Near-Shore Mapping for Detection and Tracking of Vessels

2025-02-25

AI Summary

To address the low detection and tracking accuracy of near-shore small targets (e.g., kayaks) by autonomous surface vehicles (ASVs) during berthing under strong dock-side clutter, this paper proposes a LiDAR-static mapping and vision-dynamic perception collaborative framework. First, high-precision offline dock maps are constructed using 3D LiDAR to eliminate target occlusion and misdetection caused by land-based masking. Second, a dock-specific semantic segmentation network for small targets is designed, leveraging RGB imagery and multimodal registration for robust dynamic obstacle identification. Third, a real-time multi-object tracking algorithm is integrated. Evaluated on a real-world dock dataset, the framework achieves a 32% improvement in mean average precision (mAP) for near-shore target detection and reduces identity switch rate to 0.8 switches per minute. These results significantly enhance the safety and reliability of ASV berthing operations.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Computer Vision: Motion & Tracking
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

For an autonomous surface vessel (ASV) to dock, it must track other vessels close to the docking area. Kayaks present a particular challenge due to their proximity to the dock and relatively small size. Maritime target tracking has typically employed land masking to filter out land and the dock. However, imprecise land masking makes it difficult to track close-to-dock objects. Our approach uses Light Detection And Ranging (LiDAR) data and maps the docking area offline. The precise 3D measurements allow for precise map creation. However, the mapping could result in static, yet potentially moving, objects being mapped. We detect and filter out potentially moving objects from the LiDAR data by utilizing image data. The visual vessel detection and segmentation method is a neural network that is trained on our labeled data. Close-to-shore tracking improves with an accurate map and is demonstrated on a recently gathered real-world dataset. The dataset contains multiple sequences of a kayak and a day cruiser moving close to the dock, in a collision path with an autonomous ferry prototype.

Problem

• Detect and track vessels near shore.
• Improve close-to-dock object tracking.
• Filter moving objects using LiDAR and images.

Innovation

• Uses LiDAR for precise 3D mapping
• Employs neural network for vessel detection
• Filters moving objects using image data