Satellite image classification based on multi-source information-fusion with possibility theory

Presents a multi-sources information-fusion method for satellite image classification. The main characteristics of this method are the use of possibility theory to handle the uncertainty of pixel classification, and the ability to mix numeric sources (the satellite image spectral bands) and symbolic sources (expert knowledge about geographical localisation of classes and out-image data for example). First the authors present the basic concepts of possibility theory and the fusion method used. Then they present how they have computed possibility measures for the numeric sources on the one hand, and for the symbolic sources on the other hand. Finally they introduce the fusion of the numeric and symbolic sources.