Combination of remote sensing and geocoded data for satellite image interpretation based on neural networks

Presents an image interpretation system for automatic cartography using neural networks. In this frame, the results of two neural networks are combined for producing a final map. The first network deals with radiometric satellite data and the second one with geocoded data (such as digital elevation models, road maps, and hydrographic network). In both cases, the authors propose new methods for, on the one hand, the maximum likelihood method, and on the other hand, expert knowledge based classification using production rules with certainty factors. The authors also introduce future works, that is to say rule extraction