A new approach to building identification from very-high-spatial-resolution images

The extent and rapidity of the urban growth induce a number of socio-economic and environmental conflicts everywhere. In order to reduce these problems, urban planners need to integrate spatial information in planning tools. High expectations are placed on very-high-spatial-resolution (VHSR) imagery. However, conventional interpretation methods do not seem to be adapted to this new type of images. The aim of our study is to develop a new approach for semi-automatic building identification, more specifically to individual housing, from VHSR images. The proposed methodology has been applied to Ikonos and Quickbird images in urban areas. Results show the capacity of our method for building identification, in spite of some limitations.