KSG-Net: Key-Sparse and Global-Context Learning for Maritime 3D Ship Detection

2026-09-02

AI Summary

为解决海上3D船只检测中的小船特征弱和大船全局结构建模不足问题，提出KSG-Net，通过关键稀疏多尺度聚合和全局上下文聚合模块增强特征表示。

Abstract

Accurate 3D ship detection in maritime environments is critical for autonomous navigation, yet remains challenging due to large-scale vessel variations, sparse point clouds of small vessels, and severe sea-clutter interference. Existing methods, primarily based on 2D features or dense representations, struggle to balance detection accuracy and computational efficiency, while sparse 3D detectors designed for road scenes generalize poorly to maritime scenarios. This paper focuses on two key challenges in maritime LiDAR perception: weak feature representation for small and sparse vessels, and insufficient global structural modeling for large vessels due to the limited receptive field of local sparse convolutions. To address these issues, we propose KSG-Net, a Key-Sparse and Global-Context learning network for maritime 3D ship detection. The core idea is to jointly enhance local discriminative features and global structural awareness within a unified fully sparse detection framework. Specifically, a Key Sparse Multi-scale Aggregation (KSMA) module is designed to enhance the representation of small and sparse vessels by selecting informative key voxels and aggregating cross-scale neighborhood features. Furthermore, a Global Context Aggregation (GCA) module is introduced to capture long-range geometric dependencies through scene-level context modeling with gated residual interactions, thereby improving the representation of large vessels. Extensive experiments on the Thames River vessel dataset and simulated datasets demonstrate that KSG-Net consistently outperforms existing methods in multi-scale vessel detection and exhibits strong robustness in complex maritime environments.

Problem

• 3D ship detection
• maritime environments
• sparse point clouds
• sea-clutter interference
• global structural modeling

Innovation

• Key-Sparse Multi-scale Aggregation
• Global Context Aggregation
• Maritime 3D Ship Detection