LAUSR

Hyperspectral imagery (HSI) with a high spectral resolution contains hundreds and even thousands of spectral bands, and conveys abundant spectral information, which provides a unique advantage for target detection. A number of classical target detectors have been proposed based on the linear mixing model (LMM) and sparsity-based model. Compared with the LMM, sparsity-based detectors present a better performance on dealing with the spectral variability. Despite the great success of the sparsity-based model in recent years, one problem with all state-of-the-art sparsity-based models still exist: the target dictionary is formed via the target training samples that are selected from the global image scene. This is an improper way to construct target dictionary for hyperspectral target detection since the priori information is usually a given target spectrum obtained from a spectral library. Besides, target training samples selected from the global image scene are usually insufficient, which results in the problem that the target training samples and background training samples are unbalanced in the data volume, causing a deteriorated detection model. To tackle these problems, this paper constructs a target dictionary construction-based method, then proposes the constructed target dictionary-based sparsity-based target detection model and the constructed target dictionary-based sparse representation-based binary hypothesis model, which are called TDC-STD and TDC-SRBBH, respectively. Both of the proposed algorithms only need a given target spectrum as the input priori information. By using the given target spectrum for pre-detection via constrained energy minimization, we choose the pixels that have large output values as target training samples to construct the target dictionary. The proposed algorithms were tested on three benchmark HSI datasets and the experimental results show that the proposed algorithms demonstrate outstanding detection performances when compared with other state-of-the-art detectors.