High level adaptive fusion approach: application to land cover change prediction in satellite image databases.

The purpose of this paper is to propose an adaptive possibility fusion approach to take into account the reliability of different decisions related to the prediction of land cover change. The proposed approach reduces the influence of unreliable information and thus enhances the relative weight of reliable information. Decisions about changes are obtained by applying previous works and represented as spatiotemporal trees. These trees are combined to obtain more accurate and complete ones. Validation of the approach shows good performances of the proposed approach in improving the prediction of land cover change.