Automatic radar target recognition using superresolution music 2D images and self-organizing neural network

Abstract

The key problem in any decision-making system is to gather as much information as possible about the object or the phenomenon under study. In the case of the radar targets the frequency and angular information is integrated to form a radar image, which has high information content. A supper-resolution technique (MUSIC 2D) is used in the paper in order to reconstruct the target image. A supervised self-organizing neural network was developed to classify the images obtained in this way for ten different radar targets in an anechoic chamber.