三维散乱点云模型的特征点检测  

Feature Point Detection for 3D Scattered Point Cloud Model

作　　者：王丽辉[1,2] 袁保宗[1,2] 

机构地区：[1]北京交通大学信息科学研究所,北京100044 [2]现代信息科学与网络技术北京市重点实验室,北京100044

出　　处：《信号处理》2011年第6期932-938,共7页Journal of Signal Processing

基　　金：北京市优博项目(YB20081000401);国家973计划(2006CB303105;2004CB318110);国家自然科学基金项目(NO.60673109)

摘　　要：随着三维点云模型越来越受到人们的关注,如何对数据量大,无序的三维点云模型进行特征点检测也是近几年的研究热点。本文提出了基于曲率和密度的特征点检测算法,为每个数据点定义一个特征参数,这个参数由三部分组成:点到邻居点的平均距离;点的法向与邻居点法向夹角的和;数据点曲率。然后通过八叉树方法计算模型的数据点密度,将这个密度与模型到中心点的最大距离相除得到特征阈值,特征参数大于阈值的点就是特征点。本文计算时,检测模型的特征点只需用到三维点云模型的几何特征,如数据点法向,曲率和邻居点。实例表明本算法可准确地检测出散乱数据点云的特征点。3D point cloud data have received great attention,and feature detection of the unordered and the large mount point data is hot topic for the recent years.We presented a feature point detection algorithm based curvature and density.Firstly,feature parameter of each point is calculated.The parameter includes three parts;the average distance of the neighboring points,the sum of the normal angle between the point and its neighboring points,and the data point curvature.Secondly,by using Octree we define the density of data,which is then divided by the maximum distance from model center to data points and applied as the feature threshold to determine the feature points.The feature points are recognized when its density parameter is bigger than the threshold.In this article,we only use the geometry properties,such as normal of point,curvature and the neighboring points to detect the feature points.The experimental results show that our new approach can detect accurately the feature poinst for 3D scattered point data cloud models.

关 键 词：三维点云模型 特征参数 特征点检测 K近邻 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]