中国激光, 2018, 45 (11): 1104004, 网络出版: 2018-11-15
一种密集管道点云数据自动分割算法 下载: 1303次
An Automatic Segmentation Algorithm for Dense Pipeline Point Cloud Data
测量 三维激光扫描 自动分割 随机采样一致性算法 密集管道 measurement three-dimensional laser scanning automatic segmentation random sampling consensus algorithm dense pipeline
摘要
提出了一种针对密集圆形管道点云数据的自动分割算法,通过八叉树结构将点云划分为若干个子块,并建立其空间邻域关系,采用基于法向量条件约束的随机采样一致性算法移除子块内的大区域平面,同时运用欧氏距离聚类和基于平滑条件约束的区域增长分割算法再次细化数据。实验结果表明:提出的自动分割算法在处理大小为6 m×12 m×16 m的点云空间数据时,4线程并行计算仅耗时9 s,精确率达到90%以上。因此,所提算法能够快速、准确地分割管道点云数据,具有较高的应用价值。
Abstract
An algorithm for the automatic segmentation of dense circular pipeline point cloud data is proposed. The cloud data is divided into several sub-blocks based on the octree structure, among which the spatial neighborhood relationship is established. The random sampling consensus algorithm based on the normal vector constraints is used to remove the large area plane within each sub-block and simultaneously, the Euclidean distance clustering and the region growing segmentation algorithm based on the smoothness constraints are used to refine the data again. The experimental results show that a 4 thread parallel computation only takes 9 s and the precision is larger than 90% when the proposed automatic segmentation algorithm is used to process the data with a size of 6 m×12 m×16 m in the point cloud space. Thus the proposed algorithm can be used for the quick and accurate segmentation of pipeline point cloud data and has a high application value.
黄凯, 程效军, 贾东峰, 胡旦华, 胡敏捷. 一种密集管道点云数据自动分割算法[J]. 中国激光, 2018, 45(11): 1104004. Huang Kai, Cheng Xiaojun, Jia Dongfeng, Hu Danhua, Hu Minjie. An Automatic Segmentation Algorithm for Dense Pipeline Point Cloud Data[J]. Chinese Journal of Lasers, 2018, 45(11): 1104004.