The goal of this paper is to propose a method to achieve a higher classification rate in Polarimetric Synthetic Aperture Radar (PolSAR) image classification. In our work, Pol-SAR features are extracted from Convolutional Neural Networks (CNNs) and also Graph Convolutional Networks (GCNs). Due to the construction of the adjacency matrix on all the data, traditional GCNs usually suffer from a substantial computational cost, particularly in large-scale remote sensing (RS) problems. To this end, first of all, we propose a new mini-batch GCN (called Mini-GCN), which allows to train large-scale GCNs in a mini-batch fashion. More significantly, our designed mini-GCN is capable of inferring out-of-sample data without re-training networks and improving classification performance. Furthermore, as CNNs and GCNs can extract different types of PolSAR features, an intuitive solution to break the performance bottleneck of a single model is to fuse them. Since mini-GCNs can perform batch-wise network training (enabling the combination of CNNs and GCNs), we can use the feature fusion strategy. Therefore, in this paper, a local graph-based fusion method is proposed to couple dimension reduction and feature fusion of the information extracted from the designed CNN and Mini-GCN. Experimental results on real PolSAR data are very encouraging. Compared to the methods using only single feature and stacking all the features together, the proposed feature fusion method improves the overall classification accuracy on the real PolSAR data sets for more than 5%. Moreover, the experiments conducted on PolSAR datasets, demonstrate the advantages of the used mini-GCNs over the traditional GCNs and the superiority of the proposed feature fusion method with regards to the single CNN or GCN models.
K E Y W O R D S data analysis, image classification, image fusion, pattern classification, radar, target tracking
| INTRODUCTIONSynthetic Aperture Radar (SAR) has been a highly sought-after and powerful remote sensing technology due to its all-weather, all-time, and high-resolution imaging capabilities, and it has been widely used in many fields. Earlier SAR was singlepolarised (also called single-channel), which made it difficult to completely express the target scattering characteristics. Compared with the single-polarised SAR, polarimetric synthetic aperture radar (PolSAR) is a multi-channel SAR system with more discriminative information. PolSAR can clearly describe the polarised scattering characteristics of complex ground targets by sending and receiving electromagnetic waves in different combinations. Thanks to the more abundant polarimetric target decomposition features and complexvalued information, PolSAR data interpretation has attracted many researchers' attention, and a large number of approaches have been proposed in recent years. Polarimetric target decomposition is one of the most influential approaches for PolSAR image classification. The essence of polarimetric target decomposition is polarimetric measurement data, such as scattering m...