TJ4DRadSet: A 4D Radar Dataset for Autonomous Driving

TL;DR

TJ4DRadSet is a comprehensive 4D radar dataset for autonomous driving, featuring synchronized 3D annotations across diverse scenarios, enabling research on 3D object detection using high-resolution radar data.

Contribution

The paper introduces a new large-scale 4D radar dataset with annotations, facilitating research in 3D sensing and detection for autonomous vehicles.

Findings

Demonstrated effectiveness of deep learning on 4D radar data

Provided baseline 3D object detection results

Collected diverse driving scenarios for robust evaluation

Abstract

The next-generation high-resolution automotive radar (4D radar) can provide additional elevation measurement and denser point clouds, which has great potential for 3D sensing in autonomous driving. In this paper, we introduce a dataset named TJ4DRadSet with 4D radar points for autonomous driving research. The dataset was collected in various driving scenarios, with a total of 7757 synchronized frames in 44 consecutive sequences, which are well annotated with 3D bounding boxes and track ids. We provide a 4D radar-based 3D object detection baseline for our dataset to demonstrate the effectiveness of deep learning methods for 4D radar point clouds. The dataset can be accessed via the following link: https://github.com/TJRadarLab/TJ4DRadSet.