Landcover Classification in MRF Context Using Dempster Shafer Fusion for Multisensor Imagery.

This work deals with multisensor data fusion to obtain landcover classification. The role of featurealevel fusion using the Dempster-hafer rule and that of data-level fusion in the MRF context is studied in this paper to obtain an optimally segmented image. Subsequently, segments are validated and classification ace curacy for the test data is evaluated. Two examples of data fusion of optical images and a synthetic aperture radar image are presented, each set having been acquired on different dates. Classification accuracies of the technique proposed are compared with those of some recent techniques in literature for the same image data. [ABSTRACT FROM AUTHOR]