Hyperspectral imagery target detection based on supplement dictionary

Sparse representation algorithm has been successfully applied to the field of hyperspectral imagery (HSI) target detection and achieved nice results. However, the traditional target detection algorithm only uses the spectral information of the hyperspectral imagery and the spatial information has not been considered and there are only a few training samples in the traditional dictionary. They have some bad effects on the target detection. For the lack of those, hyperspectral imagery target detection algorithm based on supplement dictionary has been proposed. The new algorithm improved the traditional dictionary and added the spatial information to the process of target detection. The simulation experiments are carried out to prove that the new algorithm does work and the new algorithm can improve the accuracy in target detection.