Author(s): LUAN Xuechen, FAN Hongchao, YANG Bisheng, LI Qiuping, State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Engineering Research Center for Spatio-temporal Data Smart Acquisition and Application, Wuhan University, Guangdong Ruitu Information Systems Co, Ltd., College of Surveying and Geo-informatics, Tongji University, School of Geography and Planning, Sun Yat-sen University
Pages: 327-331
Year: 2014 Issue:  3
Journal: Geomatics and Information Science of Wunan University
Keyword:  GIS-T; arterial roads; road networks; Gestalt; road hierarchies;
Abstract: This paper presents a shape-based approach to extract arterial roads from urban road networks is appropriate to the high level-of-detail found in volunteered geographic information(VGI) datasets.Firstly,the method calculates several shape descriptors of each polygon surrounded by roads.Secondly,some candidate arterial-road polygons are classified as seeds from all polygons with shape descriptors using support vector machine(SVM).Finally,based on seed polygons,a regional growing method is proposed to connect the arterial-road features according to the Gestalt concept.An experiment shows that this method achieves good and effective arterial road extraction results,reflecting the constructed skeleton in urban network.Furthermore,a comparison analysis of high-level roads attributes was also carried out to confirm the consistency between constructed road levels and our detected arterial roads.