Remote Sensing Image Fusion Based on Generalized IHS Transformation and Compressive Sensing

In order to improve the quality of the images fused between panchromatic and multispectral images, a remote sensing image fusion algorithm based on generalized intensity-hue-saturation (GIHS) transformation and compressive sensing is proposed in this paper.Firstly, low-resolution intensity component of low-resolution multispectral images is obtained by GIHS transformation.Then, compressive sensing model from high-resolution intensity component to low-resolution intensity component and high-resolution panchromatic image is constructed.Consequently the high-resolution intensity component is recovered by using the compressive sensing theory.Finally, panchromatic image in the GIHS-based fusion method is substituted by the recovered high-resolution intensity component, and the fused multispectral images are obtained.With the high-resolution intensity component, the spectral distortion of the fused images is reduced greatly.The proposed algorithm is tested on Geoeye-1and QuickBird images.The experimental results show that, compared with traditional methods, the proposed algorithm not only improve spatial resolution of the multispectral images but also keep the spectral information better.