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.

[1]  Te-Ming Tu,et al.  A new look at IHS-like image fusion methods , 2001, Inf. Fusion.

[2]  Bruno Aiazzi,et al.  Improving Component Substitution Pansharpening Through Multivariate Regression of MS $+$Pan Data , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[3]  J. G. Liu,et al.  Smoothing Filter-based Intensity Modulation: A spectral preserve image fusion technique for improving spatial details , 2000 .

[4]  Jian Sun,et al.  Guided Image Filtering , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Roger L. King,et al.  An Efficient Pan-Sharpening Method via a Combined Adaptive PCA Approach and Contourlets , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[6]  Naoto Yokoya,et al.  Coupled Nonnegative Matrix Factorization Unmixing for Hyperspectral and Multispectral Data Fusion , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[7]  Michael Möller,et al.  An Adaptive IHS Pan-Sharpening Method , 2010, IEEE Geoscience and Remote Sensing Letters.