Plane segmentation and fitting method of point clouds based on improved density clustering algorithm for laser radar

作     者：Xu, Xiaobin Luo, Minzhou Tan, Zhiying Zhang, Min Yang, Hao 

作者机构：Hohai Univ Coll Mech & Elect Engn Changzhou 213022 Peoples R China Hohai Univ Jiangsu Key Lab Special Robot Technol Changzhou 213022 Peoples R China 

出 版 物：《INFRARED PHYSICS & TECHNOLOGY》 (红外物理学与技术)

年 卷 期：2019年第96卷

页      面：133-140页

核心收录：

学科分类：070207[理学-光学] 07[理学] 08[工学] 0804[工学-仪器科学与技术] 0803[工学-光学工程] 0702[理学-物理学] 

基　　金：National Natural Science Foundation of China Fundamental Research Funds for the Central Universities [2017B07814] Opening Fund of Jiangsu Key Laboratory of Special Robot Technology [2017JSJQR02] 

主　　题：Segmentation Laser radar SLAM Clustering algorithm Variable threshold 

摘      要：Plane segmentation and fitting method of point clouds based on improved density clustering algorithm is put forward. We proposed the plane segmentation and fitting framework, which comprises of four steps: coordinate transformation, filtering, coarse segmentation, fine segmentation, plane fitting. The global coordinates of laser radar are deduced. Abnormal points are removed using statistical filtering based on Gaussian distribution. After filtering, Point clouds are segmented roughly adopting improved density clustering algorithm with proposed threshold, which is originally related to the resolution of laser radar. The point clouds are segmented furthermore with normal vector, which could make up for shortcomings, which are over-segmentation and under segmentation. Finally planes are fitted with normal vector and centroid point. The laser radar was designed, and plane segmentations and fitting were carried out. The experimental results show that it is effective and automatic for plane segmentation with proposed method.