CN113744245A - Method and system for positioning structural reinforcing rib welding seam in point cloud - Google Patents
Method and system for positioning structural reinforcing rib welding seam in point cloud Download PDFInfo
- Publication number
- CN113744245A CN113744245A CN202111034042.3A CN202111034042A CN113744245A CN 113744245 A CN113744245 A CN 113744245A CN 202111034042 A CN202111034042 A CN 202111034042A CN 113744245 A CN113744245 A CN 113744245A
- Authority
- CN
- China
- Prior art keywords
- plane
- points
- point
- point cloud
- dimensional
- 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
- 238000003466 welding Methods 0.000 title claims abstract description 110
- 230000003014 reinforcing effect Effects 0.000 title claims abstract description 53
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000012216 screening Methods 0.000 claims abstract description 27
- 238000005070 sampling Methods 0.000 claims description 20
- 239000011159 matrix material Substances 0.000 claims description 17
- 230000011218 segmentation Effects 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 239000003351 stiffener Substances 0.000 claims description 8
- 230000002787 reinforcement Effects 0.000 claims description 5
- 238000012217 deletion Methods 0.000 claims description 3
- 230000037430 deletion Effects 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 11
- 230000000694 effects Effects 0.000 description 6
- 230000006872 improvement Effects 0.000 description 6
- 238000005259 measurement Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000011324 bead Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
Abstract
The invention discloses a method and a system for positioning a structural reinforcing rib welding seam in point cloud, which comprises the following steps: s1: screening candidate welding line points with rich curvature characteristics from the structural reinforcing rib point cloud; s2: dividing the bottom plate plane of the structural reinforcing rib and two side plate planes intersected with the bottom plate plane, and fitting a plane equation of the bottom plate plane and the two side plate planes; s3: and (5) taking the plane equation obtained in the step (S2) as constraint, and screening out final effective weld joint points from candidate weld joint points with rich curvature characteristics to finish the weld joint positioning of the structural reinforcing rib. The invention ensures that the effective welding line point not only accords with the geometric constraint, but also can truly reflect the actual welding line position, thereby avoiding the conditions of collision or insufficient welding of the welding gun and the like, and the welding line positioning result is accurate and reliable.
Description
Technical Field
The invention relates to the technical field of machine vision, in particular to a method and a system for positioning a structural reinforcing rib welding seam in point cloud.
Background
In the welding industry, the vision technology can help the robot to independently position the welding line, and the welding precision, efficiency and automation degree of the robot are improved. Most of the existing welding seam positioning technologies are based on a line laser type 3D camera, the pixel position of the intersection point of a laser stripe and a welding seam is firstly identified from an image, and then the pixel position is converted into a three-dimensional coordinate of the welding seam point. According to the method, the line laser type 3D camera is driven by the accurate moving device to scan the whole welding line, and the complete welding line can be positioned only through multiple measurements, so that the efficiency is low. The surface structured light type 3D camera can accurately acquire the point cloud of the surface of the workpiece in the surface type range where the welding line is located through one-time measurement without the assistance of a moving device. The welding seam is directly positioned in the point cloud obtained from the surface structure light type 3D camera, and the welding efficiency can be improved.
At present, no mature three-dimensional feature recognition method can realize the direct positioning of welding seams from point clouds, and the analysis needs to be carried out by combining the three-dimensional geometrical structure of a workpiece. The welding seam of the structural reinforcing rib is positioned at the intersection of the bottom plate and the side plate, although an ideal welding seam linear equation can be obtained through the intersection relation of the surface and the surface, practical experiments show that the ideal linear equation is not the real reflection of the welding seam, and welding gun collision or false welding can occur when welding is carried out along the straight line. Therefore, it is difficult to accurately locate the bead from the point cloud by only either feature recognition or solid geometry analysis.
Disclosure of Invention
The invention aims to provide a method and a system for positioning a structural reinforcing rib welding seam in point cloud, so that an effective welding seam point not only accords with geometric constraint, but also can truly reflect the actual welding seam position, the conditions of collision or insufficient welding of a welding gun and the like are avoided, and the welding seam positioning result is accurate and reliable.
In order to solve the technical problem, the invention provides a method for positioning a structural reinforcing rib welding seam in point cloud, which comprises the following steps:
s1: screening candidate welding line points with rich curvature characteristics from the structural reinforcing rib point cloud;
s2: dividing the bottom plate plane of the structural reinforcing rib and two side plate planes intersected with the bottom plate plane, and fitting a plane equation of the bottom plate plane and the two side plate planes;
s3: and (5) taking the plane equation obtained in the step (S2) as constraint, and screening out final effective weld joint points from candidate weld joint points with rich curvature characteristics to finish the weld joint positioning of the structural reinforcing rib.
As a further improvement of the present invention, the step S1 specifically includes:
estimating neighborhood curvature of points in the point cloud by establishing a neighborhood data structure of the point cloud of the structural reinforcing rib and adopting a covariance analysis method, and constructing a neighborhood covariance matrix of each point in the point cloud;
taking the minimum eigenvalue of the covariance matrix as an estimated value of the neighborhood curvature, and setting a curvature threshold;
and screening out all points with neighborhood curvature larger than a threshold value, namely candidate welding line points with rich curvature characteristics.
As a further improvement of the present invention, the step S2 specifically includes:
obtaining a sampling plane through a random sampling mode based on a plane segmentation algorithm of random sampling consistency, extracting in-plane points meeting a threshold value of the number of the in-plane points of the sampling plane from an original point cloud set, and fitting a new effective plane;
and when the bottom plate plane and the two side plate planes intersected with the bottom plate plane are extracted, the point number in the point cloud set does not meet the requirement of the minimum point number, the algorithm is terminated, and three effective plane parameters are obtained.
As a further improvement of the present invention, the step S3 specifically includes:
combining the plane equation obtained in the step S2 as constraint, and screening the candidate weld points again;
and calculating respective distances between the candidate welding seam point and the plane of the bottom plate and the planes of the two side plates intersected with the candidate welding seam point, and when the distance between the candidate welding seam point and the plane of the bottom plate is less than 3mm and the distance between the candidate welding seam point and the plane of the side plate is less than 1mm, determining the candidate welding seam point as an effective welding seam point.
As a further improvement of the present invention, the step S1 specifically includes the following steps:
s101: all three-dimensional points of the structural reinforcing rib point cloud form a point cloud set D0Point cloud set D0Has a total number of three-dimensional points of n0,PiSet of representation points D0The ith three-dimensional point of (1), XiRepresenting three-dimensional points PiX-axis coordinate of (2), YiRepresenting three-dimensional points PiY-axis coordinate of (1), ZiRepresenting three-dimensional points PiZ-axis coordinate of (1), (2), (…), n0(ii) a Establishing a k neighborhood data structure of the point cloud, setting the number of neighborhood points as k, and setting the threshold value of the curvature feature to be lambda according to experiencethLet i equal 0,n1=0;
S102: let i equal i + 1; search point cloud set D0Middle distance three-dimensional point PiThe nearest k points, denoted as Pi,jJ is 1,2, …, k as the three-dimensional point PiK neighborhood points of (1);
s103: from three-dimensional points PiK neighborhood points construct a neighborhood covariance matrix CiComprises the following steps:
wherein the content of the first and second substances,Xi,j、Yi,j、Zi,jrespectively representing three-dimensional points Pi,jX-axis, Y-axis, Z-axis coordinates of (j) 1,2, … k; for matrix CiCarrying out SVD to obtain a matrix CiHas a minimum eigenvalue of λiAt λiIs a three-dimensional point PiA neighborhood curvature estimate of;
s104: determine lambdai>λthIf yes, the three-dimensional point P is determinediAs candidate weld points, let n1=n1+1,
S105: judging i < n0If yes, go to step S102; if not, n is obtained1A candidate weld point Pu′,u=1,2,…n1The total number of candidate weld points is n1。
As a further improvement of the present invention, the step S2 specifically includes the following steps:
s201: end point number n of plane segmentation algorithm for setting random sampling consistencyminNumber of points constituting a plane nthAnd determining whether the distance is an interior point distance threshold dthReference normal vector of the floor planeLet n bemax=n0,np=0;
S202: from a collection of point clouds D03 three-dimensional points P are sampled at randomr0、Pr1、Pr2Fitting the plane equation to a from the 3 three-dimensional pointsrx+bry+crz +1 is 0, wherein ar、br、crDenotes a plane parameter, ar、br、crIs calculated as:
wherein, Xr0、Xr1、Xr2Respectively represent points Pr0、Pr1、Pr2X-axis coordinates of (a); y isr0、Yr1、Yr2Respectively represent points Pr0、Pr1、Pr2Y-axis coordinates of (a); zr0、Zr1、Zr2Respectively represent points Pr0、Pr1、Pr2Z-axis coordinates of (a);
s203: let n bein=0,i=1,PiSet of representation points D0The ith three-dimensional point of (1), XiRepresenting three-dimensional points PiX-axis coordinate of (2), YiRepresenting three-dimensional points PiY-axis coordinate of (1), ZiRepresenting three-dimensional points PiZ-axis coordinates of (a);
s204: calculating a three-dimensional point PiTo equation arx+bry+crDistance d of plane represented by z +1 ═ 0iComprises the following steps:
s205: judgment of di<dthIf yes, the three-dimensional point P is determinediAs equation arx+bry+crz +1 is 0, let nin=nin+1,If not, go to step S206;
s206: judging i < nmaxIf yes, the process goes to step S24, where i is set to i + 1; if not, the equation a is obtainedrx+bry+crThe plane represented by z +1 ═ 0 is in the point cloud set D0Inner point P inm″,m=1,2,…ninGo to step S207;
s207: judging nin>nthIf not, go to step S202; if yes, let np=np+1, fitting out the interior point Pm″,m=1,2,…ninThe plane is an effective plane and the plane equation isParameters of equationIs calculated as:
wherein, Xm,m=1,2,…ninIs an inner point Pm″,m=1,2,…ninX-axis coordinates of (a); y ism,m=1,2,…ninIs an inner point Pm″,m=1,2,…ninY-axis coordinates of (a); zm,m=1,2,…ninIs an inner point Pm″,m=1,2,…ninZ-axis coordinates of (a);
s208: from a collection of point clouds D0Middle deletion interior point Pm″,m=1,2,…ninLet n bemax=nmax-nin;
S209: judging nmax>nminIf yes, go to step S202; if not, n is obtainedpEquation of an effective planejx+bjy+cjz+1=0,j=1,2,…npTotal number of active planes np;
S210: let t equal to 1, tB=0,tSCalculating unit normal vector of effective plane as 0Comprises the following steps:
s211: calculating unit normal vector of t-th effective planeAnd a reference normal vectorProduct of quantity ofComprises the following steps:
s212: judgment ofIf yes, let tB=tB+1, orderObtaining a plane equation of the plane of the base plateIf not, let tS=tS+1, order Obtaining the plane equation of the side plate plane
S213: judging t < npIf yes, the process goes to step S211, if t is t + 1; if not, t is obtainedBPlane equation of individual base plate plane and tSPlane equations of the individual side panel planes; when the parameter setting is appropriate n in step S201p=3、tB=1、t S2 holds true, i.e. the plane equation a 'of a floor plane is finally obtained'1x+b′1y+c′1z +1 ═ 0 and the plane equation a ″ for the two side plate planes1x+b″1y+c″1z +1 ═ 0 and a ″)2x+b″2y+c″2z+1=0。
As a further improvement of the present invention, the step S3 specifically includes the following steps:
s301: let u be 1, n 20, three-dimensional point Pu' is the u-th candidate weld point, X, obtained in step S105uRepresenting three-dimensional points Pu' X-axis coordinate, YuRepresenting three-dimensional points Pu' Y-axis coordinate, ZuRepresenting three-dimensional points Pu' Z-axis coordinates;
s302: calculating a three-dimensional point Pu' distance to floor plane dBAnd a distance d to the plane of the two side platess1And ds2Comprises the following steps:
s303: let u be u + 1; judgment of dBIf the length is less than 3mm, if the length is not less than 3mm, the step S302 is executed; if yes, go to step S304;
s304: judgment of ds1< 1mm or ds2If < 1mm is true, if not, go to step S302; if true, the three-dimensional point PuIs an effective weld point, i.e. an2=n2+1,Go to step S305;
s306: judging u < n1If yes, go to step S302; if not, obtaining the effective welding line point as Pv″′,v=1,2,…n2The total number of effective weld points is n2(ii) a And finishing the welding line positioning of the structural reinforcing rib point cloud.
A structural reinforcement weld locating system in a point cloud, comprising:
the selection module is used for screening candidate welding line points with rich curvature characteristics from the structural reinforcing rib point cloud;
the segmentation fitting module is used for segmenting the bottom plate plane of the structural reinforcing rib and two side plate planes intersected with the bottom plate plane and fitting a plane equation of the bottom plate plane;
and the positioning module is used for screening out final effective welding seam points from candidate welding seam points with rich curvature characteristics by taking the plane equation obtained in the segmentation fitting module as constraint so as to complete the welding seam positioning of the structural reinforcing rib.
A computer apparatus comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor when executing the computer program implementing the steps of a method of structural reinforcing bar weld positioning in a point cloud as described above.
A computer-readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of a method of structural reinforcing bar weld positioning in a point cloud as described above.
The invention has the beneficial effects that: extracting neighborhood curvature characteristics of reinforcing rib point cloud, and taking points with rich neighborhood curvature characteristics as candidate welding seam points; dividing and fitting a plane equation of a bottom plate plane and two side plate planes of the structural reinforcing rib; and determining a final effective welding line point from the preliminarily screened candidate welding line points by utilizing the planar geometric constraint, wherein the effective welding line point not only accords with the geometric constraint, but also can truly reflect the actual welding line position, thereby avoiding the conditions of collision or insufficient welding of a welding gun and the like, and the welding line positioning result is accurate and reliable.
Drawings
FIG. 1 is a flow chart of the structural reinforcement weld positioning of the present invention;
FIG. 2 is a schematic view of a weld of a structural reinforcing bar of the present invention;
FIG. 3 is an effect diagram before points with rich curvature characteristics are screened out;
FIG. 4 is a diagram of the effect of the invention after screening out points with rich curvature characteristics;
FIG. 5 is an effect of the present invention in dividing the plane of the bottom panel and the plane of the side panel;
FIG. 6 is a diagram of the effect of the final positioning of the structural stiffener welds of the present invention;
the reference numbers in the figures illustrate: 1. a base plate; 2. welding seams; 3. the angle is measured.
Detailed Description
The present invention is further described below in conjunction with the following figures and specific examples so that those skilled in the art may better understand the present invention and practice it, but the examples are not intended to limit the present invention.
Referring to fig. 1, the embodiment of the present invention provides a method for positioning a structural reinforcing rib weld in a point cloud, including the following steps:
s1: screening candidate welding line points with rich curvature characteristics from the structural reinforcing rib point cloud;
s2: dividing the bottom plate plane of the structural reinforcing rib and two side plate planes intersected with the bottom plate plane, and fitting a plane equation of the bottom plate plane and the two side plate planes;
s3: and (5) taking the plane equation obtained in the step (S2) as constraint, and screening out final effective weld joint points from candidate weld joint points with rich curvature characteristics to finish the weld joint positioning of the structural reinforcing rib.
Specifically, the step S1 specifically includes:
estimating neighborhood curvature of points in the point cloud by establishing a neighborhood data structure of the point cloud of the structural reinforcing rib and adopting a covariance analysis method, and constructing a neighborhood covariance matrix of each point in the point cloud;
taking the minimum eigenvalue of the covariance matrix as an estimated value of the neighborhood curvature, and setting a curvature threshold;
and screening out all points with neighborhood curvature larger than a threshold value, namely candidate welding line points with rich curvature characteristics.
The step S2 specifically includes:
obtaining a sampling plane through a random sampling mode based on a plane segmentation algorithm of random sampling consistency, extracting in-plane points meeting a threshold value of the number of the in-plane points of the sampling plane from an original point cloud set, and fitting a new effective plane;
and when the bottom plate plane and the two side plate planes intersected with the bottom plate plane are extracted, the point number in the point cloud set does not meet the requirement of the minimum point number, the algorithm is terminated, and three effective plane parameters are obtained.
The step S3 specifically includes:
combining the plane equation obtained in the step S2 as constraint, and screening the candidate weld points again;
and calculating respective distances between the candidate welding seam point and the plane of the bottom plate and the planes of the two side plates intersected with the candidate welding seam point, and when the distance between the candidate welding seam point and the plane of the bottom plate is less than 3mm and the distance between the candidate welding seam point and the plane of the side plate is less than 1mm, determining the candidate welding seam point as an effective welding seam point.
Specifically, in the calculation implementation process, referring to fig. 1, the step S1 of primarily screening out candidate weld points with rich curvature characteristics from the structural reinforcing rib point cloud specifically includes the following steps:
s101: all three-dimensional points of the structural reinforcing rib point cloud form a point cloud set D0Point cloud set D0Has a total number of three-dimensional points of n0,PiSet of representation points D0The ith three-dimensional point of (1), XiRepresenting three-dimensional points PiX-axis coordinate of (2), YiRepresenting three-dimensional points PiY-axis coordinate of (1), ZiRepresenting three-dimensional points PiZ-axis coordinate of (1), (2), (…), n0(ii) a Establishing a k neighborhood data structure of the point cloud, setting the number of neighborhood points as k, and setting the threshold value of the curvature feature to be lambda according to experiencethLet i equal 0, n1=0;
S102: let i equal i + 1; searchingPoint cloud collection D0Middle distance three-dimensional point PiThe nearest k points, denoted as Pi,jJ is 1,2, …, k as the three-dimensional point PiK neighborhood points of (1);
s103: from three-dimensional points PiK neighborhood points construct a neighborhood covariance matrix CiComprises the following steps:
wherein the content of the first and second substances,Xi,j、Yi,j、Zi,jrespectively representing three-dimensional points Pi,jX-axis, Y-axis, Z-axis coordinates of (j) 1,2, … k; for matrix CiCarrying out SVD to obtain a matrix CiHas a minimum eigenvalue of λiAt λiIs a three-dimensional point PiA neighborhood curvature estimate of;
s104: determine lambdai>λthIf yes, the three-dimensional point P is determinediAs candidate weld points, let n1=n1+1,
S105: judging i < n0If yes, go to step S102; if not, n is obtained1A candidate weld point Pu′,u=1,2,…n1The total number of candidate weld points is n1。
The step S22) of dividing the plane of the bottom plate and the planes of the two side plates of the structural reinforcing rib and fitting the plane equation thereof specifically includes the following steps:
s201: end point number n of plane segmentation algorithm for setting random sampling consistencyminNumber of points constituting a plane nthAnd determining whether the distance is an interior point distance threshold dthReference normal vector of the floor planeLet n bemax=n0,np=0;
S202: from a collection of point clouds D03 three-dimensional points P are sampled at randomr0、Pr1、Pr2Fitting the plane equation to a from the 3 three-dimensional pointsrx+bry+crz +1 is 0, wherein ar、br、crDenotes a plane parameter, ar、br、crIs calculated as:
wherein, Xr0、Xr1、Xr2Respectively represent points Pr0、Pr1、Pr2X-axis coordinates of (a); y isr0、Yr1、Yr2Respectively represent points Pr0、Pr1、Pr2Y-axis coordinates of (a); zr0、Zr1、Zr2Respectively represent points Pr0、Pr1、Pr2Z-axis coordinates of (a);
s203: let n bein=0,i=1,PiSet of representation points D0The ith three-dimensional point of (1), XiRepresenting three-dimensional points PiX-axis coordinate of (2), YiRepresenting three-dimensional points PiY-axis coordinate of (1), ZiRepresenting three-dimensional points PiZ-axis coordinates of (a);
s204: calculating a three-dimensional point PiTo equation arx+bry+crDistance d of plane represented by z +1 ═ 0iComprises the following steps:
s205: judgment of di<dthIf yes, the three-dimensional point P is determinediAs equation arx+bry+crz +1 is 0, let nin=nin+1,If not, go to step S206;
s206: judging i < nmaxIf yes, the process goes to step S24, where i is set to i + 1; if not, the equation a is obtainedrx+bry+crThe plane represented by z +1 ═ 0 is in the point cloud set D0Inner point P inm″,m=1,2,…ninGo to step S207;
s207: judging nin>nthIf not, go to step S202; if yes, let np=np+1, fitting out the interior point Pm″,m=1,2,…ninThe plane is an effective plane and the plane equation isParameters of equationIs calculated as:
wherein, Xm,m=1,2,…ninIs an inner point Pm″,m=1,2,…ninX-axis coordinates of (a); y ism,m=1,2,…ninIs an inner point Pm″,m=1,2,…ninY-axis coordinates of (a); zm,m=1,2,…ninIs an inner point Pm″,m=1,2,…ninZ-axis coordinates of (a);
s208: from a collection of point clouds D0Middle deletion interior point Pm″,m=1,2,…ninLet n bemax=nmax-nin;
S209: judging nmax>nminIf yes, go to step S202; if not, n is obtainedpEquation of an effective planejx+bjy+cjz+1=0,j=1,2,…npTotal number of active planes np;
S210: let t equal to 1, tB=0,tSCalculating unit normal vector of effective plane as 0Comprises the following steps:
s211: calculating unit normal vector of t-th effective planeAnd a reference normal vectorProduct of quantity ofComprises the following steps:
s212: judgment ofIf yes, let tB=tB+1, orderObtaining a plane equation of the plane of the base plateIf not, let tS=tS+1, order Obtaining the plane equation of the side plate plane
S213: judging t < npIf yes, the process goes to step S211, if t is t + 1; if not, t is obtainedBPlane equation of individual base plate plane and tSPlane equations of the individual side panel planes; when the parameter setting is appropriate n in step S201p=3、tB=1、t S2 holds true, i.e. the plane equation a 'of a floor plane is finally obtained'1x+b′1y+c′1z +1 ═ 0 and the plane equation a ″ for the two side plate planes1x+b″1y+c″1z +1 ═ 0 and a ″)2x+b″2y+c″2z+1=0。
The step S33) of screening out the final effective weld joint points from the candidate weld joint points with rich curvature characteristics according to plane constraint specifically comprises the following steps:
s301: let u be 1, n 20, three-dimensional point Pu' is the u-th candidate weld point, X, obtained in step S105uRepresenting three-dimensional points Pu' X-axis coordinate, YuRepresenting three-dimensional points Pu' Y-axis coordinate, ZuRepresenting three-dimensional points Pu' Z-axis coordinates;
s302: calculating a three-dimensional point Pu' distance to floor plane dBAnd a distance d to the plane of the two side platess1And ds2Comprises the following steps:
s303: let u be u + 1; judgment of dBIf the length is less than 3mm, if the length is not less than 3mm, the step S302 is executed; if yes, go to step S304;
s304: judgment of ds1< 1mm or ds2If < 1mm is true, if not, go to step S302; if true, the three-dimensional point Pu' is the effective weld point, let n2=n2+1,Go to step S305;
s306: judging u < n1If yes, go to step S302; if not, obtaining the effective welding line point as Pv″′,v=1,2,…n2The total number of effective weld points is n2(ii) a And finishing the welding line positioning of the structural reinforcing rib point cloud.
Example one
Referring to fig. 1, the embodiment of the present invention provides a method for positioning a structural reinforcing rib weld in a point cloud, including:
step 1: obtaining candidate weld points
According to the method, the basis of acquiring candidate welding seam points is the curvature characteristic of point cloud, and referring to the welding seam schematic diagram of the structural reinforcing rib shown in the attached figure 2, the welding seam 2 of the structural reinforcing rib is located at the joint of the bottom plate 1 and the two side plates, the bottom plate 1 and the two side plates are both smooth planes, so that the point curvature on the plate surface is small, the point curvature at the joint of the welding seam 2 is large, and the welding seam 2 can be preliminarily screened and positioned according to the curvature.
For the structural reinforcing rib point cloud picture shown in fig. 3, a k neighborhood data structure of the structural reinforcing rib point cloud is established, a covariance analysis method is adopted to realize rapid estimation of neighborhood curvature of the point cloud point, the method for establishing the neighborhood covariance matrix is formula (1), the minimum eigenvalue of the covariance matrix is taken as an estimated value of the neighborhood curvature, and because the included angle between the bottom plate 1 and the side plate is almost a right angle, the curvature threshold lambda in the step S101 can be easily selected through analysis of the measurement angle 3 on the test datath(ii) a Screening out all neighborhood curvatures greater than threshold lambdathThe obtained points are candidate weld points with rich curvature characteristics, and the effect of obtaining the candidate weld points is shown in fig. 4.
Step 2: dividing planes and fitting plane equations
After screening candidate welding seam point, can tentatively realize the location to welding seam 2, nevertheless candidate welding seam point is counted more and there are some interference points, is difficult to satisfy the precision demand of guide welding robot, and analysis figure 2 can see that the crossing relation of faying face can promote the precision of location.
The invention uses a plane segmentation method based on random sampling consistency, and the basic principle is that a sampling plane is obtained by a random sampling mode, and in-plane points which accord with a threshold value of the number of the in-plane points in the sampling plane are collected from an original point cloud D0Extracting, fitting new effective plane, and collecting point cloud D after extracting three effective planes, i.e. bottom plate 1 plane and side plate plane0If the point number in the plane does not meet the requirement of the minimum point number, the algorithm is terminated, and three effective plane parameters are obtained. The method has the advantages that the plane segmentation can be realized, the plane fitting precision is improved through random sampling consistency, and the effect of segmenting the plane of the bottom plate 1 and the plane of the side plate is shown in the attached drawing 5.
And step 3: obtaining effective weld points
The primary positioning of the welding seam can be realized through the steps 1 and 2, but the step 1 is insufficient in that the number of screened candidate welding seams is large, the precision is low and interference points exist, and the step 2 can obtain a more ideal welding seam linear equation by solving the intersection relation of the planes, but actually, the bottom plate 1 and the side plate are not ideal planes, the ideal linear equation is not the real reflection of the welding seam 2, and welding along the ideal straight line can cause welding gun collision or false welding under certain conditions.
Therefore, the advantages of the step 1 and the step 2 are combined, the step 1 is used for realizing the rapid positioning of the welding seam 2 to obtain the candidate welding seam points, then the plane constraint of the step 2 is combined to screen the candidate welding seam points again, the screening condition is the step S303 and the step S304 in the specific implementation mode, the effective welding seam points obtained after screening are shown in the figure 6, the effective welding seam points can truly reflect the actual position information of the welding seam 2, the plane constraint is met, and the precision and the reliability are high.
Example two
Based on the same inventive concept, the embodiment provides a system for positioning a weld joint of a structural reinforcing rib in point cloud, the principle of solving the problem is similar to the method for positioning the weld joint of the structural reinforcing rib in the point cloud, and repeated parts are not repeated.
A structural reinforcement weld locating system in a point cloud, comprising:
the selection module is used for screening candidate welding line points with rich curvature characteristics from the structural reinforcing rib point cloud;
the segmentation fitting module is used for segmenting the bottom plate plane of the structural reinforcing rib and two side plate planes intersected with the bottom plate plane and fitting a plane equation of the bottom plate plane;
and the positioning module is used for screening out final effective welding seam points from candidate welding seam points with rich curvature characteristics by taking the plane equation obtained in the segmentation fitting module as constraint so as to complete the welding seam positioning of the structural reinforcing rib.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned embodiments are merely preferred embodiments for fully illustrating the present invention, and the scope of the present invention is not limited thereto. The equivalent substitution or change made by the technical personnel in the technical field on the basis of the invention is all within the protection scope of the invention. The protection scope of the invention is subject to the claims.
Claims (10)
1. A method for positioning a structural reinforcing rib welding seam in point cloud is characterized by comprising the following steps: the method comprises the following steps:
s1: screening candidate welding line points with rich curvature characteristics from the structural reinforcing rib point cloud;
s2: dividing the bottom plate plane of the structural reinforcing rib and two side plate planes intersected with the bottom plate plane, and fitting a plane equation of the bottom plate plane and the two side plate planes;
s3: and (5) taking the plane equation obtained in the step (S2) as constraint, and screening out final effective weld joint points from candidate weld joint points with rich curvature characteristics to finish the weld joint positioning of the structural reinforcing rib.
2. The method of claim 1 for locating structural stiffener welds in a point cloud, comprising: the step S1 specifically includes:
estimating neighborhood curvature of points in the point cloud by establishing a neighborhood data structure of the point cloud of the structural reinforcing rib and adopting a covariance analysis method, and constructing a neighborhood covariance matrix of each point in the point cloud;
taking the minimum eigenvalue of the covariance matrix as an estimated value of the neighborhood curvature, and setting a curvature threshold;
and screening out all points with neighborhood curvature larger than a threshold value, namely candidate welding line points with rich curvature characteristics.
3. The method of claim 1 for locating structural stiffener welds in a point cloud, comprising: the step S2 specifically includes:
obtaining a sampling plane through a random sampling mode based on a plane segmentation algorithm of random sampling consistency, extracting in-plane points meeting a threshold value of the number of the in-plane points of the sampling plane from an original point cloud set, and fitting a new effective plane;
and when the bottom plate plane and the two side plate planes intersected with the bottom plate plane are extracted, the point number in the point cloud set does not meet the requirement of the minimum point number, the algorithm is terminated, and three effective plane parameters are obtained.
4. The method of claim 1 for locating structural stiffener welds in a point cloud, comprising: the step S3 specifically includes:
combining the plane equation obtained in the step S2 as constraint, and screening the candidate weld points again;
and calculating respective distances between the candidate welding seam point and the plane of the bottom plate and the planes of the two side plates intersected with the candidate welding seam point, and when the distance between the candidate welding seam point and the plane of the bottom plate is less than 3mm and the distance between the candidate welding seam point and the plane of the side plate is less than 1mm, determining the candidate welding seam point as an effective welding seam point.
5. The method of claim 1 for locating structural stiffener welds in a point cloud, comprising: the step S1 specifically includes the following steps:
s101: all three-dimensional points of the structural reinforcing rib point cloud form a point cloud set D0Point cloud set D0Has a total number of three-dimensional points of n0,PiSet of representation points D0The ith three-dimensional point of (1), XiRepresenting three-dimensional points PiX-axis coordinate of (2), YiRepresenting three-dimensional points PiY-axis coordinate of (1), ZiRepresenting three-dimensional points PiZ-axis coordinate of (1), (2), (…), n0(ii) a Establishing a k neighborhood data structure of the point cloud, setting the number of neighborhood points as k, and setting the threshold value of the curvature feature to be lambda according to experiencethLet i equal 0, n1=0;
S102: let i equal i + 1; search point cloud set D0Middle distance three-dimensional point PiThe nearest k points, denoted as Pi,jJ is 1,2, …, k as the three-dimensional point PiK neighborhood points of (1);
s103: from three-dimensional points PiK neighborhood points construct a neighborhood covariance matrix CiComprises the following steps:
wherein the content of the first and second substances,Xi,j、Yi,j、Zi,jrespectively representing three-dimensional points Pi,jX-axis, Y-axis, Z-axis coordinates of (j) 1,2, … k; for matrix CiCarrying out SVD to obtain a matrix CiHas a minimum eigenvalue of λiAt λiIs a three-dimensional point PiA neighborhood curvature estimate of;
s104: determine lambdai>λthIf yes, the three-dimensional point P is determinediAs candidate weld points, let n1=n1+1,
S105: judging i < n0If yes, go to step S102; if not, n is obtained1A candidate weld point Pu′,u=1,2,…n1The total number of candidate weld points is n1。
6. The method of claim 5 for locating structural stiffener welds in a point cloud, wherein: the step S2 specifically includes the following steps:
s201: end point number n of plane segmentation algorithm for setting random sampling consistencyminNumber of points constituting a plane nthAnd whether it is judged asDistance threshold d of inner pointthReference normal vector of the floor planeLet n bemax=n0,np=0;
S202: from a collection of point clouds D03 three-dimensional points P are sampled at randomr0、Pr1、Pr2Fitting the plane equation to a from the 3 three-dimensional pointsrx+bry+crz +1 is 0, wherein ar、br、crDenotes a plane parameter, ar、br、crIs calculated as:
wherein, Xr0、Xr1、Xr2Respectively represent points Pr0、Pr1、Pr2X-axis coordinates of (a); y isr0、Yr1、Yr2Respectively represent points Pr0、Pr1、Pr2Y-axis coordinates of (a); zr0、Zr1、Zr2Respectively represent points Pr0、Pr1、Pr2Z-axis coordinates of (a);
s203: let n bein=0,i=1,PiSet of representation points D0The ith three-dimensional point of (1), XiRepresenting three-dimensional points PiX-axis coordinate of (2), YiRepresenting three-dimensional points PiY-axis coordinate of (1), ZiRepresenting three-dimensional points PiZ-axis coordinates of (a);
s204: calculating a three-dimensional point PiTo equation arx+bry+crDistance d of plane represented by z +1 ═ 0iComprises the following steps:
s205: judgment of di<dthIf yes, the three-dimensional point P is determinediAs equation arx+bry+crz +1 is 0, let nin=nin+1,If not, go to step S206;
s206: judging i < nmaxIf yes, the process goes to step S24, where i is set to i + 1; if not, the equation a is obtainedrx+bry+crThe plane represented by z +1 ═ 0 is in the point cloud set D0Inner point P inm″,m=1,2,…ninGo to step S207;
s207: judging nin>nthIf not, go to step S202; if yes, let np=np+1, fitting out the interior point Pm″,m=1,2,…ninThe plane is an effective plane and the plane equation isParameters of equationIs calculated as:
wherein, Xm,m=1,2,…ninIs an inner point Pm″,m=1,2,…ninX-axis coordinates of (a); y ism,m=1,2,…ninIs an inner point Pm″,m=1,2,…ninY-axis coordinates of (a); zm,m=1,2,…ninIs an inner point Pm″,m=1,2,…ninZ-axis coordinates of (a);
s208: from a collection of point clouds D0Middle deletion interior point Pm″,m=1,2,…ninLet n bemax=nmax-nin;
S209: judging nmax>nminIf yes, go to step S202; if not, n is obtainedpEquation of an effective planejx+bjy+cjz+1=0,j=1,2,…npTotal number of active planes np;
S210: let t equal to 1, tB=0,tSCalculating unit normal vector of effective plane as 0Comprises the following steps:
s211: calculating unit normal vector of t-th effective planeAnd a reference normal vectorProduct of quantity ofComprises the following steps:
s212: judgment ofIf yes, let tB=tB+1, orderObtaining a plane equation of the plane of the base plateIf not, let tS=tS+1, order Obtaining the plane equation of the side plate plane
S213: judging t < npIf yes, the process goes to step S211, if t is t + 1; if not, t is obtainedBPlane equation of individual base plate plane and tSPlane equations of the individual side panel planes; when the parameter setting is appropriate n in step S201p=3、tB=1、tS2 holds true, i.e. the plane equation a 'of a floor plane is finally obtained'1x+b′1y+c′1z +1 ═ 0 and the plane equation a ″ for the two side plate planes1x+b″1y+c″1z +1 ═ 0 and a ″)2x+b″2y+c″2z+1=0。
7. The method of claim 6 for locating structural stiffener welds in a point cloud, comprising: the step S3 specifically includes the following steps:
s301: let u be 1, n20, three-dimensional point Pu' is the u-th candidate weld point, X, obtained in step S105uRepresenting three-dimensional points Pu' X-axis coordinate, YuRepresenting three-dimensional points Pu' Y-axis coordinate, ZuRepresenting three-dimensional points Pu' Z-axis coordinates;
s302: calculating a three-dimensional point Pu' distance to floor plane dBAnd a distance d to the plane of the two side platess1And ds2Comprises the following steps:
s303: let u be u + 1; judgment of dBIf the length is less than 3mm, if the length is not less than 3mm, the step S302 is executed; if yes, go to step S304;
s304: judgment of ds1< 1mm or ds2If < 1mm is true, if not, go to step S302; if true, the three-dimensional point Pu' is the effective weld point, let n2=n2+1,Go to step S305;
s306: judging u < n1If yes, go to step S302; if not, obtaining the effective welding line point as Pv″′,v=1,2,…n2The total number of effective weld points is n2(ii) a And finishing the welding line positioning of the structural reinforcing rib point cloud.
8. The utility model provides a structural reinforcement welding seam positioning system in point cloud which characterized in that: the method comprises the following steps:
the selection module is used for screening candidate welding line points with rich curvature characteristics from the structural reinforcing rib point cloud;
the segmentation fitting module is used for segmenting the bottom plate plane of the structural reinforcing rib and two side plate planes intersected with the bottom plate plane and fitting a plane equation of the bottom plate plane;
and the positioning module is used for screening out final effective welding seam points from candidate welding seam points with rich curvature characteristics by taking the plane equation obtained in the segmentation fitting module as constraint so as to complete the welding seam positioning of the structural reinforcing rib.
9. A computer apparatus comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the computer program implements the steps of the method of structural reinforcement weld locating in a point cloud as claimed in any one of claims 1 to 7.
10. A computer readable storage medium having stored thereon a computer program, the program when executed by a processor implementing the steps of a method of locating a structural stiffener weld in a point cloud as claimed in any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111034042.3A CN113744245A (en) | 2021-09-03 | 2021-09-03 | Method and system for positioning structural reinforcing rib welding seam in point cloud |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111034042.3A CN113744245A (en) | 2021-09-03 | 2021-09-03 | Method and system for positioning structural reinforcing rib welding seam in point cloud |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113744245A true CN113744245A (en) | 2021-12-03 |
Family
ID=78735584
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111034042.3A Pending CN113744245A (en) | 2021-09-03 | 2021-09-03 | Method and system for positioning structural reinforcing rib welding seam in point cloud |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113744245A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114419046A (en) * | 2022-03-30 | 2022-04-29 | 季华实验室 | Method and device for recognizing weld of H-shaped steel, electronic equipment and storage medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112184804A (en) * | 2020-08-31 | 2021-01-05 | 季华实验室 | Method and device for positioning high-density welding spots of large-volume workpiece, storage medium and terminal |
CN113177983A (en) * | 2021-03-25 | 2021-07-27 | 埃夫特智能装备股份有限公司 | Fillet weld positioning method based on point cloud geometric features |
-
2021
- 2021-09-03 CN CN202111034042.3A patent/CN113744245A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112184804A (en) * | 2020-08-31 | 2021-01-05 | 季华实验室 | Method and device for positioning high-density welding spots of large-volume workpiece, storage medium and terminal |
CN113177983A (en) * | 2021-03-25 | 2021-07-27 | 埃夫特智能装备股份有限公司 | Fillet weld positioning method based on point cloud geometric features |
Non-Patent Citations (2)
Title |
---|
刘磊: "《面向散乱零件机器人抓取作业的立体图像处理与匹配技术》", 《中国优秀硕士学位论文全文数据库》, no. 03, 15 March 2020 (2020-03-15), pages 33 - 48 * |
张溪溪: "《微型复杂曲面零件散乱点云特征点提取》", 《机械设计与研究》, vol. 35, no. 05, 20 October 2019 (2019-10-20), pages 4 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114419046A (en) * | 2022-03-30 | 2022-04-29 | 季华实验室 | Method and device for recognizing weld of H-shaped steel, electronic equipment and storage medium |
CN114419046B (en) * | 2022-03-30 | 2022-06-28 | 季华实验室 | Method and device for recognizing weld of H-shaped steel, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7843448B2 (en) | Identification of occluded edge regions from 3D point data | |
Bosche et al. | Automated recognition of 3D CAD objects in site laser scans for project 3D status visualization and performance control | |
CN103678754B (en) | Information processor and information processing method | |
US7995054B2 (en) | Identification of edge regions from 3D point data | |
CN109544456A (en) | The panorama environment perception method merged based on two dimensional image and three dimensional point cloud | |
WO2017195228A1 (en) | Process and system to analyze deformations in motor vehicles | |
CN102016565A (en) | System, program product, and related methods for registering three-dimensional models to point data representing the pose of a part | |
CN110728753B (en) | Target point cloud 3D bounding box fitting method based on linear fitting | |
Triggs et al. | Automatic camera placement for robot vision tasks | |
CN108280852B (en) | Door and window point cloud shape detection method and system based on laser point cloud data | |
CN107622530B (en) | Efficient and robust triangulation network cutting method | |
Shmuel et al. | Active vision: 3d from an image sequence | |
CN109781003B (en) | Method for determining next optimal measurement pose of structured light vision system | |
CN107504917B (en) | Three-dimensional size measuring method and device | |
CN113744245A (en) | Method and system for positioning structural reinforcing rib welding seam in point cloud | |
JP7145770B2 (en) | Inter-Vehicle Distance Measuring Device, Error Model Generating Device, Learning Model Generating Device, Methods and Programs Therefor | |
CN115203778A (en) | Tunnel overbreak and underexcavation detection method and device, terminal equipment and storage medium | |
JP4836065B2 (en) | Edge tracking method and computer program therefor | |
Li et al. | Method for detecting pipeline spatial attitude using point cloud alignment | |
CN116858102A (en) | Weld joint size detection method, system, medium and equipment based on point cloud matching | |
CN114419046B (en) | Method and device for recognizing weld of H-shaped steel, electronic equipment and storage medium | |
Fang et al. | A vision-based method for narrow weld trajectory recognition of arc welding robots | |
Zhang et al. | Design and Research of Low-Cost and Self-Adaptive Terrestrial Laser Scanning for Indoor Measurement Based on Adaptive Indoor Measurement Scanning Strategy and Structural Characteristics Point Cloud Segmentation | |
CN110728222B (en) | Pose estimation method for target object in mechanical arm grabbing system | |
CN112069445A (en) | 2D SLAM algorithm evaluation and quantification method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |