基于局部熵的点云精简算法  

A point cloud reduction algorithm based on local entropy

作　　者：董嘉敏 田华 DONG Jiamin;TIAN Hua(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：《现代电子技术》2020年第1期20-23,27,共5页Modern Electronics Technique

基　　金：国家自然科学基金（61403329）

摘　　要：针对目前流行的三维物体激光扫描仪获取的点云数据量大,冗余度高等问题,提出一种基于信息熵的点云精简算法。首先,定义数据点的曲率、点到邻域点重心的距离、点到邻域点的平均距离的倒数,三者乘积为权值积;然后,使用K-means聚类算法划分点云数据,根据类内估计曲率差值区分特征区域与非特征区域;最后,针对特征区域,利用提出的精简方法精简点云。实验结果表明,该方法计算相对简单,能够有效避免孔洞现象,同时,更好地保留了点云数据的原始物理特征。A point cloud reduction algorithm based on information entropy is proposed to deal with the large amount of point cloud data and high redundancy produced by the popular three⁃dimensional laser scanner.Firstly,the product of curvature of the data points,the distance from the points to the center of gravity of the neighborhood points,and the reciprocal of the average distance from the points to the neighborhood points is defined as the product of weight;secondly,the K⁃means clustering algo⁃rithm is used to classify the point cloud data,and the characteristic region and the non⁃characteristic region are distinguished ac⁃cording to the estimated curvature difference;finally,for the characteristic region,the proposed reduction algorithm is used to reduce the point cloud.The experimental results show that the calculation process of the proposed algorithm is relatively simple,which can effectively avoid the hole phenomenon,and preserve the original physical characteristics of the point cloud data better.

关 键 词：点云精简 信息熵 K-MEANS算法 特征区域区分 点云数据 曲率估计 

分 类 号：TN911-34[电子电信—通信与信息系统] TP391.9[电子电信—信息与通信工程]