Automated Road Network Extraction Using Collaborative Linear and Surface Models

The availability of very high spatial resolution satellite images over urban areas is recent. The very high spatial resolution enables a real representation of streets on a map, but generates a significant increase of noise. A state-of the-art on road and street extraction with the evolution from linear to surface models for road and street is proposed. Then, a method for extracting urban street networks from very high spatial resolution images is presented. It models streets as a surface and is built on a cooperation between linear and surface representation of streets. Its goal is to meet the need for an automatized building of maps. The method has been applied on images from different sensors and with different urban types. An innovative protocol for a quantitative assessment of the results compared to human interpretation has shown its generic aspect, as well as its robustness with respect to noise.