Infrared small target detection in compressive domain

A novel approach to detect an infrared small target in the compressive domain is presented. First, the original infrared image is projected on a sensing matrix to obtain the measurement vector. Then the target and the background are recovered simultaneously from the measurements based on low-rank and sparse matrix decomposition. Experimental results indicate that the proposed method not only works well under different complex backgrounds with less data storage, but also outperforms some existing methods in both subjective and objective qualities.