高斯函数约束下的多判别参数散乱点云边缘检测  

Multi-Discrimination Parameter Scattered Point Cloud Edge Detection Under Constraint of Gaussian Function

作　　者：杨文桥 郑力新 朱建清[1,2] 董进华 郑义姚[1,2] 刘颖 汪泰伸 YANG Wenqiao;ZHENG Lixin;ZHU Jianqing;DONG Jinhua;ZHENG Yiyao;LIU Ying;WANG Taishen(College of Engineering,Huaqiao University,Quanzhou 362021,China;Industrial Intelligence and System Fujian University Engineering Research Center,Huaqiao University,Quanzhou 362021,China)

机构地区：[1]华侨大学工学院,福建泉州362021 [2]华侨大学工业智能化与系统福建省高校工程研究中心,福建泉州362021

出　　处：《华侨大学学报（自然科学版）》2021年第1期97-102,共6页Journal of Huaqiao University(Natural Science)

基　　金：国家自然科学基金项目面上资助项目(61976098);福建省厦门市科技计划资助项目(3502Z20173045);华侨大学研究生科研创新能力培育计划资助项目(18014084013)。

摘　　要：设计一种散乱点云数据边缘检测算法,从而快速、精确地提取边缘特征.该算法以点云的局部特征为基础,通过分析点云数据各点的法向特性,构建各点k近邻法向夹角特征、曲率特征、距离特征,并在高斯函数的约束下完成点云边缘特征的检测.利用公共数据进行多组实验,对比不同算法下的检测效果.结果表明:该算法提取点云边缘特征的速度更快、效果更好.A scattered point cloud data edge detection algorithm is designed to extract edge features quickly and accurately.The algorithm is based on the local characteristics of the point cloud.By analyzing the characteristics of the normal vector of each point of the point cloud data,the k-nearest neighbor normal angle feature,the curvature feature,and the distance feature of each point are constructed to complete the point cloud edge feature detection under the constraint of the Gaussian function.Using public data to conduct multiple sets of experiments to compare the detection effects of different algorithms.The results show that the proposed algorithm is faster and better at extracting edge features of point clouds.

关 键 词：点云边缘检测 法向夹角 欧氏距离 高斯函数 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]