Efficient 4D Radar Data Auto-labeling Method using LiDAR-based Object Detection Network

TL;DR

This paper presents an auto-labeling method for 4D radar data using a LiDAR-based detection network, enabling efficient training of 4D radar object detection models without manual labeling, and demonstrating comparable performance to manually labeled data.

Contribution

The paper introduces a novel auto-labeling approach for 4D radar datasets using LiDAR-based detection, reducing manual effort and accelerating dataset expansion.

Findings

RTNH trained with auto-labels performs similarly to models trained with manual labels.

The proposed method significantly reduces labeling time and cost.

Auto-labeling enables effective training of 4D radar detection networks.

Abstract

Focusing on the strength of 4D (4-Dimensional) radar, research about robust 3D object detection networks in adverse weather conditions has gained attention. To train such networks, datasets that contain large amounts of 4D radar data and ground truth labels are essential. However, the existing 4D radar datasets (e.g., K-Radar) lack sufficient sensor data and labels, which hinders the advancement in this research domain. Furthermore, enlarging the 4D radar datasets requires a time-consuming and expensive manual labeling process. To address these issues, we propose the auto-labeling method of 4D radar tensor (4DRT) in the K-Radar dataset. The proposed method initially trains a LiDAR-based object detection network (LODN) using calibrated LiDAR point cloud (LPC). The trained LODN then automatically generates ground truth labels (i.e., auto-labels, ALs) of the K-Radar train dataset without human intervention. The generated ALs are used to train the 4D radar-based object detection network (4DRODN), Radar Tensor Network with Height (RTNH). The experimental results demonstrate that RTNH trained with ALs has achieved a similar detection performance to the original RTNH which is trained with manually annotated ground truth labels, thereby verifying the effectiveness of the proposed auto-labeling method. All relevant codes will be soon available at the following GitHub project: https://github.com/kaist-avelab/K-Radar