An iterative technique for the detection of land-cover transitions in multitemporal remote-sensing images

We propose a supervised nonparametric technique, based on the “compound classification rule” for minimum error, to detect land-cover transitions between two remote-sensing images acquired at different times. Thanks to a simplifying hypothesis, the compound classification rule is transformed into a form easier to compute. In the obtained rule, an important role is played by the probabilities of transitions, which take into account the temporal dependence between two images. In order to 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 images under investigation. Experimental results on two Thematic Mapper images confirm that the proposed algorithm may provide remarkably better detection accuracy than the “Post-Classification Comparison” algorithm, which is based on the separate classifications of the two images.