Target Discrimination for SAR ATR Based on Scattering Center Feature and K-center One-Class Classification

Target discrimination plays an important role in the typical synthetic aperture radar (SAR) automatic target recognition (ATR) system. The conventional discrimination features roughly describing the difference between the target and the clutter are useful to discriminate the target from natural clutter, but these features may not well discriminate the target from the artificial clutter. To solve the above problem, a new algorithm for target discrimination is proposed based on the scattering center feature and the K-center one-class classification in this paper. The amplitudes and locations of the scattering centers have not been used as discrimination feature to our best knowledge, even though the distributions of the scattering centers associated with the targets are different from those of the natural clutter and artificial clutter. Then, since the scattering center feature is a typical kind of point set feature, we improve the K-center one-class classification based on Hausdorff distance (HD), where HD is a distance measure for the point set feature. Experimental results based on the measured MiniSAR dataset show that the discrimination performance of the scattering center feature is better than that of the conventional discrimination features, especially for the artificial clutter.