Polarimetric SAR Image Classification Using Radial Basis Function Neural Network

Abstract

This paper presents a robust radial basis function (RBF) network based classifier for polarimetric synthetic aperture radar (SAR) images. The proposed feature extraction process utilizes the covariance matrix, the gray level co-occurrence matrix (GLCM) based texture features, and the backscattering power (Span) combined with the H/alpha/A decomposition, which are projected onto a lower dimensional feature space using principal component analysis. For the classifier training two popular techniques are explored: conventional backpropagation (BP) and particle swarm optimization (PSO). By using both polarimetric covariance matrix and decomposition based pixel values and textural information (contrast, correlation, energy, and homogeneity) in the feature set, classification accuracy is improved. An experimental study is performed using the fully polarimetric San Francisco Bay and Flevoland data sets acquired by the NASA/Jet Propulsion Laboratory Airborne SAR, (AIRSAR.) at L-band to evaluate the performance of the proposed classifier. Classification results (in terms of confusion matrix, overall accuracy and classification map) compared with competing state of the art algorithms demonstrate the effectiveness of the proposed RBF network classifier.