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：2013
卷号：XL-1/W2
页码：419-423
DOI：10.5194/isprsarchives-XL-1-W2-419-2013
出版社：Copernicus Publications
摘要：The increasing availability in multiple data sources acquired by different sensor platforms has provided the great advantages for desired result achievement. This paper proposes the use of both mobile laser scanning (MLS) data and Unmanned Aerial Vehicle (UAV) images for 3D model reconstruction. Due to no available exterior orientation parameters for UAV images, the first task is to georeference these images to 3D points. In order to fast and accurate acquire 3D points which are also easy to be found the corresponding locations on UAV images, automated pole extraction from MLS was developed. After georeferencing UAV images, building roofs are acquired from those images and building walls are extracted from MLS data. The roofs and the walls are combined to achieve the complete building models
关键词：Mobile laser scanning; UAV images; Building wall detection; Building roof extraction; Pole extraction; 3D models; 3D building reconstruction
