Automatic GIS Updating from High Resolution Satellite Images

Among all the issues involved in Geographic Information Science, automating the update of 2D building databases is a crucial and challenging issue. Such an update usually starts out with a manual change detection process. The main goal of this paper is to present a new method to automate the detection of changes in a 2D building database, starting from satellite images. The workflow of our approach is divided into 2 phases. Primitives, extracted from multiple images and from a correlation Digital Elevation Model (DEM), are firstly collected for each building and matched with primitives derived from the existing database to achieve a final decision about acceptance or rejection. A specific algorithm, based on the DEM and a computed Digital Terrain Model (DTM), is subsequently used to extract the new buildings of the scene. The method is here introduced and tested in two test areas, very different regarding the land use and topography. The outcomes of the method are assessed and show the good performance of our system, especially in terms of completeness, robustness and transferability.