使用冯·米塞斯分布提取特征的点云精简方法  

Point Cloud Simplification Method Using von Mises-Fisher Distribution to Extract Features

作　　者：刘源 左小清[1] 李勇发 杨栩 周定义 黄琨 Liu Yuan;Zuo Xiaoqing;Li Yongfa;Yang Xu;Zhou Dingyi;Huang Kun(Faculty of Land Resources Engineering,Kunming University of Science and Technology,Kunming 650093,Yunnan,China)

机构地区：[1]昆明理工大学国土资源工程学院,云南昆明650093

出　　处：《激光与光电子学进展》2023年第2期331-341,共11页Laser & Optoelectronics Progress

摘　　要：针对点云精简算法提取特征时较为依赖传统参数、特征提取不全面和特征边界易丢失等问题,提出一种使用冯·米塞斯(vMF)分布提取特征的点云精简方法。该方法首先利用邻域重心点构建向量,通过与法向之间的夹角关系设置阈值划分曲面,降低噪声对细节特征的影响;然后利用冯·米塞斯分布提取曲面点的优先度,实现全局特征提取;最后基于特征进行八叉树分级精简。实验结果表明:所提方法可有效提取细节特征,相比于基于曲率、Hausdorff距离的方法所提取到的特征,有着更好的特征提取效果;利用基于曲率、栅格、随机的精简算法与所提方法进行关于重建结果、3D偏差、定量分析的对比,证明所提精简方法效果更优。所提方法为点云特征提取和精简提供一种新的思路。Addressing the issues of point cloud simplification algorithms that rely on traditional parameters when extracting features,which is not comprehensive and easy to lose feature boundaries,this study provides a point cloud simplification approach using von Mises-Fisher(vMF) distribution to extract features.This method first uses a neighborhood center point to create a vector,divides the surface through the threshold of the relationship with the normal direction,reduces the impact of noise on the finer features.Then,the priority of surface points is extracted by using vMF distribution to realize global feature extraction.Finally,octree hierarchical simplification is operated based on features.Experiments described that the method in this study can successfully extract detailed features.Compared with methods based on curvature and Hausdorff distance,it has a better feature extraction effect.The simplification algorithms based on curvature,grid,and random,and the proposed method are used to analyze the reconstruction results,3D bias,and quantitative analysis,results prove that the proposed simplification method is more effective.The proposed simplification method provides a fresh approach for point cloud feature extraction and simplification.

关 键 词：点云精简 特征提取 冯·米塞斯分布 八叉树 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]