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：1998
卷号：XXXII Part 4
出版社：Copernicus Publications
摘要：This paper presents a knowledge-based method for automatic road extraction from aerial images. The method uses ahybrid control strategy in which hypotheses of roads are generated in a bottom-up process, and a top-down procedure isapplied to verify the generated hypotheses. In this paper, a road model is proposed, which includes the geometric andradiometric properties of roads and relationship between roads in low- and high-resolution images. These propertiesand relationship are formulated as rules in PROLOG and stored in the knowledge base. The structures and relationshipsof roads yielded from images are stored as facts in the knowledge base. The hypotheses of roads are generated byapplying the corresponding rules to the derived facts. To remove the ambiguity of the generated hypotheses, structuralinformation of road surface and topological information of road networks are used. The missing road segments arepredicted in the process of verification using topological information. An image in Hunter Valley, New South Wales, hasbeen tested in this study. The results show that the road network is successfully extracted using the proposed method.
