Abstract: Incomplete utilization of polarimetric information is one of the important factors that impact the result of polarimetric Synthetic Aperture Radar (SAR) image classification. In order to achieve the comprehensive utilization of polarimetric information, quotient space granularity composition theory, combined with multiple classifiers to construct different quotient space, was applied in classification of polarimetric SAR. Firstly, using different polarization decomposition method to get different characteristics, and based on these characteristics, setting different Support Vector Machine (SVM) classifiers to classify the image. Secondly, integrating these quotient spaces based on granularity composition theory to get more fine-grained result in order to achieve the upgrading of the classification accuracy. Finally, an experiment for AIRSAR image was given. The result shows the misclassification of targets is inhibited significantly and the classification accuracy of each class is improved.

Key words: polarimetry Synthetic Aperture Radar (SAR), quotient space theory, granularity composition, Support Vector Machine (SVM), image classification

摘要： 当前极化合成孔径雷达(SAR)图像的分类研究中，极化信息的不完全利用是影响极化SAR图像分类效果的重要原因之一。故将商空间粒度合成理论引入到极化SAR图像分类中，通过建立不同的支持向量机(SVM)分类器构建不同的商空间，从多个粒度层面实现对极化信息的综合利用。首先通过不同的极化分解方法得到不同的极化特征，分别对其建立不同的支持向量机分类器进行分类；再根据粒度合成理论对这些商空间进行融合，得到更细粒度上的改进的分类结果。最后，利用AIRSAR图像进行实验比较，算法改进后的结果在地物误分上有明显的抑制，各类别分类正确率都有所提高。

关键词: 极化合成孔径雷达, 商空间理论, 粒度合成, 支持向量机, 图像分类