A MRF-Based approach for a multisensor land cover mapping of mis-resgistered images

The traditional land cover mapping (LCM) algorithms assume that images are perfectly registered. In practice, this assumption may not always be valid since these images may be acquired from different sensor platforms, or at different time which may suffer small variations in platform flight paths. As a result, it is imperative to incorporate the registration error into the land cover mapping algorithm. In this paper, we propose a joint LCM and image registration algorithm under the Markov random field model. Here, the expectation-maximization algorithm is employed to search for the optimum LCM as well as the map parameters. Our result shows that the proposed MRF-Based approach can increase the accuracies of the classification maps as well as the map parameter estimation.