Classification of coastal wetlands in eastern China using polarimetric SAR data

This study was initiated to classify Jiangsu coastal wetlands, which are situated on the north bank of the Yangtze River in eastern China, using fully polarimetric synthetic aperture radar (PolSAR) data with an improved classification scheme. First, Cloude-Pottier decomposition was completed to obtain polarimetric parameters. Then, the data were classified into 24 clusters using the decomposed parameters. Third, the agglomerative hierarchical-clustering algorithm was applied to merge the clusters into seven classes; the outcomes were regarded as initial values in the subsequent processing. Finally, the improved fuzzy C-means (FCM) algorithm, in which a fuzzy factor was introduced and the traditional Euclidean distance was replaced by the Wishart distance, was used to adjust the land cover boundaries. The experiment results revealed that for similar scattering mechanisms with different scattering intensities, the proposed method presented a satisfactory performance, with an overall accuracy of 86.93 %. The accuracies of seven land cover types were much higher and the boundaries were more clear when using the proposed method compared with two other methods. The study demonstrated the potential of using L-band fully polarimetric SAR data in coastal wetland classification.