SPECTRAL UNMIXING BASED ON JOINT SPARSITY AND TOTAL VARIATION USING REMOTE SENSING DATA

Abstract

@IJRTER-2019, All Rights Reserved 27 Abstract—Hyperspectral imaging belongs to a class of technique called spectral imaging or spectral analysis. The objective of hyperspectral imaging is to find the spectrum for each pixel Present in the image of a scene. Hyperspectral unmixing is an emerging topic in hyperspectral image analysis to distinguish the materials present in an image and thereby finding the proportion of each material in an image. The distinct materials are called as end members and proportion values are called as abundance maps. Hyperspectral unmixing is an important technique for estimating fraction of different land cover types from remote sensing imagery. It is the process of estimating constituent endmembers and their fractional abundances present at each pixel in a hyperspectral image. A hyperspectral image is often corrupted by several kinds of noise. Joint Sparsity and Total variation (JSTV) addresses the hyperspectral unmixing problem in a general scenario that considers the presence of mixed noise. The Joint sparsity has been formulated to exploit the abundance maps. A totalvariation based regularization has also been utilized for modeling smoothness of abundance maps. The split-Bregman technique has been utilized to derive an algorithm for solving resulting optimization problem. Results indicate that the proposed joint sparsity and total variation methods are able to successfully perform unmixing on synthetic data and real hyperspectral imagery while preserving endmember spatial information with smooth abundance maps.