AN ADVANCED NEURAL NETWORK-BASED APPROACH FOR MILITARY GROUND VEHICLE RECOGNITION IN SAR AERIAL IMAGERY

Abstract

The paper presents a novel neural network approach for automatic target recognition (ATR) in the synthetic aperture radar (SAR) aerial imagery; this is applied to identify military ground vehicles. The proposed ATR algorithm consists of a processing cascade with the following stages: (a) object detection using a pulse-coupled neural network (PCNN) segmentation module; (b) a first feature selection module using Gabor filtering (GF); (c) a second feature selection module using principal component analysis (PCA); (d) a support vector machine (SVM) classifier improved by using virtual training data generation (VTDG) with concurrent self-organization maps (CSOM). The proposed model has been applied for the recognition of three classes of military ground vehicles of the former Soviet Union represented by the set of 2987 images of the MSTAR public release database. The experimental results have confirmed the method effectiveness, leading to a total success rate of 97.36%.