基于超体素的LiDAR点云粘连目标分割算法

Research of Segmentation Algorithm for LiDAR Point Cloud Based on Supervoxel

针对点云地物分割结果中存在的粘连现象,结合三维点云的空间分布和颜色信息,引入过分割方法将点云集划分为超体素,并构建加权图模型。在此基础上,利用归一化分割方法实现点云粘连区域的目标分割。针对树木、建筑物的实验结果表明,该方法对树木之间、树木与建筑物之间的粘连具有良好的分类效果。

Due to the existence of adhesion phenomenon in the point cloud segmentation, by using combined with the spatial distribution and color information of the three-dimensional point cloud, this paper proposes an over-segmentation method to divide the point clouds into supervoxels, and then gives a weighted graph model. Hence, we realize the segmentation of point clouds adhesion areas using graph cut. In view of the trees, buildings, the experiment results show that the method has a good classification effect about the adhesion between the trees and buildings.