USVTrack: USV-Based 4D Radar-Camera Tracking Dataset for Autonomous Driving in Inland Waterways
This work addresses object tracking for autonomous driving in inland waterways, which is incremental as it adapts existing methods to a new domain with a novel dataset.
The authors tackled object tracking for autonomous driving in inland waterways by creating USVTrack, the first 4D radar-camera tracking dataset, and demonstrated that their radar-camera matching method improves tracking accuracy and reliability in waterborne environments.
Object tracking in inland waterways plays a crucial role in safe and cost-effective applications, including waterborne transportation, sightseeing tours, environmental monitoring and surface rescue. Our Unmanned Surface Vehicle (USV), equipped with a 4D radar, a monocular camera, a GPS, and an IMU, delivers robust tracking capabilities in complex waterborne environments. By leveraging these sensors, our USV collected comprehensive object tracking data, which we present as USVTrack, the first 4D radar-camera tracking dataset tailored for autonomous driving in new generation waterborne transportation systems. Our USVTrack dataset presents rich scenarios, featuring diverse various waterways, varying times of day, and multiple weather and lighting conditions. Moreover, we present a simple but effective radar-camera matching method, termed RCM, which can be plugged into popular two-stage association trackers. Experimental results utilizing RCM demonstrate the effectiveness of the radar-camera matching in improving object tracking accuracy and reliability for autonomous driving in waterborne environments. The USVTrack dataset is public on https://usvtrack.github.io.