Multisensor Information Fusion Application to SAR Data Classification

Abstract

A new multisensor information fusion classifier is introduced and applied to land cover classification using SAR composites. This classifier aims at the integration of multi-source, contextual and prior to information in a single and a homogeneous framework. Statistical and fuzzy logic approaches have been employed in the experiments. Fuzzy membership maps to different thematic classes are first calculated using classes and sensors a priori knowledge. These maps are then iteratively updated using spatial contextual information. A classification rule is associated to different iterations. The confidence map constitutes an important issue in order to evaluate the classification process complexity and the validity of the used assumptions. Finally, after compared the statistical properties of the fusion result by different methods, the proposed method showed satisfied result.