Sparse Weighting for Pyramid Pooling-Based SAR Image Target Recognition

In this study, a novel feature learning method for synthetic aperture radar (SAR) image automatic target recognition is presented. It based on spatial pyramid matching (SPM), which represents an by concatenating the pooling vectors that are obtained from different resolution sub-regions. This exploits dependability of obtaining weighted features generated SPM The determined residuals sparse representation. aims at enhancing weights in sub-regions located and suppressing background. representation SAR discriminative robust to speckle noise background clutter. Experiments performed Moving Stationary Target Acquisition Recognition public dataset prove advantageous performance presented algorithm over several state-of-the-art methods.