文献类型：会议论文

英文题名：BUILDING HEIGHT EXTRACTION FROM OVERLAPPING AIRBORNE IMAGES IN URBAN ENVIRONMENT USING COMPUTER VISION APPROACH

作者：Li, Shiming[1] QingwangLiu[1] ZengyuanLi[1] Chen, Erxue[1] Zhang, Jianbing[2]

第一作者：李世明

通信作者：Li, SM[1]

机构：[1]Chinese Acad Forestry, Inst Forest Resources Informat Tech, 1 Dongxiaofu, Beijing 100091, Peoples R China;[2]China Univ Petr, 18 Fuxue Rd, Beijing 102249, Peoples R China

会议论文集：IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

会议日期：JUL 23-28, 2017

会议地点：Fort Worth, TX

语种：英文

外文关键词：building height; overlapping aerial imagery; object-based image analysis; Structure from Motion

年份：2017

摘要：Estimating and measuring building height has become one of the significant factors in urban planning, legal and illegal construction inspection, urban disaster warning and assessing, as well as providing initial mapping data for creating three dimensional (3D) digital city models. In this paper we examine the feasibility of extracting building height information using computer vision algorithms with Structure from Motion procedures (SfM) from overlapping airborne images in urban environment. 3D land surface models can be generated from airborne images, and then DTM is subtracted from the DSM to form the nDSM layer. Using object-based image analysis, building height can be differentiated from bush, trees, and others by rulesets of spectral features, geometric features and contextual information. The accuracy of the building height based on orthorectified images and nDSM from airborne imagery was at a similar level to those based on airborne LiDAR data from the same study area.