Ground Radar Target Classification Using Singular Value Decomposition and Multilayer Perceptron

Abstract

The paper deals with classification of ground radar targets. A received radar signal backscattered from a ground radar target was digitized and in the form of radar signal matrix utilized for a feature extraction based on Singular Value Decomposition. Furthermore, singular values of a backscattered radar signal matrix, as a target feature, were utilized for Radar Target Classification by multilayer perceptron. In the learning phase of a multilayer perceptron we used the learning target set and in the testing phase the testing target set was used. The learning and testing target sets were created on the basis of real ground radar targets.