AN ITERATIVE TECHNIQUE FOR THE DETECTION OF LAND-COVER TRANSITIONS INMULTITEMPORAL REMOTE-SENSING IMAGES

We propose a supervised nonparametric technique, based on the ''compou nd classification rule'' for minimum error, to detect land-cover trans itions between two remote-sensing images acquired at different times, Thanks to a simplifying hypothesis, the compound classification rule i s transformed into a form easier to compute, In the obtained rule, an important role is played by the probabilities of transitions, which ta ke into account the temporal dependence between two images. In order t o avoid requiring that training sets be representative of all possible types of transitions, we propose an iterative algorithm which allows the probabilities of transitions to be estimated directly from the ima ges under investigation, Experimental results on two Thematic Mapper i mages confirm that the proposed algorithm may provide remarkably bette r detection accuracy than the ''Post-Classification Comparison'' algor ithm, which is based on the separate classifications of the two images .