High-precision registration method for multi-view point cloud of welding workpiece

Abstract

The invention discloses a high-precision registration method for multi-view point clouds of welding workpieces, which is characterized by comprising the following steps of: firstly, carrying out spot welding on welding grooves of two workpieces to obtain a to-be-welded workpiece; a structured light camera is used for collecting multiple frames of original point clouds of a to-be-welded workpiece at different visual angles, background point clouds are removed, and multiple frames of workpiece point clouds at different visual angles are obtained; then extracting the point cloud of the upper surface of the workpiece containing the welding groove, and performing coarse registration on the point cloud of the upper surface of each frame of the workpiece; the mass weight of each point in the point cloud of the upper surface of the workpiece is calculated, then the point clouds of adjacent frames are subjected to precise registration through a weighted ICP algorithm to optimize the poses of the adjacent frames, precise splicing of the point clouds of the upper surface of the workpiece at multiple frames of different view angles is achieved, and the complete point cloud of the upper surface of the workpiece containing the welding groove is obtained; the method has the advantages that the influence of point cloud distortion on point cloud precise registration is well reduced, and the precision of point cloud registration is improved, so that the precision of subsequent three-dimensional model reconstruction and the precision of automatic welding are ensured.

Description

Technical Field

[0001] The present invention relates to the field of intelligent welding technology, and in particular to a high-precision registration method for multi-view point clouds of welding workpieces. Background Art

[0002] Traditional workpiece welding is usually done manually, but manual welding has problems such as poor consistency and low efficiency, and cannot meet the current mass production welding industry needs. In order to improve the welding quality and efficiency of workpieces, robot automated welding is gradually replacing manual welding.

[0003] Before automatically welding the workpiece, it is necessary to first collect the morphological features of the workpiece to be welded. Due to the limitations of the field of view of the current 3D scanning equipment, it is impossible to directly obtain the complete point cloud data of the target object. Therefore, it is necessary to collect point cloud data of different perspectives of the target object at different angles, and then perform registration processing (i.e. point cloud registration) on the obtained point cloud data of different perspectives. The accuracy of point cloud registration will directly affect the accuracy of subsequent 3D reconstruction. At present, when using a structured light camera to collect the point cloud on the surface of the target object, there will inevitably be a certain degree of distortion, and point cloud distortion will affect the subsequent point cloud precise registration, that is, it will affect the accuracy of point cloud registration, thereby affecting the accuracy of subsequent automatic welding. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a high-precision registration method for multi-view point clouds of welding workpieces, which can reduce the influence of point cloud distortion on subsequent point cloud precise registration, so as to improve the accuracy of point cloud registration.

[0005] The technical solution adopted by the present invention to solve the above technical problems is: a high-precision registration method for multi-view point clouds of welding workpieces, comprising the following specific steps: (1) Spot welding is first performed on the welding grooves of the two workpieces to connect them together to obtain the workpieces to be welded; (2) Install a structured light camera on the end arm of the robot, use the structured light camera to collect multiple frames of original point clouds of the workpiece to be welded at different perspectives, and remove the background point clouds of the workpiece to be welded from the multiple frames of original point clouds to obtain multiple frames of workpiece point clouds at different perspectives; (3) Divide the workpiece side point cloud in the workpiece point cloud into independent clusters, and extract the workpiece upper surface point cloud containing the welding groove from the clusters; (4) Unify the upper surface point clouds of the workpiece at different perspectives in each frame into the robot base coordinate system, and perform coarse registration on the upper surface point clouds of the workpiece at different perspectives in each frame; (5) Calculate the quality weight of each point in the workpiece upper surface point cloud, and then use the weighted ICP algorithm to accurately align the point clouds of adjacent frames to optimize the poses of adjacent frames, so as to achieve accurate stitching between the workpiece upper surface point clouds of multiple frames with different perspectives, and obtain a complete workpiece upper surface point cloud including the welding groove.

[0006] Furthermore, in the step (2), the background point cloud in the original point cloud is removed by a random sampling consistency algorithm.

[0007] Furthermore, in the step (3), the workpiece side point cloud in the workpiece point cloud is divided into independent clusters by using the NV-DBSCAN clustering algorithm.

[0008] Furthermore, the specific process of the NV-DBSCAN clustering algorithm is as follows: Calculate the point cloud to be clustered The normal vector of each point in constitutes the normal vector set , for a point in the point cloud P , , if its corresponding normal vector n i , n j Satisfies the relationship: , where: γ is the threshold for determining whether two points satisfy the normal vector consistency constraint, then the definition point and Satisfy the normal vector consistency constraint and move the point and Grouped into the same cluster of point clouds.

[0009] Furthermore, in the step (5), the quality weight of each point in the workpiece surface point cloud is calculated as follows: For a point in the point cloud P , by calculating the optical center and point of the structured light camera P The angle between the connected straight line and the camera optical axis α To define the point P The off-axis weight function f(α) of the point cloud quality is: ,in: α 1 is the angle α The maximum value of is the off-axis weight function f( α )’s decay exponent, The larger the value is, the larger the off-axis weight function f( α )along with α The increase of decay is faster; At the same time, the direction vector of the camera optical axis is z, and the point in the point cloud P The local normal vector in the point cloud is n, then the camera optical axis and the normal vector n Angle β for: , through the angle β To define the point P The point cloud quality tilt weight function f( β ): ,in: β 1 is the angle β The maximum value of is the tilt weight function f( β )’s decay exponent, The larger the value is, the more inclined the weight function f( β )along with β The increase of decay is faster.

[0010] Furthermore, in step (5), the specific steps of the weighted ICP algorithm are: (5-1) Define the rough registration result of step (4) as the initial transformation matrix T 0 ; (5-2) Corresponding point matching: The point clouds collected from each frame form a multi-frame point cloud set , m is the number of point clouds, which is equal to the number of frames of the original point cloud of the workpiece to be welded collected by the structured light camera. Take one of the point clouds in Q is the source point cloud, k Initialized to 2, for the source point cloud Each point in , find its The nearest neighbor point in ; (5-3) Use Euclidean distance to measure point pair error : , T is the transformation matrix in the optimization process; (5-4) Calculate the weight value of the matching point pair ω i : ,in: Source point cloud Points in The off-axis weight function value of the point cloud quality is Source point cloud Points in The point cloud quality tilt weight function value; (5-5) By minimizing the weighted error, the transformation matrix T is iteratively optimized and the source point cloud is transformed using the weighted least squares method. All points in the target point cloud The weighted error sum of the Euclidean distances of the corresponding nearest neighbor points in is used as the optimization target: , where: T * It represents the optimal solution of the transformation matrix T obtained by iterative optimization, that is, the optimal transformation matrix, and m represents the number of point clouds; (5-6) When the number of iterations reaches the set maximum number of iterations or when the difference between the optimization variables is less than the threshold, the iteration is stopped and convergence is completed; (5-7), using the optimal transformation matrix T * Source point cloud Perform pose transformation and transform the source point cloud With the target point cloud Combine into a new point cloud and perform point cloud downsampling to obtain a new point cloud , complete the target point cloud Update of k = k +1 increases in sequence until k =m, stop updating; then the point cloud finally updated is the spliced ​​point cloud obtained by precise registration.

[0011] Compared with the prior art, the advantage of the present invention is that the method calculates the quality weight of each point in the point cloud, that is, by establishing a point cloud quality weight model to evaluate the accuracy of the point cloud collected by the structured light camera, and in the subsequent point cloud registration, provides weight parameters for the traditional ICP algorithm, and performs point cloud precise registration through the weighted ICP algorithm to more accurately match adjacent point clouds, thereby greatly reducing the impact of point cloud distortion on point cloud precise registration and improving the accuracy of point cloud registration, thereby ensuring the accuracy of subsequent three-dimensional model reconstruction and automatic welding. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 It is a flow chart of the present invention.

[0013] Figure 2 Schematic diagram of point cloud quality weight of the present invention. DETAILED DESCRIPTION

[0014] The present invention is further described in detail below with reference to the accompanying drawings.

[0015] like Figure 1 As shown, a high-precision registration method for multi-view point clouds of welding workpieces includes the following specific steps: (1) Spot welding is first performed on the welding grooves of the two workpieces to connect them together to obtain the workpieces to be welded; (2) Install a structured light camera on the end arm of the robot, use the structured light camera to collect multiple frames of original point clouds of the workpiece to be welded at different perspectives (i.e., different local parts), and use a random sampling consistency algorithm (i.e., RANSAC algorithm) to remove the background point clouds of the workpiece to be welded in the multiple frames of original point clouds to obtain multiple frames of workpiece point clouds at different perspectives; (3) The side point cloud of the workpiece in the workpiece point cloud is divided into independent clusters by using the NV-DBSCAN clustering algorithm, and the upper surface point cloud of the workpiece containing the welding groove is extracted from the clusters; The specific process of the NV-DBSCAN clustering algorithm is as follows: Calculate the point cloud to be clustered The normal vector of each point in constitutes the normal vector set , for a point in the point cloud P , , if its corresponding normal vector n i , n j Satisfies the relationship: , where: γ is the threshold for determining whether two points satisfy the normal vector consistency constraint, then the definition point and Satisfy the normal vector consistency constraint and move the point and Classify into the same cluster of point clouds; (4) Unifying the upper surface point clouds of the workpiece at different viewing angles in each frame into the robot base coordinate system, and coarsely registering the upper surface point clouds of the workpiece at different viewing angles in each frame; the specific method of coarse registration of point clouds is well known in the art and will not be elaborated here; (5) Calculate the mass weight of each point in the workpiece surface point cloud, such as Figure 2 As shown, specifically: For a point in the point cloud P , by calculating the optical center and point of the structured light camera P The angle between the connected straight line and the camera optical axis α To define the point P The off-axis weight function f(α) of the point cloud quality is: ,in: α 1 is the angle α The maximum value of is the off-axis weight function f( α )’s decay exponent, The larger the value is, the larger the off-axis weight function f( α )along with α The increase of decay is faster; At the same time, the direction vector of the camera optical axis is z, and the point in the point cloud PThe local normal vector in the point cloud is n , then the camera optical axis and the normal vector n Angle β for: , through the angle β To define the point P The point cloud quality tilt weight function f( β ): ,in: β 1 is the angle β The maximum value of is the tilt weight function f( β )’s decay exponent, The larger the value is, the more inclined the weight function f( β )along with β The increase of decay is faster; Then, the weighted ICP algorithm is used to precisely align the point clouds of adjacent frames to optimize the poses of adjacent frames, and to achieve accurate splicing of the workpiece upper surface point clouds of multiple frames with different perspectives, so as to obtain a complete workpiece upper surface point cloud including the welding groove; the specific steps of the weighted ICP algorithm are as follows: (5-1) Define the rough registration result of step (4) as the initial transformation matrix T 0 ; (5-2) Corresponding point matching: The point clouds collected from each frame form a multi-frame point cloud set , m is the number of point clouds, which is equal to the number of frames of the original point cloud of the workpiece to be welded collected by the structured light camera. Take one of the point clouds in Q is the source point cloud, k Initialized to 2, for the source point cloud Each point in , find its The nearest neighbor point in ; (5-3) Use Euclidean distance to measure point pair error : , T is the transformation matrix in the optimization process; (5-4) Calculate the weight value of the matching point pair ω i : ,in: Source point cloud Points in The off-axis weight function value of the point cloud quality is Source point cloud Points in The point cloud quality tilt weight function value; (5-5) By minimizing the weighted error, the transformation matrix T is iteratively optimized and the source point cloud is transformed using the weighted least squares method. All points in the target point cloud The weighted error sum of the Euclidean distances of the corresponding nearest neighbor points in is used as the optimization target: , where: T * It represents the optimal solution of the transformation matrix T obtained by iterative optimization, that is, the optimal transformation matrix, and m represents the number of point clouds; (5-6) When the number of iterations reaches the set maximum number of iterations or when the difference between the optimization variables is less than the threshold, the iteration is stopped and convergence is completed; (5-7), using the optimal transformation matrix T * Source point cloud Perform pose transformation and transform the source point cloud With the target point cloud Combine into a new point cloud and perform point cloud downsampling to obtain a new point cloud , complete the target point cloud Update of k = k +1 increases in sequence until k =m, stop updating; then the point cloud finally updated is the spliced ​​point cloud obtained by precise registration.

[0016] The protection scope of the present invention includes but is not limited to the above embodiments, and its protection scope is subject to the claims. Any replacement, deformation, and improvement of the technology that can be easily thought of by technicians in this field shall fall within the protection scope of the present invention.

Claims

1. A high-precision registration method for multi-view point clouds of welding workpieces, characterized in that The specific steps include: (1) Spot welding is first performed on the welding grooves of the two workpieces to connect them together to obtain the workpieces to be welded; (2) Install a structured light camera on the end arm of the robot, use the structured light camera to collect multiple frames of original point clouds of the workpiece to be welded at different perspectives, and remove the background point clouds of the workpiece to be welded from the multiple frames of original point clouds to obtain multiple frames of workpiece point clouds at different perspectives; (3) Divide the workpiece side point cloud in the workpiece point cloud into independent clusters, and extract the workpiece upper surface point cloud containing the welding groove from the clusters; (4) Unify the upper surface point clouds of the workpiece at different perspectives in each frame into the robot base coordinate system, and perform coarse registration on the upper surface point clouds of the workpiece at different perspectives in each frame; (5) Calculate the quality weight of each point in the workpiece upper surface point cloud, and then use the weighted ICP algorithm to accurately align the point clouds of adjacent frames to optimize the poses of adjacent frames, so as to achieve accurate stitching between the workpiece upper surface point clouds of multiple frames with different perspectives, and obtain a complete workpiece upper surface point cloud including the welding groove.

2. A high-precision registration method for multi-view point clouds of welding workpieces as claimed in claim 1, characterized in that: In the step (2), the background point cloud in the original point cloud is removed by a random sampling consistency algorithm.

3. A high-precision registration method for multi-view point clouds of welding workpieces as claimed in claim 1, characterized in that: In the step (3), the workpiece side point cloud in the workpiece point cloud is divided into independent clusters by using the NV-DBSCAN clustering algorithm.

4. A high-precision registration method for multi-view point clouds of welding workpieces as claimed in claim 3, characterized in that: The specific process of the NV-DBSCAN clustering algorithm is as follows: Calculate the point cloud to be clustered The normal vector of each point in constitutes the normal vector set , for a point in the point cloud P , , if its corresponding normal vector n i , n j Satisfies the relationship: , where: γ is the threshold for determining whether two points satisfy the normal vector consistency constraint, then the definition point and Satisfy the normal vector consistency constraint and move the point and Grouped into the same cluster of point clouds.

5. The high-precision registration method for multi-view point clouds of welding workpieces according to claim 1, characterized in that: In the step (5), the mass weight of each point in the workpiece surface point cloud is calculated as follows: For a point in the point cloud P , by calculating the optical center and point of the structured light camera P The angle between the connected straight line and the camera optical axis α To define the point P The off-axis weight function f(α) of the point cloud quality is: ,in: α 1 is the angle α The maximum value of is the off-axis weight function f( α )’s decay exponent, The larger the value is, the larger the off-axis weight function f( α )along with α The increase of decay is faster; At the same time, the direction vector of the camera optical axis is z, and the point in the point cloud P The local normal vector in the point cloud is n , then the camera optical axis and normal vector n Angle β for: , through the angle β To define the point P The point cloud quality tilt weight function f( β ): ,in: β 1 is the angle β The maximum value of is the tilt weight function f( β )’s decay exponent, The larger the value is, the more inclined the weight function f( β )along with β The increase of decay is faster.

6. A high-precision registration method for multi-view point clouds of welding workpieces as claimed in claim 5, characterized in that: In step (5), the specific steps of the weighted ICP algorithm are: (5-1) Define the rough registration result of step (4) as the initial transformation matrix T0; (5-2) Corresponding point matching: The point clouds collected from each frame form a multi-frame point cloud set , m is the number of point clouds, which is equal to the number of frames of the original point cloud of the workpiece to be welded collected by the structured light camera. Take one of the point clouds in Q is the source point cloud, k Initialized to 2, for the source point cloud Each point in , find its The nearest neighbor point in ; (5-3) Use Euclidean distance to measure point pair error : , T is the transformation matrix in the optimization process; (5-4) Calculate the weight value of the matching point pair ω i : ,in: Source point cloud Points in The off-axis weight function value of the point cloud quality is Source point cloud Points in The point cloud quality tilt weight function value; (5-5) By minimizing the weighted error, the transformation matrix T is iteratively optimized and the source point cloud is transformed using the weighted least squares method. All points in the target point cloud The weighted error sum of the Euclidean distances of the corresponding nearest neighbor points in is used as the optimization target: , where: T * It represents the optimal solution of the transformation matrix T obtained by iterative optimization, that is, the optimal transformation matrix, and m represents the number of point clouds; (5-6) When the number of iterations reaches the set maximum number of iterations or when the difference between the optimization variables is less than the threshold, the iteration is stopped and convergence is completed; (5-7), using the optimal transformation matrix T * Source point cloud Perform pose transformation and transform the source point cloud With the target point cloud Combine into a new point cloud and perform point cloud downsampling to obtain a new point cloud , complete the target point cloud Update of k = k +1 increases in sequence until k =m, stop updating; then the point cloud finally updated is the spliced ​​point cloud obtained by precise registration.

Images