Graph neural network-based remote target classification in hyperspectral imaging

• Published in: International journal of remote sensing Vol. 44; no. 14; pp. 4465 - 4485
• Main Authors: Niruban, R., Deepa, R.
• Format: Journal Article
• Language: English
• Published: London Taylor & Francis 18.07.2023; Taylor & Francis Ltd
• Subjects: Accuracy; Autoregressive moving average; Classification; Datasets; Graph neural network; Graph neural networks; hyperspectral image; Hyperspectral imaging; Image classification; Neural networks; Remote sensing; remote target detection; spectral characteristics; target categorization
• ISSN: 0143-1161; 1366-5901
• DOI: 10.1080/01431161.2023.2237661

Hyperspectral Imagery (HSI) onboard target classification is a frequently used technique in remote sensing. Due to the small volume of labelled data, the classification of HSI has been a challenging subject in recent study. The graph neural network (GNN) has become a popular method for semi-supervised classification, and its use with hyperspectral images has gained a lot of interest. A graph filter or single graph neural network has been typically employed in the earlier GNN-based approaches, and it is used to obtain HSI characteristics. It has not fully utilized the benefits of different graph filters or graph neural networks. The issue of oversmoothing also persists with the classical GNNs. We propose a spectral filter and an autoregressive moving average filter for the multi-graph neural network; (SAF-GNN) to address such drawbacks as the one mentioned above. The first is excellent at extracting the nodes' spectral characteristics, and the second is effective at suppressing graph distortion. With the help of performance measures like overall accuracy (OA), individual class accuracy (ICA), and Kappa coefficient (KC), the performance of the proposed method was compared to that of other state-of-the-art methods. The result shows that the SAF-GNN provides an improvement in OA, ICA and KC of 2.21%, 7.93% and 0.025 for the cuprite dataset and 4.84%, 11.78% and 0.025 for the Pavia University dataset, respectively. Comparison results show that the proposed method is suitable for remote target classification problem.