层次化点云边界快速精确提取方法研究

Research on the method of rapid and accurate extraction of boundary points by hierarchy

为了提高依据邻近点最大夹角提取边界点方法的提取效率,提出了一种层次化快速精确提取边界点的方法。先对任意采样点检索其R邻域内点集,依据R邻域内点集重心点坐标与采样点的距离粗提取边界点,然后将粗提取的边界点及其邻域点投影至微切平面,通过各邻近点与采样点的方向向量求取相邻向量间的最大夹角,再依据最大夹角精提取边界点。通过理论分析和点云数据实验验证了该算法的可行性。结果表明,该算法相较于传统的方法,能缩短22.11%的运行时间,但精度降低5.23%;相较于其它层次化提取方法,在缩短10.99%的运行时间的同时精度提高7.17%。该研究为点云3维重建中边界提取提供了参考。

In order to improve the extraction efficiency of the boundary point extraction method based on the maximum Angle of adjacent points,a hierarchical fast and accurate boundary point extraction method was proposed.R in the neighborhood at any sampling point set was firstly retrieved,followed by the crude extraction of boundary point according to the distance from the center of gravity point coordinates to the sampling point in the R neighborhood point set.The crude extract of boundary points and their neighborhood points were then projected to the tangent plane,and the maximum angle between adjacent vectors was calculated through the adjacent points and sampling points in the direction of the vector,the final accurate boundary point was then extracted based on the maximum angle.Through theoretical analysis and point cloud data experiment,the feasibility of the algorithm was verified.The results show that this algorithm can respectively shorten the running time by 22.11%and the accuracy by 5.23%compared with the traditional method,and can respectively shorten the running time by 10.99%and improve the accuracy by 7.17%compared with other hierarchical extraction methods.This study provides a reference for boundary extraction in point cloud 3-D reconstruction.