文章基本信息

标题：ROAD EXTRACTION IN URBAN AREAS SUPPORTED BY CONTEXT OBJECTS
本地全文：下载
作者：Stefan Hinz
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：2000
卷号：XXXIII Part B3(/1+2)
页码：405-412
出版社：Copernicus Publications
摘要：In this contribution, we introduce our concept for automatic road extraction in urban areas using high resolution aerialimagery and dense height information. For facilitating the extraction we use a hierachical road model comprising differentroad elements (markings, lanes, junctions, road network) at different scales as well as context objects of roads like buildingsand vehicles. Global contextual knowledge about roads in residential areas helps us to focus on certain image parts,and thus, to cope with the inherently high complexity of urban scenes. Road extraction is then performed in a mainly datadriven fashion starting with the extraction of the basic road elements at the lowest level of the road model and reachingthe top level, i.e., a topologically consistent road network, with the final steps of processing. On each step in between,hypotheses for the respective road elements are generated and validated, and thus, evidence about roads is collected andtransfered to the next step. Since urban roads are often characterized by rather dense traffic the detection of vehicles andvehicle convoys plays a major role. The results of the currently implemented modules give us rise to further realize thisconcept.
关键词：Image Understanding; Road Extraction; Context