USVTrack: USV-Based 4D Radar-Camera Tracking Dataset for Autonomous Driving in Inland Waterways

TL;DR

USVTrack introduces a novel 4D radar-camera dataset for autonomous waterway navigation, along with an effective matching method that enhances object tracking accuracy in complex aquatic environments.

Contribution

The paper presents the first comprehensive 4D radar-camera dataset for inland waterway autonomous driving and a simple matching method that improves tracking performance.

Findings

RCM improves tracking accuracy

Dataset covers diverse waterway scenarios

Effective in complex waterborne environments

Abstract

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.