Polarimetric SAR (PolSAR) image processing has become a hot research topic in SAR remote sensing field in recent years. However, due to the complexity of the image and limited availability of advanced techniques, PoISAR image processing is still a challenging issue. In this paper the suggestion of ensemble learning (EL) is introduced into PoISAR image classification by integrating various polarimetric features and multiple classifiers. The most popular ensemble learning methods, including Bagging, AdaBoost, and Rotation Forest are adopted to combine multiple classifiers and polarimetric features. The proposed classification scheme is evaluated on three real PoISAR data. Experimental results shows that the covariance and coherence features can give better performance than other polarimetric decomposition features, and complementary between different polarimetric decomposition features improving the classification performance. Although a weak classifier gives unsatisfactory classification accuracy on polarimetric decomposition features, the performance can be highly improved by using EL strategies.
展开▼
