A comparative study of several supervised target detection algorithms for hyperspectral images

Target detection using hyperspectral images has gained popularity in recent years. In this paper, we present a preliminary comparative study of several simple, easy to use, and supervised target detection algorithms, including constrained signal detector (CSD), adaptive CSD, matched subspace detector (MSD), and adaptive subspace detector (ASD). Actual hyperspectral data have been used in our studies. Receiver operating characteristics (ROC) curves were used to compare the various algorithms. It was found that ASD yielded the best performance under the same set of conditions.