Supervised hyperspectral image classification using sparse logistic regression and spatial-TV regularization

In this paper, we propose a new model for hyperspectral image classification using spectral-spatial information. The main contributions of our paper are that we exploit the posterior distribution from both spectral and spatial information in the original hyperspectral data. The association potential in our model is a sparse multinomial logistic regression (SMLR) classifier and the interaction potential is a spatial-relevant total variation (TV) constraint upon the posterior distribution itself which encourages neighboring pixels to belong to the same class. The proposed model is solved by the alternating direction method of multipliers (ADMM); we enhance the spatial smoothness by expanding the spatial information from the fixed labeled samples to the whole data to further improve the classification accuracy. Experimental results with real hyperspectral data set validate that our proposed approach provides good performance when compared with other state-of-the-art methods.