期刊名称：Advances in Information Technology and Management
印刷版ISSN：2167-6372
出版年度：2012
卷号：1
期号：3
页码：132-137
语种：English
出版社：World Science Publisher
摘要：Polarimetric synthetic aperture radar has attracted the research interest among numerous scholars and researchers. It plays an important role in either the military or the domestic fields. In this study, we proposed a novel Polarimetric SAR image classification method. We first extract the feature sets including span image, the H/A/α decomposition, and the gray-level co-occurrence matrix based texture features. Afterwards, we used an artificial neural network to construct the classifier and chose the particle swarm optimization method as the training algorithm. The experiments used the San Francisco area as the test data, and compared our PSONN method with traditional IPNN method and SVM method. The results show that our method achieves the best classification accuracy as 96.55%, meanwhile, IPNN and SVM only achieved 96.13% and 96.43% classification accuracy, respectively. Therefore, our method is effective.
