基于坡度自适应的机载LiDAR分割算法

Slope adaptive based segmentation for airborne LiDAR

本文提出了一种适用于离散LiDAR数据的区域生长算法:将离散点云数据重采样为规则格网,通过坡度自适应区域生长法分割规则格网,获得不同的面片;建立各个分割面片之间的拓扑关系,将分割面片划分为粗差、植被、建筑物和地面;检测原始激光脚点到DTM的距离,判断是否为地面点。文中采用ISPRS提供的测试数据验证了算法分割的有效性。

In this paper an improved region growing for discrete LiDAR data was algorithm presented ： firstly, the raw data was re- sampled to grid, density and usage intention, and the slope adaptive region growing was used to segment grid cells to different surface patches ; secondly, segmentation adjacency was established based on topological analysis, and the segmentations were classified as ter- rain, building, vegetation and others; finally, the grid cells classified as terrain were used to build approximation of the terrain surface, as DTM, and the raw data were accepted as terrain point within a given distance from the surface. To illustrate the effectiveness of the new procedure for LiDAR segmentation, one reference data set from ISPRS was tested.