Hyperspectral Image Fusion Based on Multistage Guided Filter

In this paper, a novel multistage guided filter based hyperspectral (HS) pansharpening algorithm is presented. The intensity component (INT) from interpolated HS image is generated using adaptive IHS method and the optimization equation is solved to get weight vector at first. Then, the paper proposes a multistage guided filter strategy to extract the spatial detail by using panchromatic image and INT image as a guidance image respectively, which is different from the traditional methods. In this way, the detail information can be obtained in a consistent manner. The obtained spatial details information is finally added into the interpolated HS image to generate fused HS image. Experimental results based on different remote sensing images indicate that the presented approach improves performance in the spatial and spectral aspects.