polar curve constraint and distance restraint are proofreaied and correct coupling is right, about the unique point of two images match to being respectively: X
l, X
r', X
2l, X
2r' ... X
3l, X
3r'.
(4) three-dimensional coordinate asks for
The light beam method of adjustment can also be carried out the optimization of three-dimensional coordinate point simultaneously except can being optimized camera parameters; The optimization of three-dimensional coordinate point herein namely is asking for of three-dimensional coordinate; It is as follows to ask for process: the corresponding Jacobian matrix of camera parameters in the optimizer is made as zero, calculates the Jacobian matrix equation that embeds in the iteration factor part about volume coordinate x, y, z at optimizer simultaneously; With optimize good about image coordinate and the world coordinates estimated value input beam method of adjustment optimizer of two ccd video camera parameters and spatial point, just can the three-dimensional coordinate of spatial point be optimized, obtain the measured value of three dimensions point, thereby finish asking for of three-dimensional coordinate point.
The present invention preferably resolves because the measurement difficult problem that target area to be measured is little, problems such as positioning accuracy request is high, noncontact produce.Employing has well been finished the accurate location of precision component based on the contactless measurement of binocular microscopic stereovision.
Claims (1)
1. part accurate positioning method based on the binocular microscopic stereovision, it is characterized in that, adopt binocular microscopic stereovision system, two ccd video cameras (2,2 ') are gathered the picture position information of tested part (4) about utilization, and stereo microscope (3) amplifies the picture position information in the zone to be measured (6) on the tested part (4); Image after the amplification passes in the industrial control computer (9) through image pick-up card, adopt the higher gridiron pattern scaling board of precision to about two ccd video cameras demarcate; Adopt Harris Corner Detection Algorithm and sub-pix extraction algorithm to carry out the extraction of unique point to be measured; Unique point to be measured after extracting is carried out just coupling and the right correction of match point; The unique point image coordinate that has matched is input to the space actual coordinate that obtains unique point in the good system of demarcation; The concrete steps of measuring method are as follows:
(1) demarcation of two ccd video cameras about
About the demarcation of two ccd video cameras comprise camera intrinsic parameter and external parameters of cameras; Camera intrinsic parameter comprises scale factor α, β, principal point coordinate u
0, v
0, and vertical factor γ; In calibration process, need obtain five intrinsic parameters of video camera earlier, on the basis of trying to achieve the intrinsic parameter matrix, find the solution the external parameters of cameras matrix; Scale factor is spatial point after through the translation rotational transform, its coordinate in camera coordinate system and the scaling relation of its coordinate in image coordinate system, and the present invention is to the demarcation employing Zhang Shi camera calibration method of scale factor; The relation formula that can set up image coordinate system and world coordinate system according to the pin-hole model of video camera is:
Wherein: α and β are exactly the scale factor that needs demarcation, X
w, Y
w, Z
wBe the three dimensional space coordinate of 1 P in the space, u, v are the image coordinate of P point on image, and R, t have represented rotation and the translation matrix of camera coordinate system with respect to world coordinate system; If make X '
w=(X
w, Y
w, Z
w)
T,
Then
Wherein, H is also referred to as homography matrix, and has
H=K[r
1,r
2,t] (3)
Each position calibration plate image is independent corresponding homography matrix all, makes H=[h
1, h
2, h
3] then can be pushed away by following formula:
[h
1 h
2 h
3]=λK[r
1 r
2 t] (4)
Wherein, λ is scale factor arbitrarily, and K camera intrinsic parameter matrix is because of r
1And r
2Be unit orthogonal vector, i.e. r
1 Tr
1=r
2 Tr
2=1 and r
1 Tr
2=0:
h
1K
-TK
-1h
2=0 (6)
According to formula (5) formula (6), calculate the video camera scale factor of stereo microscope left and right sides light path; At the principal point coordinate, adopt change multiplying power method that the principal point of video camera is demarcated; The coordinate of any 1 P in camera coordinate system is x in the hypothesis space
1, y
1, z
1, under the situation of not considering nonlinear distortion and image coordinate verticality, the coordinate of the plane of delineation projection of this point is:
U wherein
1, v
1Be the image coordinate of this point, r is arbitrary enlargement ratio, u
0, v
0It is the principal point coordinate; R cancellation with in the formula can get straight-line equation:
Namely under any enlargement ratio, put x
1, y
1, z
1Image coordinate all on same straight line, and this straight line necessarily passes through video camera principal point u
0, v
0In order to ask for video camera principal point u
0, v
0Selected 12 points that on image projection plane, do not overlap, make these 12 points under different enlargement ratios, 0.7,1,2,2.4,3,5,5.8,8 carry out projection respectively, utilize least square method that 12 straight lines that obtain are carried out match, and be video camera principal point u with the intersecting point coordinate that least square method is asked for 12 straight lines
0, v
0The imaging precision influence is little because vertical factor γ is, therefore at the initial parameter timing signal, γ is made as 0, obtains the γ occurrence by optimization means; At external parameters of cameras rotation matrix R and translation matrix t; Known by formula (2), can be in the hope of video camera rotation matrix R=[r after having demarcated intrinsic parameter matrix K and homography matrix H
1, r
2, r
3] and translation vector t as follows:
r
1=λK
-1h
1
r
2=λK
-1h
2 (9)
r
3=r
1×r
2
t=λK
-1h
3
After the principal parameter of two ccd video cameras, next step is the optimization to principal parameter and distortion parameter about tentatively having demarcated; In order to simplify the optimization parameter, the present invention adopts the hypercomplex number method with rotation matrix
In nine unknown numbers be reduced to four, formula is as follows:
Calculate new rotation matrix from formula (10):
Because hypercomplex number q
1, q
2, q
3, q
4Quadratic sum equal one, so the parameter predigesting to be optimized of rotation matrix is three; Utilize the optimization algorithm that video camera principal parameter and distortion parameter are carried out global optimization as optimizing initial value two ccd video camera calibrating parameters values about having tried to achieve; To about the optimization of two ccd video camera principal parameters and distortion parameter be based on the maximal possibility estimation criterion, for given n m * n that the scaling board picture provides calibration point coordinate, about the optimization problem of two ccd video camera parameters express by the minimization problem of following formula:
Wherein j refers to j video camera participating in calculating, and i refers to i the point that j video camera obtains, X
iBe the spatial point coordinate of input, y
iBe the image coordinate that space i is ordered, C
jBe changeless camera parameters vector, its length is n
0, p
jBe the camera parameters vector that needs adjustment, its length is n
1, n
0+ n
1Be all parameter vector length of video camera, m
i(C
j, p
j, X
i) be the imaging equation of video camera; The present invention adopts the optimization problem that minimizes that solves following formula based on the light beam method of adjustment of LM algorithm; Utilize the light beam method of adjustment write optimizer the time about will providing, also to provide respective image coordinates some and three dimensional space coordinate point form and these three-dimensional coordinate points the calibrating parameters initial value of two ccd video cameras, therefore in order accurately to obtain the angular coordinate of high-accuracy scaling board in the space, whole visual field, adopt the feeding of numerically-controlled machine z axle to drive the method that microscope vertically moves; And adopt laser interferometer (measuring accuracy can reach 0.1um) that the z axle is measured the actual range that the z axle moves, guarantee that the z of institute's acquisition angle point coordinate point is to realistic accuracy; In the light beam method of adjustment, the Jacobian matrix that the iteration factor of optimization algorithm is made up of the first order derivative of iteration parameter constitutes, and therefore need introduce the Jacobian matrix of adjusting parameter in the equation to be imaged in computation process;
The light beam method of adjustment is formed iteration factor with the Jacobian matrix of its parameter to be adjusted, and model parameter is adjusted, and obtains making image error S (θ) to reach minimum model parameter optimum solution;
(2) extraction of provincial characteristics point to be measured
What the present invention is directed to that the extraction of provincial characteristics point to be measured adopts is the Harris Corner Detection Algorithm; Harris has proposed to replace with Gaussian function the algorithm of square region compute gradient, if the pixel coordinate of impact point is x, and y, its displacement in x direction and y direction is respectively u and v, and then the grey scale change of this impact point is represented by following formula:
Order
Then:
The eigenvalue of compute matrix M
1, λ
2If two eigenwerts are all bigger, illustrate that the value on two orthogonal directionss of gradation of image autocorrelation function of impact point is all bigger, then this point is unique point; After by the Harris algorithm unique point being carried out just extracting; Adopt sub-pix angle point extraction algorithm to extract the higher angular coordinate of precision; For desirable angle point, near the shade of gray direction of the pixel it is all perpendicular to the line of this point with desirable angle point; These characteristics can be with equation expression:
Wherein
Be the shade of gray direction of desirable angle point,
Vector points to the coordinate of desirable angle point for image origin,
Vector points near the coordinate of the arbitrary marginal point of desirable angle point for image origin; In fact, owing to be subjected to the influence of picture noise, formula (10) is all non-vanishing usually, it can be considered as error e, namely
In the neighborhood centered by angle point, all to be pressed following formula calculate, sum of errors is E, then
Wherein, i is i point in the neighborhood; Asking the point that makes sum of errors E minimum so namely is other angular coordinate of sub-pixel;
(3) solid of unique point coupling
Adopt normalization crossover algorithm (NCC) to realize the first coupling of unique point, with ccd video camera 2 clap picture as reference base picture, and with unique point p
lCentered by, construct a N*N(representative image pixel) topography's piece as masterplate figure T, and make masterplate figure T in the certain limit that includes unique point of image S to be matched, travel through, the subgraph note that search template covers is S
I, j, i, j are the pixel coordinate of subgraph central point in matching image S, calculate masterplate figure T and search subgraph S by using normalization crossover algorithm (NCC)
I, jBetween the normalized crosscorrelation coefficient, algorithm is as follows:
M wherein, n represents the coordinate of each pixel, E (S
I, j) and E (T) be respectively search subgraph S
I, jAverage gray with masterplate figure T; Cross-correlation coefficient R (i, value j) is more big, and the matching degree of then searching for subgraph and template figure is more high; (i after threshold value j), selects unique point p to set cross-correlation coefficient R
lThe candidate matches point; Use the NCC algorithm also needing after the first coupling to carry out utilizing outer limit constraint and distance restraint to come the unique point of mating proofreading and correct; By the fundamental matrix F of two ccd video cameras about using 8 algorithms of normalization that Longguet-Higgins proposes to calculate when the camera calibration, according to outer polar curve theory, to benchmark image unique point p
l, the outer polar curve l of correspondence in image S to be matched
rCan be expressed as:
l
r=F·p
l (20)
Just the candidate feature point of coupling is as if polar curve l outside
rNear can determine further that then this candidate feature point is match point; Add up each candidate feature point unique point in the distance of other unique points and the benchmark image at last and put equidistant number num to other unique points; The candidate feature point of correspondence then is the correct match point of unique point in the benchmark image during num maximal value;
(4) three-dimensional coordinate asks for
At first calculate the image coordinate value that unique point extracts through the sub-pix algorithm in the binocular image, and roughly estimate the estimated value of unique point in world coordinate system; In optimizer with about the corresponding Jacobian matrixs of two ccd video camera parameters be made as zero, calculate the Jacobian matrix equation that embeds in the iteration factor part about volume coordinate x, y, z at optimizer simultaneously; With optimize good about two ccd video camera parameters and unique point dot image coordinate figure and world coordinates estimated value input beam method of adjustment optimizer, just can the three-dimensional coordinate of spatial point be optimized, obtain the three-dimensional space measurement value of unique point, thereby finish the location of asking for and finally realizing unique point of three-dimensional coordinate point.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310182221.0A CN103247053B (en) | 2013-05-16 | 2013-05-16 | Based on the part accurate positioning method of binocular microscopy stereo vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310182221.0A CN103247053B (en) | 2013-05-16 | 2013-05-16 | Based on the part accurate positioning method of binocular microscopy stereo vision |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103247053A true CN103247053A (en) | 2013-08-14 |
CN103247053B CN103247053B (en) | 2015-10-14 |
Family
ID=48926558
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310182221.0A Active CN103247053B (en) | 2013-05-16 | 2013-05-16 | Based on the part accurate positioning method of binocular microscopy stereo vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103247053B (en) |
Cited By (58)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103529655A (en) * | 2013-10-29 | 2014-01-22 | 天津芯硕精密机械有限公司 | Method and system for calibrating linearity of displacement platform |
CN103630072A (en) * | 2013-10-25 | 2014-03-12 | 大连理工大学 | Layout optimization method for camera in binocular vision measuring system |
CN103824298A (en) * | 2014-03-10 | 2014-05-28 | 北京理工大学 | Intelligent body visual and three-dimensional positioning method based on double cameras and intelligent body visual and three-dimensional positioning device based on double cameras |
CN103996015A (en) * | 2013-09-26 | 2014-08-20 | 深圳市云立方信息科技有限公司 | Method and apparatus for 3D image identification |
CN104236478A (en) * | 2014-09-19 | 2014-12-24 | 山东交通学院 | Automatic vehicle overall size measuring system and method based on vision |
CN104318050A (en) * | 2014-09-03 | 2015-01-28 | 大连理工大学 | Energy control method for constantly removing numerical control laser processing materials |
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 |
CN104406594A (en) * | 2014-12-09 | 2015-03-11 | 上海新跃仪表厂 | Measuring algorithm for relative position and posture of rendezvous and docking spacecraft |
CN104751452A (en) * | 2015-03-08 | 2015-07-01 | 大连理工大学 | Monocular camera calibration method based on any known movement |
CN104897062A (en) * | 2015-06-26 | 2015-09-09 | 北方工业大学 | Visual measurement method and device for shape and position deviation of part non-coplanar parallel holes |
CN105138999A (en) * | 2015-09-16 | 2015-12-09 | 三峡大学 | Shadow-based night object single-camera locating device and method |
CN105180806A (en) * | 2015-08-25 | 2015-12-23 | 大连理工大学 | Trans-scale geometrical parameter measurement method based on microscopic visual sense |
CN105258710A (en) * | 2015-09-12 | 2016-01-20 | 长春理工大学 | High-precision camera principal point calibration method |
CN106023146A (en) * | 2016-05-06 | 2016-10-12 | 北京信息科技大学 | Field-correlation single-side self-calibration light beam adjustment method for photogrammetry |
CN106041937A (en) * | 2016-08-16 | 2016-10-26 | 河南埃尔森智能科技有限公司 | Control method of manipulator grabbing control system based on binocular stereoscopic vision |
WO2017008516A1 (en) * | 2015-07-15 | 2017-01-19 | 华为技术有限公司 | Two-camera relative position calculation system, device and apparatus |
CN106780632A (en) * | 2017-01-24 | 2017-05-31 | 长沙全度影像科技有限公司 | A kind of demarcation target group demarcated target and demarcated for four road fish eye lenses |
CN106887023A (en) * | 2017-02-21 | 2017-06-23 | 成都通甲优博科技有限责任公司 | For scaling board and its scaling method and calibration system that binocular camera is demarcated |
CN106952262A (en) * | 2017-04-25 | 2017-07-14 | 大连理工大学 | A kind of deck of boat analysis of Machining method based on stereoscopic vision |
CN107303204A (en) * | 2016-04-21 | 2017-10-31 | 北京大学口腔医学院 | A kind of hand held oral three-dimensional scanner and control method |
CN107358632A (en) * | 2017-06-29 | 2017-11-17 | 西北工业大学 | Underwater Camera scaling method applied to underwater binocular stereo vision |
CN107391631A (en) * | 2017-07-10 | 2017-11-24 | 国家电网公司 | A kind of electric transmission line channel solid space monitoring and fast ranging method |
CN107726975A (en) * | 2017-09-20 | 2018-02-23 | 大连理工大学 | A kind of error analysis method of view-based access control model stitching measure |
CN108010085A (en) * | 2017-11-30 | 2018-05-08 | 西南科技大学 | Target identification method based on binocular Visible Light Camera Yu thermal infrared camera |
CN108765495A (en) * | 2018-05-22 | 2018-11-06 | 山东大学 | A kind of quick calibrating method and system based on binocular vision detection technology |
CN108961419A (en) * | 2018-06-15 | 2018-12-07 | 重庆大学 | The microscopic field of view spatial digitalized method and system of the micro-vision system of microassembly system |
CN108972557A (en) * | 2018-08-16 | 2018-12-11 | 中国科学院自动化研究所 | Micro- part pose automatic alignment apparatus and its method |
CN109029442A (en) * | 2018-06-07 | 2018-12-18 | 武汉理工大学 | Based on the matched positioning device of multi-angle of view and method |
CN109074663A (en) * | 2018-07-19 | 2018-12-21 | 深圳前海达闼云端智能科技有限公司 | Object volume measuring method, related device and computer readable storage medium |
CN109261528A (en) * | 2018-09-03 | 2019-01-25 | 广州铁路职业技术学院(广州铁路机械学校) | Express delivery sorting method and device based on binocular vision |
TWI650530B (en) * | 2018-01-22 | 2019-02-11 | 國立臺灣科技大學 | Measure system and method thereof |
CN109522935A (en) * | 2018-10-22 | 2019-03-26 | 易思维(杭州)科技有限公司 | The method that the calibration result of a kind of pair of two CCD camera measure system is evaluated |
CN109579871A (en) * | 2018-11-14 | 2019-04-05 | 中国直升机设计研究所 | Inertial navigation components installation error detection method and device based on computer vision |
CN109600599A (en) * | 2018-10-29 | 2019-04-09 | 上海神添实业有限公司 | A kind of the stereopsis device and its processing method of quickly positioning target |
CN109781002A (en) * | 2019-01-31 | 2019-05-21 | 浙江省计量科学研究院 | A kind of lathe holoaxial journey accurate positioning method based on machine vision |
CN110060304A (en) * | 2019-03-31 | 2019-07-26 | 南京航空航天大学 | A kind of organism three-dimensional information acquisition method |
CN110136248A (en) * | 2019-05-20 | 2019-08-16 | 湘潭大学 | A kind of case of transmission three-dimensional reconstruction apparatus and method based on binocular stereo vision |
CN110516350A (en) * | 2019-08-25 | 2019-11-29 | 大连理工大学 | A kind of ERS point tolerance modification method based on anisotropy weighting |
CN110820447A (en) * | 2019-11-22 | 2020-02-21 | 武汉纵横天地空间信息技术有限公司 | Binocular vision-based track geometric state measuring system and measuring method thereof |
CN110866954A (en) * | 2019-11-13 | 2020-03-06 | 中山大学 | Method for measuring high-precision attitude of bullet target under length constraint |
CN111199542A (en) * | 2019-12-30 | 2020-05-26 | 季华实验室 | Accurate positioning method for tooling plate |
CN111445537A (en) * | 2020-06-18 | 2020-07-24 | 浙江中控技术股份有限公司 | Calibration method and system of camera |
CN111612731A (en) * | 2020-04-01 | 2020-09-01 | 中国科学院上海微系统与信息技术研究所 | Measuring method, device, system and medium based on binocular microscopic vision |
CN111664798A (en) * | 2020-04-29 | 2020-09-15 | 深圳奥比中光科技有限公司 | Depth imaging method and device and computer readable storage medium |
CN112002016A (en) * | 2020-08-28 | 2020-11-27 | 中国科学院自动化研究所 | Continuous curved surface reconstruction method, system and device based on binocular vision |
CN112037281A (en) * | 2020-08-18 | 2020-12-04 | 重庆大学 | Visual system for guiding automatic hair follicle harvesting machine |
CN112161997A (en) * | 2020-09-28 | 2021-01-01 | 南京工程学院 | Online precise visual measurement method and system for three-dimensional geometric dimension of semiconductor chip pin |
CN112304220A (en) * | 2020-10-26 | 2021-02-02 | 中国人民解放军陆军装甲兵学院 | Binocular camera coordinate system registration method based on measurement adjustment |
CN112326206A (en) * | 2020-11-06 | 2021-02-05 | 歌尔光学科技有限公司 | AR module binocular fusion detection device and detection method |
CN112720469A (en) * | 2020-12-18 | 2021-04-30 | 北京工业大学 | Zero point calibration method for three-axis translational motion system by microscopic stereo vision |
CN113028986A (en) * | 2021-03-03 | 2021-06-25 | 北京科技大学 | Volume measuring device and mass measuring system |
CN113050264A (en) * | 2021-04-23 | 2021-06-29 | 南京甬宁科学仪器有限公司 | Microscope objective automatic identification system |
CN113112548A (en) * | 2020-12-23 | 2021-07-13 | 合肥工业大学 | Quick calibration method for internal and external parameters of binocular camera based on coded three-dimensional target |
CN113177977A (en) * | 2021-04-09 | 2021-07-27 | 上海工程技术大学 | Non-contact three-dimensional human body size measuring method |
CN113284111A (en) * | 2021-05-26 | 2021-08-20 | 汕头大学 | Hair follicle region positioning method and system based on binocular stereo vision |
CN115075857A (en) * | 2022-08-18 | 2022-09-20 | 中煤科工开采研究院有限公司 | Quantitative pushing method and system for hydraulic support |
CN115797461B (en) * | 2022-11-11 | 2023-06-06 | 中国消防救援学院 | Flame space positioning system calibration and correction method based on binocular vision |
CN116735613A (en) * | 2023-08-16 | 2023-09-12 | 昆山龙雨智能科技有限公司 | CCD camera-based product positioning and measuring system and use method |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100755450B1 (en) * | 2006-07-04 | 2007-09-04 | 중앙대학교 산학협력단 | 3d reconstruction apparatus and method using the planar homography |
CN101876532A (en) * | 2010-05-25 | 2010-11-03 | 大连理工大学 | Camera on-field calibration method in measuring system |
-
2013
- 2013-05-16 CN CN201310182221.0A patent/CN103247053B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100755450B1 (en) * | 2006-07-04 | 2007-09-04 | 중앙대학교 산학협력단 | 3d reconstruction apparatus and method using the planar homography |
CN101876532A (en) * | 2010-05-25 | 2010-11-03 | 大连理工大学 | Camera on-field calibration method in measuring system |
Non-Patent Citations (2)
Title |
---|
ZHENGYOU ZHANG: "A Flexible New Technique for Camera Calibration", 《PATTERN ANALYSIS AND MACHINE INTELLIGENCE》 * |
王跃宗: "SLM显微立体视觉量化和三维数据重构研究", 《中国博士学位论文全文数据库工程科技Ⅱ辑》 * |
Cited By (86)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103996015A (en) * | 2013-09-26 | 2014-08-20 | 深圳市云立方信息科技有限公司 | Method and apparatus for 3D image identification |
CN103996015B (en) * | 2013-09-26 | 2016-09-07 | 深圳市云立方信息科技有限公司 | A kind of method and device to 3D rendering identification |
CN103630072B (en) * | 2013-10-25 | 2016-01-13 | 大连理工大学 | The layout optimization method of video camera in two CCD camera measure system |
CN103630072A (en) * | 2013-10-25 | 2014-03-12 | 大连理工大学 | Layout optimization method for camera in binocular vision measuring system |
CN103529655A (en) * | 2013-10-29 | 2014-01-22 | 天津芯硕精密机械有限公司 | Method and system for calibrating linearity of displacement platform |
CN103824298A (en) * | 2014-03-10 | 2014-05-28 | 北京理工大学 | Intelligent body visual and three-dimensional positioning method based on double cameras and intelligent body visual and three-dimensional positioning device based on double cameras |
CN103824298B (en) * | 2014-03-10 | 2016-09-28 | 北京理工大学 | A kind of intelligent body 3 D visual positioner based on twin camera and method |
CN104318050A (en) * | 2014-09-03 | 2015-01-28 | 大连理工大学 | Energy control method for constantly removing numerical control laser processing materials |
CN104318050B (en) * | 2014-09-03 | 2017-05-03 | 大连理工大学 | Energy control method for constantly removing numerical control laser processing materials |
CN104236478A (en) * | 2014-09-19 | 2014-12-24 | 山东交通学院 | Automatic vehicle overall size measuring system and method based on vision |
CN104236478B (en) * | 2014-09-19 | 2017-01-18 | 山东交通学院 | Automatic vehicle overall size measuring system and method based on vision |
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 |
CN104406594A (en) * | 2014-12-09 | 2015-03-11 | 上海新跃仪表厂 | Measuring algorithm for relative position and posture of rendezvous and docking spacecraft |
CN104406594B (en) * | 2014-12-09 | 2017-06-06 | 上海新跃仪表厂 | The Measurement Algorithm of spacecrafts rendezvous spacecraft relative pose |
CN104751452A (en) * | 2015-03-08 | 2015-07-01 | 大连理工大学 | Monocular camera calibration method based on any known movement |
CN104897062A (en) * | 2015-06-26 | 2015-09-09 | 北方工业大学 | Visual measurement method and device for shape and position deviation of part non-coplanar parallel holes |
CN104897062B (en) * | 2015-06-26 | 2017-10-27 | 北方工业大学 | Visual measurement method and device for shape and position deviation of part non-coplanar parallel holes |
WO2017008516A1 (en) * | 2015-07-15 | 2017-01-19 | 华为技术有限公司 | Two-camera relative position calculation system, device and apparatus |
US10559090B2 (en) | 2015-07-15 | 2020-02-11 | Huawei Technologies Co., Ltd. | Method and apparatus for calculating dual-camera relative position, and device |
CN105180806A (en) * | 2015-08-25 | 2015-12-23 | 大连理工大学 | Trans-scale geometrical parameter measurement method based on microscopic visual sense |
CN105258710A (en) * | 2015-09-12 | 2016-01-20 | 长春理工大学 | High-precision camera principal point calibration method |
CN105258710B (en) * | 2015-09-12 | 2017-12-29 | 长春理工大学 | A kind of high-precision principal point for camera scaling method |
CN105138999B (en) * | 2015-09-16 | 2019-03-15 | 三峡大学 | Night object monocular positioning device and method based on shade |
CN105138999A (en) * | 2015-09-16 | 2015-12-09 | 三峡大学 | Shadow-based night object single-camera locating device and method |
CN107303204B (en) * | 2016-04-21 | 2019-12-27 | 北京大学口腔医学院 | Handheld oral three-dimensional scanning device and control method |
CN107303204A (en) * | 2016-04-21 | 2017-10-31 | 北京大学口腔医学院 | A kind of hand held oral three-dimensional scanner and control method |
CN106023146A (en) * | 2016-05-06 | 2016-10-12 | 北京信息科技大学 | Field-correlation single-side self-calibration light beam adjustment method for photogrammetry |
CN106023146B (en) * | 2016-05-06 | 2018-10-30 | 北京信息科技大学 | For the related unilateral self-calibration bundle adjustment method in field in photogrammetric |
CN106041937A (en) * | 2016-08-16 | 2016-10-26 | 河南埃尔森智能科技有限公司 | Control method of manipulator grabbing control system based on binocular stereoscopic vision |
CN106780632A (en) * | 2017-01-24 | 2017-05-31 | 长沙全度影像科技有限公司 | A kind of demarcation target group demarcated target and demarcated for four road fish eye lenses |
CN106887023A (en) * | 2017-02-21 | 2017-06-23 | 成都通甲优博科技有限责任公司 | For scaling board and its scaling method and calibration system that binocular camera is demarcated |
CN106952262A (en) * | 2017-04-25 | 2017-07-14 | 大连理工大学 | A kind of deck of boat analysis of Machining method based on stereoscopic vision |
CN106952262B (en) * | 2017-04-25 | 2022-09-20 | 大连理工大学 | Ship plate machining precision analysis method based on stereoscopic vision |
CN107358632A (en) * | 2017-06-29 | 2017-11-17 | 西北工业大学 | Underwater Camera scaling method applied to underwater binocular stereo vision |
CN107391631A (en) * | 2017-07-10 | 2017-11-24 | 国家电网公司 | A kind of electric transmission line channel solid space monitoring and fast ranging method |
CN107726975A (en) * | 2017-09-20 | 2018-02-23 | 大连理工大学 | A kind of error analysis method of view-based access control model stitching measure |
CN107726975B (en) * | 2017-09-20 | 2019-05-14 | 大连理工大学 | A kind of error analysis method of view-based access control model stitching measure |
CN108010085B (en) * | 2017-11-30 | 2019-12-31 | 西南科技大学 | Target identification method based on binocular visible light camera and thermal infrared camera |
CN108010085A (en) * | 2017-11-30 | 2018-05-08 | 西南科技大学 | Target identification method based on binocular Visible Light Camera Yu thermal infrared camera |
TWI650530B (en) * | 2018-01-22 | 2019-02-11 | 國立臺灣科技大學 | Measure system and method thereof |
CN108765495B (en) * | 2018-05-22 | 2021-04-30 | 山东大学 | Rapid calibration method and system based on binocular vision detection technology |
CN108765495A (en) * | 2018-05-22 | 2018-11-06 | 山东大学 | A kind of quick calibrating method and system based on binocular vision detection technology |
CN109029442A (en) * | 2018-06-07 | 2018-12-18 | 武汉理工大学 | Based on the matched positioning device of multi-angle of view and method |
CN108961419B (en) * | 2018-06-15 | 2023-06-06 | 重庆大学 | Microscopic visual field space digitizing method and system for microscopic visual system of micro assembly system |
CN108961419A (en) * | 2018-06-15 | 2018-12-07 | 重庆大学 | The microscopic field of view spatial digitalized method and system of the micro-vision system of microassembly system |
WO2020014913A1 (en) * | 2018-07-19 | 2020-01-23 | 深圳前海达闼云端智能科技有限公司 | Method for measuring volume of object, related device, and computer readable storage medium |
CN109074663A (en) * | 2018-07-19 | 2018-12-21 | 深圳前海达闼云端智能科技有限公司 | Object volume measuring method, related device and computer readable storage medium |
CN108972557A (en) * | 2018-08-16 | 2018-12-11 | 中国科学院自动化研究所 | Micro- part pose automatic alignment apparatus and its method |
CN109261528A (en) * | 2018-09-03 | 2019-01-25 | 广州铁路职业技术学院(广州铁路机械学校) | Express delivery sorting method and device based on binocular vision |
CN109522935A (en) * | 2018-10-22 | 2019-03-26 | 易思维(杭州)科技有限公司 | The method that the calibration result of a kind of pair of two CCD camera measure system is evaluated |
CN109522935B (en) * | 2018-10-22 | 2021-07-02 | 易思维(杭州)科技有限公司 | Method for evaluating calibration result of binocular vision measurement system |
CN109600599A (en) * | 2018-10-29 | 2019-04-09 | 上海神添实业有限公司 | A kind of the stereopsis device and its processing method of quickly positioning target |
CN109579871A (en) * | 2018-11-14 | 2019-04-05 | 中国直升机设计研究所 | Inertial navigation components installation error detection method and device based on computer vision |
CN109781002A (en) * | 2019-01-31 | 2019-05-21 | 浙江省计量科学研究院 | A kind of lathe holoaxial journey accurate positioning method based on machine vision |
CN110060304A (en) * | 2019-03-31 | 2019-07-26 | 南京航空航天大学 | A kind of organism three-dimensional information acquisition method |
CN110136248A (en) * | 2019-05-20 | 2019-08-16 | 湘潭大学 | A kind of case of transmission three-dimensional reconstruction apparatus and method based on binocular stereo vision |
CN110516350A (en) * | 2019-08-25 | 2019-11-29 | 大连理工大学 | A kind of ERS point tolerance modification method based on anisotropy weighting |
CN110866954B (en) * | 2019-11-13 | 2022-04-22 | 中山大学 | Method for measuring high-precision attitude of bullet target under length constraint |
CN110866954A (en) * | 2019-11-13 | 2020-03-06 | 中山大学 | Method for measuring high-precision attitude of bullet target under length constraint |
CN110820447A (en) * | 2019-11-22 | 2020-02-21 | 武汉纵横天地空间信息技术有限公司 | Binocular vision-based track geometric state measuring system and measuring method thereof |
CN111199542A (en) * | 2019-12-30 | 2020-05-26 | 季华实验室 | Accurate positioning method for tooling plate |
CN111612731A (en) * | 2020-04-01 | 2020-09-01 | 中国科学院上海微系统与信息技术研究所 | Measuring method, device, system and medium based on binocular microscopic vision |
CN111612731B (en) * | 2020-04-01 | 2021-04-02 | 中国科学院上海微系统与信息技术研究所 | Measuring method, device, system and medium based on binocular microscopic vision |
CN111664798B (en) * | 2020-04-29 | 2022-08-02 | 奥比中光科技集团股份有限公司 | Depth imaging method and device and computer readable storage medium |
CN111664798A (en) * | 2020-04-29 | 2020-09-15 | 深圳奥比中光科技有限公司 | Depth imaging method and device and computer readable storage medium |
CN111445537A (en) * | 2020-06-18 | 2020-07-24 | 浙江中控技术股份有限公司 | Calibration method and system of camera |
CN112037281B (en) * | 2020-08-18 | 2022-09-23 | 重庆大学 | Visual system for guiding automatic hair follicle harvesting machine |
CN112037281A (en) * | 2020-08-18 | 2020-12-04 | 重庆大学 | Visual system for guiding automatic hair follicle harvesting machine |
CN112002016B (en) * | 2020-08-28 | 2024-01-26 | 中国科学院自动化研究所 | Continuous curved surface reconstruction method, system and device based on binocular vision |
CN112002016A (en) * | 2020-08-28 | 2020-11-27 | 中国科学院自动化研究所 | Continuous curved surface reconstruction method, system and device based on binocular vision |
CN112161997A (en) * | 2020-09-28 | 2021-01-01 | 南京工程学院 | Online precise visual measurement method and system for three-dimensional geometric dimension of semiconductor chip pin |
CN112304220A (en) * | 2020-10-26 | 2021-02-02 | 中国人民解放军陆军装甲兵学院 | Binocular camera coordinate system registration method based on measurement adjustment |
CN112326206B (en) * | 2020-11-06 | 2023-06-13 | 歌尔光学科技有限公司 | AR module binocular fusion detection device and detection method |
CN112326206A (en) * | 2020-11-06 | 2021-02-05 | 歌尔光学科技有限公司 | AR module binocular fusion detection device and detection method |
CN112720469A (en) * | 2020-12-18 | 2021-04-30 | 北京工业大学 | Zero point calibration method for three-axis translational motion system by microscopic stereo vision |
CN113112548B (en) * | 2020-12-23 | 2022-08-19 | 合肥工业大学 | Rapid calibration method for internal and external parameters of binocular camera based on coded three-dimensional target |
CN113112548A (en) * | 2020-12-23 | 2021-07-13 | 合肥工业大学 | Quick calibration method for internal and external parameters of binocular camera based on coded three-dimensional target |
CN113028986A (en) * | 2021-03-03 | 2021-06-25 | 北京科技大学 | Volume measuring device and mass measuring system |
CN113177977B (en) * | 2021-04-09 | 2022-06-10 | 上海工程技术大学 | Non-contact three-dimensional human body size measuring method |
CN113177977A (en) * | 2021-04-09 | 2021-07-27 | 上海工程技术大学 | Non-contact three-dimensional human body size measuring method |
CN113050264A (en) * | 2021-04-23 | 2021-06-29 | 南京甬宁科学仪器有限公司 | Microscope objective automatic identification system |
CN113284111A (en) * | 2021-05-26 | 2021-08-20 | 汕头大学 | Hair follicle region positioning method and system based on binocular stereo vision |
CN115075857A (en) * | 2022-08-18 | 2022-09-20 | 中煤科工开采研究院有限公司 | Quantitative pushing method and system for hydraulic support |
CN115797461B (en) * | 2022-11-11 | 2023-06-06 | 中国消防救援学院 | Flame space positioning system calibration and correction method based on binocular vision |
CN116735613A (en) * | 2023-08-16 | 2023-09-12 | 昆山龙雨智能科技有限公司 | CCD camera-based product positioning and measuring system and use method |
CN116735613B (en) * | 2023-08-16 | 2023-10-13 | 昆山龙雨智能科技有限公司 | CCD camera-based product positioning and measuring system and use method |
Also Published As
Publication number | Publication date |
---|---|
CN103247053B (en) | 2015-10-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103247053B (en) | Based on the part accurate positioning method of binocular microscopy stereo vision | |
Tang et al. | Real-time detection of surface deformation and strain in recycled aggregate concrete-filled steel tubular columns via four-ocular vision | |
CN111192235B (en) | Image measurement method based on monocular vision model and perspective transformation | |
CN108986070B (en) | Rock crack propagation experiment monitoring method based on high-speed video measurement | |
CN102221331B (en) | Measuring method based on asymmetric binocular stereovision technology | |
CN105180806A (en) | Trans-scale geometrical parameter measurement method based on microscopic visual sense | |
CN104052986B (en) | Detection apparatus, stereographic machine testing device and detection method | |
CN107589069B (en) | Non-contact type measuring method for object collision recovery coefficient | |
CN106500625B (en) | A kind of telecentricity stereo vision measurement method | |
CN106709955B (en) | Space coordinate system calibration system and method based on binocular stereo vision | |
CN107816942A (en) | A kind of planar dimension measurement method based on cross structure light vision system | |
Zhu et al. | Noncontact 3-D coordinate measurement of cross-cutting feature points on the surface of a large-scale workpiece based on the machine vision method | |
CN104634246A (en) | Floating type stereo visual measuring system and measuring method for coordinates of object space | |
Chen et al. | Binocular visual dimension measurement method for rectangular workpiece with a precise stereoscopic matching algorithm | |
Zhang et al. | Global measurement method for large-scale components based on a multiple field of view combination | |
CN105678088B (en) | A kind of adjustment optimization algorithm of target gauge head | |
Percoco et al. | Image analysis for 3D micro-features: A new hybrid measurement method | |
Hwang et al. | Camera calibration and 3D surface reconstruction for multi-camera semi-circular DIC system | |
Zhang et al. | Freight train gauge-exceeding detection based on three-dimensional stereo vision measurement | |
CN105157562A (en) | On-line dynamic visual measuring system and on-line dynamic visual measuring method for geometrical dimension of complex and precise workpiece in small space | |
Wang | Disparity surface reconstruction based on a stereo light microscope and laser fringes | |
CN114018167A (en) | Bridge deflection measuring method based on monocular three-dimensional vision | |
Kawata et al. | Scale optimization of structure from motion for structured light-based all-round 3D measurement | |
CN114663486A (en) | Building height measurement method and system based on binocular vision | |
Mu et al. | Research on target ranging method based on binocular stereo vision |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |