PROJECT TITLE :

A MAP-Based Approach for Hyperspectral Imagery Super-Resolution - 2018

ABSTRACT:

In this Project, we have a tendency to propose a novel single image Bayesian super-resolution (SR) algorithm where the hyperspectral image (HSI) is the only source of data. The main contribution of the proposed approach is to convert the ill-posed SR reconstruction problem in the spectral domain to a quadratic optimization drawback in the abundance map domain. In order to do therefore, Markov random field primarily based energy minimization approach is proposed and proved that the answer is quadratic. The proposed approach consists of 5 main steps. First, the amount of endmembers in the scene is set using virtual dimensionality. Second, the endmembers and their low resolution abundance maps are computed using simplex identification via the splitted augmented Lagrangian and absolutely constrained least squares algorithms. Third, high resolution (HR) abundance maps are obtained using our proposed most a posteriori based mostly energy function. This energy function is minimized subject to smoothness, unity, and boundary constraints. Fourth, the HR abundance maps are additional enhanced with texture preserving strategies. Finally, HR HSI is reconstructed using the extracted endmembers and the improved abundance maps. The proposed methodology is tested on three real HSI data sets; particularly the Cave, Harvard, and Hyperspectral Remote Sensing Scenes and compared with state-of-the-art various strategies using peak signal to noise ratio, structural similarity, spectral angle mapper, and relative dimensionless international error in synthesis metrics. It's shown that the proposed methodology outperforms the state-of-the-art methods in terms of quality while preserving the spectral consistency.