improving the urban area classification using radar polarimetry data and multiobjective optimization methods

land cover classification is one of the most important applications of polarimetric radar images, especially in urban areas. there are numerous features that can be extracted from these images for the use of their high potential, hence feature selection plays an important role in polsar image classification. in this study, three main steps are used to improve the classification: 1) feature extraction in the form of three categories, namely original data features, target decomposition features, and sar discriminators; 2) selection of minimum number of features to achieve the high classification accuracy; and 3) classification using the best subset of features. in the proposed methods, nsga-ii multiobjective optimization algorithm is employed as the search tool and support vector machine (svm) or adaptive neuro fuzzy inference system (anfis) is used in the evaluation step. the implementation results on the radarsat-2 san francisco bay image showed that the proposed methods outperform the other approaches tested against them.