Multi-Mode Radar Target Detection and Recognition Using Neural Networks

Abstract

In typical radar systems, the process of recognizing a target requires human involvement. This human element makes radar systems not fully reliable due to unstable performance that varies between operators. This paper describes an intelligent radar system which addresses this problem in a border surveillance environment. The proposed radar system is capable of automatically detecting and then classifying different targets using an artificial neural network trained with the Levenberg-Marquardt algorithm. The training and test sets presented to the neural network are composed by high-resolution Inverse Synthetic Aperture Radar pictures obtained by the radar's detection module. Simulation results show that the intelligent radar system can reliably detect and distinguish the different objectives. Moreover, the radar system can outperform human operators and another radar system that deals with similar objectives. These results indicate that future intelligent systems can potentially replace human radar operators in this critical security setting.