Spatial–Spectral Graph Convolutional Network for Hyperspectral Target Detection

doi:10.1109/LGRS.2025.3617086

Spatial–Spectral Graph Convolutional Network for Hyperspectral Target Detection

2025-01-01

0

PRE

AI

DOI：10.1109/LGRS.2025.3617086

Original

Original request for help

Save

Abstract

En 中文

Deep-learning-based hyperspectral target detection methods commonly face challenges such as insufficient target samples and inadequate use of spatial context. To address these limitations, we propose a novel hyperspectral target detection approach leveraging spatial–spectral graph convolutional networks. First, we introduce an innovative sample augmentation strategy using predetection and target implantation, which can simulate different backgrounds around the target and expand the target sample, thereby enhancing the representation ability of the model. Next, a graph-based representation strategy is proposed to integrate spatial and spectral information. Finally, we develop four specialized graph network detectors (graph convolutional network detector (GCND), graph attention network detector (GATD), GCN–GAT1, and GCN–GAT2) with structural optimizations involving multiscale feature fusion and dynamic neighborhood adjustments. Extensive experiments demonstrate the superior detection performance of our method compared with existing techniques, highlighting its practical significance.

Keywords:

Deep learning

graph convolutional network

hyperspectral target detection

spatial–spectral joint

Spatial–Spectral Graph Convolutional Network for Hyperspectral Target Detection

Abstract

Journal

Organization