USV Obstacles Detection and Tracking in Marine Environments

2025-11-11

AI Summary

To address the insufficient robustness of obstacle perception for unmanned surface vehicles (USVs) in complex marine environments, this paper proposes a vision–LiDAR tightly coupled multimodal fusion detection and tracking method. Within the ROS framework, the approach jointly optimizes 2D image-plane object detection and 3D point cloud segmentation, while introducing a spatiotemporally consistent data association mechanism and dynamic map construction to enable real-time, high-precision 3D obstacle localization and persistent tracking. Evaluated on the MIT Marine public dataset, the method achieves a 23.6% improvement in detection accuracy and an 18.4% increase in tracking success rate over single-sensor baselines. Crucially, it maintains stable performance under challenging conditions including illumination variations and wave-induced disturbances. This work delivers a deployable, end-to-end perception solution for autonomous USV navigation.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Developing a robust and effective obstacle detection and tracking system for Unmanned Surface Vehicle (USV) at marine environments is a challenging task. Research efforts have been made in this area during the past years by GRAAL lab at the university of Genova that resulted in a methodology for detecting and tracking obstacles on the image plane and, then, locating them in the 3D LiDAR point cloud. In this work, we continue on the developed system by, firstly, evaluating its performance on recently published marine datasets. Then, we integrate the different blocks of the system on ROS platform where we could test it in real-time on synchronized LiDAR and camera data collected in various marine conditions available in the MIT marine datasets. We present a thorough experimental analysis of the results obtained using two approaches; one that uses sensor fusion between the camera and LiDAR to detect and track the obstacles and the other uses only the LiDAR point cloud for the detection and tracking. In the end, we propose a hybrid approach that merges the advantages of both approaches to build an informative obstacles map of the surrounding environment to the USV.

Problem

• Developing obstacle detection for USVs in marine environments
• Evaluating sensor fusion vs LiDAR-only tracking approaches
• Creating hybrid mapping system for USV environment perception

Innovation

• Sensor fusion of camera and LiDAR data
• Real-time ROS integration for marine testing
• Hybrid approach combining sensor fusion and LiDAR