NEW ROTATION-INVARIANT FEATURES FOR RADAR TARGET RECOGNITION

Sophisticated modem radar systems have made it possible to build up de tailed electromagnetic images of an object in the radar beam. This has generated interest in pattern recognition methods for radar target re cognition. A feature of these high-resolution images is that some peak s relate to interactions between structures, as opposed to direct spec ular scattering. We propose a new method using interaction (multiple b ounce) terms to compute a truly rotation-invariant feature for radar t argets to be used for recognition. The effectiveness of the method is demonstrated by applying it to real data obtained from measurements in a compact range and demonstrating that the resulting feature sets cou ld be used to effectively classify two similar target configurations.