Mapping of Urban Areas : a multiresolution modeling approach for semi-automatic extraction of streets

Abstract : A new method to hierarchically extract urban road networks from very high spatial resolution space-borne imagery (spatial resolution of 2 m and higher) is presented. An explicit and generic model of 'streets' was developed according to a multiresolution analysis of images associated with a wavelet transform. The method consists of two processing steps the multiresolution extraction of edges of streets, and, if existing, the multiresolution extraction of strips of streets. The extraction of sides is achieved by the use of a multiscale representation of images, and the extraction of strips is done by a modeling of distinct substructures of streets at different characteristic scales achieved by the application of the associated wavelet transform. The method would help cartographers in their cartographic works in urban areas by a partial automation of tasks.