Radarsat-2 Polarimetric SAR Data for Boreal Forest Classification Using SVM and a Wrapper Feature Selector

Abstract

The main objective is to propose a wrapper feature selection algorithm for analyzing the Radarsat-2 polarimetric SAR data for the classification of boreal forest. The method is based on the concept of feature selection and classifier ensemble. The support vector machine (SVM) algorithm is used as the classifier. The limitation of SVM as the evaluation function for feature selection is its time-consuming optimization. To accelerate the SVM training process, a training sample reduction strategy based on the notion of support vectors is proposed. Two fine quad-polarized Radarsat-2 images, which were acquired in leaf-on and leaf-off seasons, were chosen for this study. A wide range of SAR parameters were derived from each PolSAR image. A combined dataset was also considered. The classification results compared to the baseline methods demonstrate the effectiveness of the proposed wrapper scheme for forest classification.