MFFCG-Multi feature fusion for hyperspectral image classification using graph attention network

Classification methods that are based on hyperspectral images (HSIs) are playing an increasingly significant role in the processes of target detection, environmental management, and mineral mapping as a result of the fast development of hyperspectral remote sensing technology. Improving classification performance is still a sig-nificant problem, however, as a result of the high dimensionality and redundancy of hyperspectral image sets (HSIs), as well as the presence of class imbalance in hyperspectral datasets. In the past few years, convolutional neural networks (CNNs) and graph convolutional networks (GCNs) have achieved good results in HSI classifi-cation, but CNNs struggle to achieve good accuracy in low samples, while GCNs have a huge computational cost. To resolve these issues, this paper proposes a Multi-Feature Fusion of 3D-CNN and Graph Attention Network MFFCG. The algorithm consists of two elements: the 3D-CNN, which produces good classification for 3D HSI cube data, and GAT-based encoder and decoder modules that help in improving the classification accuracy of the 3D -CNN. Finally, the multiple features are merged with the help of two neural network models. We further develop two optimized GAT models named GAT1 and GAT2, which are used with different layers of 3D-CNN. Algorithms after merging with 3D-CNN are named MFFCG-1 and MFFCG-2, which produce better classification results then other developed methods. Experiments on three public HSI datasets show that the proposed methods perform better than other state-of-the-art methods using the limited training samples and in low classification time.

Automated summary

Classification methods based on hyperspectral images have become increasingly important in target detection, environmental management, and mineral mapping. However, improving classification performance is still challenging due to the high dimensionality and redundancy of hyperspectral image sets, as well as class imbalance in the datasets. This paper proposes a Multi-Feature Fusion of 3D-CNN and Graph Attention Network (MFFCG) algorithm, which combines 3D-CNN and GAT-based encoder and decoder modules to improve classification accuracy. Experimental results on three public datasets show that MFFCG outperforms other state-of-the-art methods in terms of limited training samples and low classification time.