基于改进的区域生长三维点云分割  

Three-Dimensional Point Cloud Segmentation Algorithm Based on Improved Region Growing

作　　者：李仁忠[1] 刘阳阳[1] 杨曼[1] 张缓缓[1] Li Renzhong;Liu Yangyang;Yang Man;Zhang Huanhuan(School of Electics and Information, Xi＇an Polytechnic University, Xi＇an, Shaanxi 710048, China)

机构地区：[1]西安工程大学电子信息学院,陕西西安710048

出　　处：《激光与光电子学进展》2018年第5期319-325,共7页Laser & Optoelectronics Progress

基　　金：中国纺织工业联合会科技指导性项目(2017071)

摘　　要：点云分割是点云数据处理的关键环节,区域生长因在三维点云分割中易于实现、便于使用而得到了广泛应用,然而由于点云特征的不确定性及种子点选取不合理导致传统区域生长法局部分割性能不稳定。针对此问题,提出一种改进的区域生长分割方法。通过估算点云数据曲率大小,并将曲率最小点设置为种子节点,即从点云数据最平坦的区域开始生长,以减少分段总数,再根据点云数据的局部特征确定生长准则。实验结果表明,该方法不仅能有效地对点云数据进行分割,而且解决了传统区域生长分割不稳定的问题,提高了点云分割的精确性和可靠性。The segmentation of point cloud play a key role in the processing of point cloud data, the regional growth is widely used in three-dimensional point cloud segmentation because it is easy to implement and use. However, due to the uncertainty of the point cloud characteristics and the unreasonable selection of seed point, the traditional regional growth method has the instability of local segmentation performance. To resolve this problem, an improved method of regional growth segmentation is presented, we set the minimum curvature point to the seed point by estimating the magnitude of the curvature of point cloud data. The reason for this is that the point with the minimum curvature is located in the flat area , growth from the flattest area can reduce the total number of segments, then the growth criteria is determined according to the local characteristics of point cloud data. Experimental results show that this method can divide the point cloud data effectively, solve the problem of the instability of the traditional regional growth, and improve the accuracy and reliability of point cloud segmentation.

关 键 词：机器视觉 点云分割 区域生长 点云滤波 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]