Change Detection in a Topographic Building Database Using Submetric Satellite Images

Submetric satellite imagery (Pleiades, GeoEye) offers advantages for map update purposes, e.g. an interesting ground resolution, a good reactivity and the ability to capture wide areas. Experiments on the use of such stereoscopic images for 2D change detection among building objects of GIS topographic database are presented in this paper. Two approaches have been tested. The first one extracts land cover from satellite ortho-images and additional information (correlation DSM-DTM, database) and compares building objects of this classification to those of the database. The second one creates a pseudo-DSM from height information of database building objects combined with a DTM and compares it to a correlation DSM computed from satellite images. Obtained results are quite encouraging even if the correctness rate remains too low for an operational use.