Supervised PolSAR Image Classification with Multiple Features and Locally Linear Embedding

In this paper, we propose a new method of land use and land cover classification for polarimetric SAR data. This algorithm consists of three parts. First, the multiple-component model-based scattering decomposition technique is improved and the decomposed scattering powers can be used to support the classification of PolSAR data. With this decomposition, the volume scattering of vegetated areas is enhanced while their double-bounce scattering is reduced. Furthermore, the double-bounce scattering of urban areas is enhanced and their volume scattering is decreased, which leads to an improvement in the classification accuracy especially for the urban areas. Second, this classification strategy is carried out on the superpixel level, which can decrease the influence of speckle noise and speed up the classification. Moreover, the contexture and spatial features extracted from these superpixels are utilized to improve classification accuracy. Lastly, we introduce the supervised locally linear embedding approach to map the high dimensional features into the low dimensional features as the inputs of classifiers. The classification is completed using the nearest neighbor classifier. The effectiveness of our proposed method is demonstrated using the AIRSAR C-band PolSAR data set, which is compared with the original MCSM-SVM and newly published LE-IF PolSAR classification methods. Further investigation is also carried out on the individual contribution of the three parts to LULC classification using AIRSAR C-band data. It indicates that all three components have important contributions to the final classification result.