An accurate pose measurement method of workpiece based on rapid extraction of local feature points

Abstract

Ceramic sanitary products with complex curved surfaces are generally fragile and difficult to clamp. If the industrial robot is utilized to realize the automatic grinding of such products, the precise positioning of the product is required firstly. In this paper, an accurate pose measurement system for complex curved surface parts is designed by point cloud registration algorithm. In order to improve the stability of the system, this paper combines the advantages of normal vector features and fast point feature histogram (FPFH) features, and proposes a point cloud registration algorithm based on the rapid extraction of local feature points. Experimental results verify that the improved algorithm has improved both efficiency and accuracy, and the system can effectively achieve accurate positioning of products.

References

[1] LiuS, GeW M. Research on intelligent grinding trajectory of industrial robot based on particle swarm optimization[J]. Journal of Tianjin University of Technology, 2020, 36(06):8-12(in Chinese)

[2] KongX X. Identifying geomorphological changes of coastal cliffs through point cloud registration from UAV images[J]. Remote sensing, 2021, 13(16):3152

[3] ShuZ C, CaoS X, JiangQ, et al.. Pairwise registration algorithm for large-scale planar point cloud used in flatness measurement[J]. Sensors, 2021, 21(14): 4860

[4] GuoY, XiaY H, YangX Y, et al.. A comparative study of large karst cave point cloud registration in various scanning modes[J]. Survey review, 2020, 52(374): 383-393

[5] TsaiC Y, HuangC H. Indoor scene point cloud registration algorithm based on RGB-d camera calibration[J]. Sensors, 2017, 17(8):1874

[6] MohammadK, KhalilK, HossionA. Employing Nelder-Mead and gravitational search algorithm methods in point clouds registration process[J]. Procedia technology, 2015, 19: 112-119

[7] ShiG G, GaoX G, DangX H. Improved ICP point cloud registration based on KD-tree[J]. International journal of earth sciences and engineering, 2016, 9(5):2195-2199

[8] SunJ H, ZhangJ, ZhangG J. An automatic 3D point cloud registration method based on regional curvature maps[J]. Image and vision computing, 2016, 56: 49-58

[9] ZhangX T, YangB, LiY H, et al.. A method of partially overlapping point clouds registration based on differential evolution algorithm[J]. PLOS one, 2019, 13(12):e0209227

[10] LiL, CaoX Y, SunJ. Three-dimensional point cloud registration based on normal vector angle[J]. Springer india, 2019, 47(4): 585-593

[11] RanY Y, XuX B. Point cloud registration method based on sift and geometry feature[J]. Optik, 2020, 203: 163902

[12] RenS Y, ChenX D, CaiH H, et al.. Color point cloud registration algorithm based on hue[J]. Applied sciences, 2021, 11(12): 5431