43 T - Rex : Tum Research on Road Extraction

In this paper we report on research on road extraction at TUM (Technische Universität München). We propose a scheme for road extraction in rural areas that integrates three different modules with specific strengths. The first module employs local grouping and uses multiple scales and context to reliably extract most parts of the road network. In order to connect these parts, the second module exploits the network characteristics of roads for global grouping. The third module completes the network based on an analysis of path lengths within the network. An evaluation of the results shows that the system benefits from the integration of different types of knowledge within the road extraction scheme. In addition to the scheme for rural areas, we present first results of an approach for road extraction in urban areas that focuses on the substructure of roads (markings, lanes) and related objects (vehicles).