基于加权最小二乘法曲率计算的点云精简算法  

Point clouds simplification algorithm based on weighted least squares surface fitting for curvature computation

作　　者：唐泽宇 高保禄 窦明亮 TANG Ze-yu;GAO Bao-lu;DOU Ming-liang(College of Information and Computer,Taiyuan University of Technology,Jinzhong 030600,China)

机构地区：[1]太原理工大学信息与计算机学院

出　　处：《计算机工程与设计》2019年第6期1606-1610,1659,共6页Computer Engineering and Design

摘　　要：针对目前点云精简算法的曲率计算不准确、精度不高等问题,提出一种基于加权最小二乘法曲率计算的点云精简算法。使用点的离群率作权值;使用二次曲面为计算模型;使用加权最小二乘曲面拟合生成曲面,计算曲面的平均曲率。对于点云的精简,结合使用K-means聚类算法和基于泊松分布的特征点检测算法进行精简。实验结果表明,该算法能够有效提升曲率计算的准确度,避免了孔洞现象,更好保留了点云数据的原始物理特征。Aiming at the problem that the precision of curvature computation is low in the process of point cloud simplification, a method of curvature calculation was proposed. The outlier of points was used as weights, while a quadric surface was used as calculation model and a weighted least square method was used to generate surfaces. In the process of point clouds simplification, K-means algorithm and feature point detection algorithm based on Poisson distribution were used to simplify point clouds. Experimental results show that the proposed methods have high precision, the number of holes is reduced in the process of clouds simplification, and more features of the point clouds are retained.

关 键 词：最小二乘法 加权最小二乘法 曲率 特征点 K-MEANS 泊松分布 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]