Urban street mapping using Quickbird and Ikonos images

This article addresses the problem of urban street mapping from new high resolution satellite images. The proposed algorithm is divided in two sequential modules: a topologically correct graph of the street network is first extracted, and streets are then extracted as surface elements. The graph of the network is extracted by a following algorithm which minimizes a cost function. The surface extraction algorithm makes use of specific active contours (snakes) combined with a multiresolution analysis (MRA) for minimizing the problem of noise. This reconstruction phase is composed of two steps: the extraction of street segments and the extraction of street intersections. Results of the street network extraction are presented on Quickbird and Ikonos images. Future prospects are also exposed. I. URBAN STREET NETWORK EXTRACTION Among possibilities of remote sensing for urban uses, extraction of street networks is an important issue. An upto-date knowledge of the street network is necessary for urban planning, map updating or estimation of atmospheric or noise pollution. Moreover, an assisted street extraction from remotely sensed data can highly help cities which do not have a cartography of their street network. While the developed extraction method systems yield to very encouraging results when applied on rather simple scenes (i.e. rural areas), the automatic extraction of objects in complex scenes, such as dense urban areas, has turned out to be very challenging. Few methods focus on urban areas (one can mention [1] or [2]). The recent possibility to have satellite images with a high spatial resolution (1 meter or less) has re-boosted the interest for street extraction in urban areas. This increased resolution enables a more accurate localization of the street sides as well as its extraction as a surface element. In return, it generates a higher complexity of the image and an increase of geometric noise (vehicles, trees along the street, occlusions, . . . ). II. THE PROPOSED APPROACH