关键词: 核函数, 参数选择, 极化合成孔径雷达, Cameron分解, 支持向量机

Abstract: First, Cameron decomposition decomposes Sinclair matrix into reciprocity component and non- reciprocity component. Then, reciprocity component is decomposed into symmetric component and asymmetric component. This is a important way to extract properties from polarimetric synthetic aperture radar image. Samples are composed of norms of four components. Classifier can be designed using support vector machines based on statistical learning theory, a new algorithm of target classification is proposed, and classification experiments to polarimetric SAR data are done. The results indicate it is feasible and efficient to classify polarimetric SAR image by combining Cameron decomposition and SVM. Discrimination of classification results is rather big by selecting different parameters. Parameters selecting is very important to SVM classifier.

Key words: kernel functions, parameters selecting, polarimetric synthetic aperture radar, Cameron decomposition, support vector machines