USV Obstacles Detection and Tracking in Marine Environments
Yara AlaaEldin, Enrico Simetti, Francesca Odone
TL;DR
This work advances USV obstacle detection and tracking in marine environments by extending a Genova-based dual-sensor framework (camera and LiDAR) and evaluating it on MIT marine datasets within a ROS-based real-time pipeline. It systematically compares image-LiDAR sensor fusion against LiDAR-only detection and tracking, and proposes a hybrid approach that leverages the strengths of both modalities to produce a comprehensive 3D obstacle map. The methodology combines YOLOv3-based detection, Hungarian-data-association tracking with a Kalman-filter predictor, and a 3D localization step using LiDAR-camera calibration to project detections into the scene. Experimental analyses include quantitative benchmarks on public datasets, qualitative MIT assessments, and detailed timing studies, highlighting the trade-offs between coverage, accuracy, and computation, and outlining practical integration steps for robust USV navigation."
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.