Fusion of Remote Sensing Multispectral and Hyperspectral Images using Adaptive Sparse Representation

In this paper, we propose a novel spatial and spectral fusion method for remote sensing satellite multispectral and hyperspectral images based on adaptive sparse representation. By combining the spectral information from hyperspectral image, which is characterized by low spatial resolution but high spectral resolution and the spatial information from multispectral image, which is featured by high spatial resolution but low spectral resolution, this method aims to generate the fused data with both high spatial and high spectral resolutions. In the proposed method, according to the current pattern, an optimum dictionary is selected for coding in the bands of multispectral image which is a resistant and local procedure for the selection of the patches. The results of the simulation show the performance of the proposed algorithm compared to advanced techniques of image fusion