Incorporating an Adaptive Image Prior Model Into Bayesian Fusion of Multispectral and Panchromatic Images

Abstract

Reconstruction of a sharpened multispectral (MS) image from its coarser measurements, namely the low spatial resolution MS and panchromatic (Pan) images, is a severely illposed inverse problem which requires the definition of an appropriate prior model. This letter incorporates an adaptive Markov random field (MRF)-based prior model into a Bayesian framework to recover the desired MS image. The proposed MRF-based prior model combines the high frequency details of the Pan image with the spectral relation between the bands of the MS image into a single energy function. Consequently, unlike most pansharpening methods, not directly injecting the spatial information of the Pan image into the fused product, the proposed method offers a fused product with minimum spectral distortion, along with perfectly enhanced spatial resolution. Visual and quantitative assessments of the fused products of the proposed method compared to those of some famous pansharpening methods prove the superiority of the proposed method.