中文摘要：

将建筑物立面数据从散乱无序的车载LiDAR点云中分割出来是一项繁琐而艰巨的任务.本文提出基于基础地理数据辅助的分割方法：首先对基础地理数据进行要素精简,提取有效的建筑物轮廓数据;然后将提取数据转换到车载LiDAR点云数据所在坐标系中,实现坐标基准的统一;再根据建筑物立面特征设置合理的建筑物轮廓缓冲阈值,对建筑物立面点云进行自动分割;最后采用合理的质量评价机制,对分割结果进行检核和评价,实现分割结果的质量控制.实验表明文中方法简单有效.

英文摘要：

It＇s a tedious and difficult task to segment the building facades data from vehicle-borne Li-DAR point cloud data, which is commonly considered as scattered and disorderly point clouds. In this paper, the author proposed a segmentation method based on the fundamental geographic data： firstly, simplify the features of fundamental geographic data, and extract effective contour information of the buildings; secondly, convert the coordinate system of fundamental geographic data to that of Vehicle-borne Li- DAR point cloud to realize the unification of coordinate system; thirdly, set a suitable buffer threshold value for building contour, and segment out the point cloud data of building facades automatically; lastly, take a reasonable quality assessment mechanism to check and evaluate the segmentation results with their quality control. Experiment shows that the proposed method would be simple and effective.