Supervised hyperspectral image classification combining sparse unmixing and spatial constraint

In this paper, a new supervised classification method, combines spectral and spatial information, is proposed. The method is based on the two following facts. First, a hyperspectral pixel can be sparsely represented by a linear combination of the dictionary consists of a few labeled samples. If any unknown hyperspectral pixel lies in the subspace spanned by some labeled-class samples, it will be classified to this labeledclass. And it is to solve a fully constrained sparse unmixing problem and the classification is relaxed to be determined by the sparse vector whose nonzero entries correspond to the weights of the selected labeled samples. Second, since the nearest neighbors probably belong to the same class, a spatial constraint is introduced. Alternating direction method of multipliers (ADMM) and the Graph Cut based method are then used to solve the spectral-spatial model. Finally, our method is applied to two real hyperspectral data sets (Indian Pines and University of Pavia) for classification. Experimental results show that the proposed method outperforms many of the state-of-the-art methods.