A Sea Clutter Suppression Method With Graph Neural Network for Maritime Target Detection

Radar is widely applied in maritime target detection. However, the performance of sea-surface target detection in complex ocean environments is limited because of the low signal-to-clutter ratio (SCR). Hence, sea clutter suppression has become a highly investigated research topic. In this study, we explicitly characterize spatiotemporal information in range-Doppler spectra using non-Euclidean graphs and subsequently present a sea clutter suppression method with a graph neural network (GNN). We propose a representation of radar signal graph data that are constructed using patches segmented from sequential range-Doppler maps. In the proposed GNN, edge values are updated through a global attention mechanism that captures the correlations between resolution cells in multiple coherent processing intervals (CPIs) and extracts the feature differences between the target and clutter. A graph convolution operation is designed. We incorporate the learned adjacency matrix into the graph convolution kernel to discriminatively aggregate node features based on the associations between nodes. To increase the model capacity, we devise an auxiliary graph classification head and a compound training loss comprising contrastive and cross-entropy losses. The proposed method was verified on real sea clutter data and demonstrated a significant sea clutter suppression effect and improved target detection performance. In addition, this approach was found to exhibit satisfactory generalization ability.