WaterScenes: A Multi-Task 4D Radar-Camera Fusion Dataset and Benchmarks for Autonomous Driving on Water Surfaces

TL;DR

WaterScenes introduces a comprehensive multi-task 4D radar-camera dataset for autonomous water surface driving, enabling improved perception in adverse conditions through multi-modal fusion and benchmarking various perception tasks.

Contribution

This work provides the first multi-task 4D radar-camera dataset for water surface autonomous driving, with detailed annotations and benchmark experiments demonstrating the benefits of sensor fusion.

Findings

Radar-camera fusion improves perception accuracy and robustness.

Multi-task annotations enable diverse perception capabilities.

Fusion outperforms single modality in adverse conditions.

Abstract

Autonomous driving on water surfaces plays an essential role in executing hazardous and time-consuming missions, such as maritime surveillance, survivors rescue, environmental monitoring, hydrography mapping and waste cleaning. This work presents WaterScenes, the first multi-task 4D radar-camera fusion dataset for autonomous driving on water surfaces. Equipped with a 4D radar and a monocular camera, our Unmanned Surface Vehicle (USV) proffers all-weather solutions for discerning object-related information, including color, shape, texture, range, velocity, azimuth, and elevation. Focusing on typical static and dynamic objects on water surfaces, we label the camera images and radar point clouds at pixel-level and point-level, respectively. In addition to basic perception tasks, such as object detection, instance segmentation and semantic segmentation, we also provide annotations for free-space segmentation and waterline segmentation. Leveraging the multi-task and multi-modal data, we conduct benchmark experiments on the uni-modality of radar and camera, as well as the fused modalities. Experimental results demonstrate that 4D radar-camera fusion can considerably improve the accuracy and robustness of perception on water surfaces, especially in adverse lighting and weather conditions. WaterScenes dataset is public on https://waterscenes.github.io.