期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：2008
卷号：XXXVII Part B3b
页码：153-156
出版社：Copernicus Publications
摘要：The research in the detection and feature extraction of typical objects in urban areas has intensified. In existing detection technologies, it has been shown that the LIDAR technique is very promising and suitable for 3D object detection mainly because 3D sub-randomly spatial distributed point cloud represented the object's geometrical structure can be obtained easily and instantly. In this paper, the points' spatial distribution characteristics of LIDAR data are analyzed firstly. Then, a slope-based planar-fitting filtering algorithm of LIDAR data is presented based on the analysis of the spatial distribution feature of LIDAR point cloud. This algorithm is used for the experimental research of data filtering and feature extraction of LIDAR data in urban area. The experimental result shows that this algorithm is able to extract more effectively objects feature
