光学精密工程2025，Vol.33Issue(19)：3106-3120,15.DOI:10.37188/OPE.20253319.3106
三维点云的邻域分布快速配准
Rapid registration for neighborhood distribution of 3D point cloud
摘要
Abstract
A fast point-cloud registration method based on neighborhood distribution features is proposed to address the high computational cost of traditional high-dimensional feature extraction and the slow per-formance of dense registration algorithms that rely on coarse-fine two-step feature matching.First,three deep geometric features of neighboring points are defined,and a low-dimensional,multi-scale neighbor-hood distribution descriptor is introduced to substantially reduce feature-computation complexity while en-hancing descriptor discriminability for efficient characterization of local point-cloud properties.Second,a rapid coarse-registration scheme is developed using the neighborhood distribution descriptor:feature points are selected according to the global undulation degree and neighborhood distribution direction;initial corre-spondences are established based on the neighborhood distribution descriptor;and Euclidean-distance con-straints between point pairs are strengthened to remove incorrect matches,enabling efficient and accurate coarse alignment.Finally,to accelerate dense registration,the iterative closest point(ICP)algorithm is improved using a k-dimensional tree and voxel-grid downsampling,and a quadratic fine-registration strate-gy is employed to correct downsampling-induced errors,thereby further improving fine-registration accura-cy and efficiency.Experiments on Stanford models and industrial part point clouds demonstrate that,com-pared with conventional feature-descriptor-based methods,the proposed approach increases registration ac-curacy by over 22%and reduces computation time by more than 43%,confirming its effectiveness,ro-bustness,and practical applicability for rapid registration of object-surface point clouds acquired from differ-ent viewpoints.关键词
点云配准/邻域分布特征/匹配点对优化/迭代最近点/体素化网格法Key words
point cloud registration/neighborhood distribution feature/matched point pair optimization/iterative closest point/voxelized grid method分类
计算机与自动化引用本文复制引用
余永维,方荣,杜柳青,刘豪,刘中元..三维点云的邻域分布快速配准[J].光学精密工程,2025,33(19):3106-3120,15.基金项目
国家自然科学基金资助项目(No.52375083) （No.52375083）
重庆英才资助项目(No.QYC20220207232,No.cstc2024ycjh-bgzxm0052) （No.QYC20220207232,No.cstc2024ycjh-bgzxm0052）
重庆教委科研重大资助项目(No.KJZD-M202401101,No.KJZD-M202501102) （No.KJZD-M202401101,No.KJZD-M202501102）
重庆技术创新与应用资助项目(No.CSTB2022TIAD-CUX0017) （No.CSTB2022TIAD-CUX0017）
重庆理工大学研究生创新资助项目(No.gzl-cx20253073) （No.gzl-cx20253073）
精密机械检测技术与装备工程中心资助项目(No.2023PTTS001) （No.2023PTTS001）
