CNN-Improved Superpixel-to-Pixel Fuzzy Graph Convolution Network for PolSAR Image Classification

Superpixel-based graph convolutional network (S-GCN) has shown the advantages of less computational time and global modeling ability for polarimetric synthetic aperture radar (PolSAR) image classification. However, the effectiveness is heavily dependent on the superpixel segmentation result. Existing superpixel segmentation methods usually produce edge errors due to speckle and scattering confusion, which directly results in mistakes in the final classification. To address this issue, a novel hybrid weighted fuzzy SGCN method (HF-SGCN) is proposed to correct the edge pixels by defining a fuzzy projection matrix (FPM). The FPM can transform features from superpixel to pixel, by which features of edge pixels can be calculated from all the neighboring superpixels with a certain probability, to correct edges to the most similar region. In addition, a hybrid weighted adjacent matrix is formulated by incorporating both the revised Wishart and multifeature distances, which can enhance the discriminating features effectively. The proposed HF-SGCN method is capable of capturing the global contextual information and rectifying edges while disregarding the local individual features for each pixel. To combine global and local features, we further propose the HF-SGCN-convolutional neural network (CNN) method, which integrates the superpixel-wise HF-SGCN network and the pixel-wise 3D-CNN network into a unified framework. Thus, we can fuse the features extracted from two subnetworks, producing complementary global and local features that significantly improve classification accuracy. Experiments are conducted on four publicly real PolSAR datasets with different sensors and bands. Experimental results demonstrate the effectiveness of the proposed methods.