MAP-MRF estimation for multiresolution fusion of remotely sensed images

In this paper we propose a novel approach for multiresolution fusion for the satellite images based on modeling low resolution multispectral image. Given a high resolution panchromatic (Pan) image and a low spatial but high spectral resolution multispectral (MS) image acquired over the same geographical area, the goal is to obtain a high spatial resolution MS image. To solve this problem use a maximum a posteriori (MAP) - Markov random field (MRF) based approach. Each of the low spatial resolution MS images are modeled as the aliased and noisy versions of their high resolution versions. The high spatial resolution MS images to be estimated are modeled separately as discontinuity preserving MRF that serve as a prior information. The unknown MRF parameters are estimated from the available high resolution Pan image using homotopy continuation method. The proposed approach has the advantage of having minimum spectral distortion in the fused image as we do not directly operate on the Pan pixel intensities. Our method do not require registration of MS and Pan images. Also the number of MRF parameters to be estimated from the Pan image are limited as we use homogeneous MRF. The time complexity of our approach is reduced by using the particle swarm optimization (PSO) in order to minimize the final cost function. We demonstrate the effectiveness of our approach by conducting experiments on real image captured by Landsat-7 Enhanced Thematic Mapper Plus (ETM+) satellite sensor acquired over the city of Trento, Italy.