Polarimetric SAR Image Classification Based on Deep Learning and Hierarchical Semantic Model

Stacked auto-encoder model can effectively represent the complex terrain structures, such as the urban and the forest, by automatically learning high-level features. However, it has difficulty in preserving details and edges. In order to overcome this shortcoming, a new unsupervised polarimetric synthetic aperture radar (PolSAR) classification method is proposed by combining the deep learning and the polarimetric hierarchical semantic model (PHSM). According to the PHSM, a PolSAR image is partitioned into aggregated, homogeneous and structural regions. For aggregated regions, a stacked auto-encoder model is applied to learn high-level features, and further the sparse representation and classification is constructed by learning a dictionary with high-level features. For homogeneous regions, hierarchical segmentation and classification is applied. In addition, edges are located and line objects are preserved for structural regions. Experimental results demonstrate that the proposed method can obtain good performance in both region homogeneity and edge preservation. Copyright © 2017 Acta Automatica Sinica. All rights reserved.