基于LIDAR数据的建筑物轮廓提取

The study on building boundary extraction based on LIDAR data

建筑物轮廓的准确提取是建筑物三维重建中最重要的一步。本文在研究已有建筑物轮廓提取方法的基础上,针对LIDAR离散的点云数据,提出了一种自动快速提取建筑物轮廓信息的方法。首先通过点云数据生成城市的数字表面模型(DSM)和数字地面模型(DTM)相减计算得出规则化的数字表面模型(nDSM),进而将地面点和非地面点进行分类;其次,考虑到地物的几何特性,提出一种8邻域搜索的方法对非地面点点云进行分割,得到建筑物表面点云;最后运用基于梯度图的边界跟踪的方法来获取建筑物的轮廓信息。实验表明:该方法能有效地提取建筑物轮廓。

Building boundary extraction is the key approach for 3D reconstruction of building. In this paper, a new automatic method of extracting building boundary for LIDAR random point clouds is presented based on the existed extracting methods. Firstly, ground points and non-ground points are classified with the help of nDSM which are generated by the subtraction of DSM and DTM. Then, given the geometric features of objects, a new algorithm is brought forward to segment building points by searching 8 adjacent fields of point. Finally, the method of boundary tracing based on gradient maps is used to extract building boundaries. The experiment shows that building boundaries are extracted efficiently with this proposed approach.