This paper proposes an approach for automatic road extraction in aerial imagery which exploits the scale-space behavior of roads in combination with geometric constrained snake-based edge extraction. The approach not only has few parameters to be adjusted, but for the first time allows for a bridging of shadows and partially occluded areas using the heavily disturbed evidence in the image. The road network is constructed after extracting crossings of various shape and topology. Reasonable results are obtained which are evaluated based on ground truth.