Unsupervised change detection on remote sensing images using non-local information and Markov Random Field Models

In this paper, inspiring by the idea of non-local means filter, the non-local information is introduced into the Markov Random Field Models (MRF) based change detection. A new distance based on non-local information of the neighborhood area of remote sensing image is defined. Then the image information is map to a higher dimension feather space. The initial cluster classification is performed in the high dimension non local space. And it provides the initial value for the MRF change detection. Both the data term and the smoothing term in the MRF based change detection are defined in this frame of non-local information. Different multi-temporal images with different resolutions and different locations are experimented. And better performances are achieved in the experiments when comparing with two other method.