Classification of remote sensing imaging by an ICM method with constraints: Application in land cover cartography

In this paper we present a Markovian method of classification of the satellite images, this method is based on a minimization of the posterior energy by the ICM method (iterated conditional mode) with the introduction of constraints of the spatial context. The originality of our method is the variability over the iterations of a temperature factor like in the simulated annealing algorithm (SA), indeed, the algorithm refines classification by re-estimating the statistics of the classes according to the previous iteration and by giving more and more importance to the contextual information through the parameter of temperature T. The implemented method is tested in an application of cartography of the land cover. The results are satisfactory comparing to other no-contextual classification methods such as the ISODATA and Kmeans.