Scene-aware SAR ship detection guided by unsupervised sea-land segmentation

2025-06-15

AI Summary

Prior knowledge deficiency—particularly the absence of sea-land segmentation masks—severely degrades detection accuracy in Synthetic Aperture Radar (SAR) ship detection. Method: This paper proposes a scene-aware two-stage detection framework: (1) unsupervised clustering-driven sea-land segmentation (ULSM) to automatically extract maritime prior knowledge; and (2) a land-attention suppression mechanism (LASM) coupled with a scene-type adaptive weight modulation module, jointly optimizing scene classification and background suppression for adaptive near-shore and far-shore detection. Contribution/Results: The work establishes the first “unsupervised sea-land segmentation-guided scene-aware detection” paradigm, significantly enhancing model interpretability and far-sea robustness. On the SSDD dataset, it achieves a 4.2% mAP improvement and markedly higher far-sea recall, without requiring manually annotated sea-land masks—demonstrating both effectiveness and practical applicability.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Semi-Supervised Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Large language models for search
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

DL based Synthetic Aperture Radar (SAR) ship detection has tremendous advantages in numerous areas. However, it still faces some problems, such as the lack of prior knowledge, which seriously affects detection accuracy. In order to solve this problem, we propose a scene-aware SAR ship detection method based on unsupervised sea-land segmentation. This method follows a classical two-stage framework and is enhanced by two models: the unsupervised land and sea segmentation module (ULSM) and the land attention suppression module (LASM). ULSM and LASM can adaptively guide the network to reduce attention on land according to the type of scenes (inshore scene and offshore scene) and add prior knowledge (sea land segmentation information) to the network, thereby reducing the network's attention to land directly and enhancing offshore detection performance relatively. This increases the accuracy of ship detection and enhances the interpretability of the model. Specifically, in consideration of the lack of land sea segmentation labels in existing deep learning-based SAR ship detection datasets, ULSM uses an unsupervised approach to classify the input data scene into inshore and offshore types and performs sea-land segmentation for inshore scenes. LASM uses the sea-land segmentation information as prior knowledge to reduce the network's attention to land. We conducted our experiments using the publicly available SSDD dataset, which demonstrated the effectiveness of our network.

Problem

• Improving SAR ship detection accuracy using unsupervised sea-land segmentation
• Reducing false land attention in SAR ship detection models
• Enhancing interpretability of SAR ship detection with prior knowledge

Innovation

• Unsupervised sea-land segmentation for scene classification
• Land attention suppression using prior knowledge
• Two-stage framework with ULSM and LASM modules