Sparse representation within disconnected spatial support for target detection in hyperspectral imagery

Target detection (TD) is one of the fundamental tasks in hyperspectral imagery (HSI) processing. Sparse representation (SR) as a novel tool is powerful in accurate detection of target of interest. In this paper, SR approach within disconnected spatial support is proposed for effective TD in HSI. For conventional sparse representation, an HSI pixel is represented as a sparse vector whose non-zero entries correspond to the weights of the selected training atoms from a structured dictionary. For improved sparse representation, spatial correlation and spectral similarity of pixels in the whole image are exploited in this context. The pixels within disconnected spatial are automatically determined using similarity compare strategy. Accordingly, a solution based on greedy pursuit algorithms is also given to solve the extended optimization problem in recovering the desired sparse representation. Comprehensive experiments on two different datasets using both visual inspection and quantitative evaluation are carried out. The results from the two datasets have indicated that the proposed approaches help to generate improved results in terms of efficacy and efficiency.