用多种策略从机载Lidar数据中提取建筑脚点

Picking up Footprints of Building from Airborne Lidar Data with Multi-strategies

设计了一种采用多种策略的建筑脚点提取方法,针对建筑脚点提取中的两个关键步骤———数据分类和建筑脚点分割,分别提出和引入了邻近关系和r半径点密度,从仅反映单次反射的DSM数据中,直接提取出建筑表面点。

The pro and con of all classic algorithms for picking up building footprints are analyzed. And then an arithmetic with multi-strategies is put forward to pick up the building footprints from airborne Lidar data. A workflow of this arithmetic is given. Aiming at the deficiencies in settling out data classification, a new measure named neighbor relation is put forward and as a result, points on vegetation surface are effectively separated and eliminated from points on building surface. Aiming at the deficiencies in settling out data classification, r-radius point density is introduced and as a result, the way to choose seed points are improved better and the perform efficiency in segmentation is advanced.