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：2012
卷号：XXXIX-B3
页码：149-154
DOI：10.5194/isprsarchives-XXXIX-B3-149-2012
出版社：Copernicus Publications
摘要：In this paper, we present an automatic approach for the derivation of 3D building models of level-of-detail 1 (LOD 1) from point clouds obtained from (dense) image matching or, for comparison only, from LIDAR. Our approach makes use of the predominance of vertical structures and orthogonal intersections in architectural scenes. After robustly determining the scene's vertical direction based on the 3D points we use it as constraint for a RANSAC-based search for vertical planes in the point cloud. The planes are further analyzed to segment reliable outlines for rectangular surface within these planes, which are connected to construct cuboid-based building models. We demonstrate that our approach is robust and effective over a range of real-world input data sets with varying point density, amount of noise, and outliers
关键词：Point Cloud Segmentation; Surface Detection; Building Recognition; Building Reconstruction
