Multi-View Automatic Target Recognition using Joint Sparse Representation

We introduce a novel joint sparse representation based multi-view automatic target recognition (ATR) method, which can not only handle multi-view ATR without knowing the pose but also has the advantage of exploiting the correlations among the multiple views of the same physical target for a single joint recognition decision. Extensive experiments have been carried out on moving and stationary target acquisition and recognition (MSTAR) public database to evaluate the proposed method compared with several state-of-the-art methods such as linear support vector machine (SVM), kernel SVM, as well as a sparse representation based classifier (SRC). Experimental results demonstrate that the proposed joint sparse representation ATR method is very effective and performs robustly under variations such as multiple joint views, depression, azimuth angles, target articulations, as well as configurations.