Fusion based resolution enhancement in hyperspectral images

Abstract

Increasing the low spatial resolution of hyperspectral images (HSIs) improves the performance of applications in which the HSIs are used. In this study, a fusion based method is proposed to increase the resolution of HSIs. In the proposed method, low resolution (LR) HSI is fused with the high resolution (HR) RGB image to obtain the HR HSI. In this approach, instead of using the spectral images as in the conventional methods, RGB image is used with the abundance maps of the HSI estimated from the linear unmixing and the spatial resolution is enhanced using these maps. In this method, firstly, endmembers are estimated and LR abundance maps are obtained. Then, HR abundance maps are obtained by minimizing an energy function, which is constructed from the LR abundance maps with the HR RGB image. Finally, HR HSI is obtained from these HR abundance maps. The method is tested with real HSIs. Main contribution of the method is converting fusion problem to a quadratic optimization problem in the abundance map domain without any assumption or prior knowledge. The proposed method solves the fusion problem with a computational time much lower than the state-of-the-art fusion based methods with a competing performance.