Improving Joint Sparse Hyperspectral Unmixing by Simultaneously Clustering Pixels According to their Mixtures

In this paper, we propose a novel hierarchical Bayesian model for sparse regression problem to use in semi-supervised hyperspectral unmixing, which assumes the signal recorded in each hyperspectral pixel is a linear combination of members of the spectral library contaminated by additive Gaussian noise. To effectively utilize the spatial correlation between neighboring pixels during the unmixing process, we exploit a Markov random field to simultaneously group pixels to clusters associated with regions with homogeneous mixtures in a natural scene. We assume Sparse fractional abundances of members of a cluster to be generated from an exponential distribution with the same rate parameter. We show that our method can detect unconnected regions which have similar mixtures. Experiments on synthetic and real hyperspectral images confirm the superiority of the proposed method compared to alternatives.