Marine Small Floating Target Detection Method Based on Fusion Weight and Graph Dynamic Attention Mechanism

• Published in: IEEE transactions on geoscience and remote sensing Vol. 61; pp. 1 - 11
• Main Authors: Ru, Hongtao, Xu, Shuwen, He, Qi, Shui, Penglang
• Format: Journal Article
• Language: English
• Published: New York IEEE 2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Clutter; Clutter map; Convolution; Correlation; Detection; Detectors; Doppler sonar; Feature extraction; Floating; graph attention network (GAT); Graph neural networks; graph structural; Neural networks; Radar; Radar data; Sea surface; Sensors; Surface clutter; Target detection
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2023.3332127

Sea surface target detection with graph neural networks (GNNs) is an emerging method. However, the correlation information of radar returns cannot be efficiently exploited by the conventional graph convolutional network (GCN). Therefore, this article proposes a small floating target detection method based on a graph attention network (GAT) with spatiotemporal correlation of clutter maps, and designs fusion weighting and dynamic attention mechanism for practical problems. First, the dwell radar data are modeled as a graph structure according to its spatio-temporal information. The proposed graph structure allows Doppler spectra of same-type samples to be accumulated separately for sea clutter and target returns. Then, we propose a GAT-based detector and optimize it to create variants: GATv2, GAT-Fused, and GATv2-Fused. These variants aim to reduce sea spike interference and jointly utilize spatiotemporal clutter map information and feature correlation. Both measured and simulated data demonstrate that the proposed attention-based detectors effectively identify marine small floating targets, including out-of-distribution (OOD) detection, outperforming conventional feature-based detectors, the GCN detector, and the pure GAT detector.