4D-CAAL: 4D Radar-Camera Calibration and Auto-Labeling for Autonomous Driving

TL;DR

This paper introduces 4D-CAAL, a unified framework for calibrating 4D radar and camera sensors and automatically labeling radar data, enhancing autonomous driving perception with high accuracy and reduced manual effort.

Contribution

The paper presents a novel dual-purpose calibration target and correspondence algorithm, along with an auto-labeling pipeline that transfers camera annotations to radar data, streamlining sensor calibration and annotation processes.

Findings

Achieves high calibration accuracy between 4D radar and camera.

Reduces manual annotation effort significantly.

Enhances multi-modal perception system development.

Abstract

4D radar has emerged as a critical sensor for autonomous driving, primarily due to its enhanced capabilities in elevation measurement and higher resolution compared to traditional 3D radar. Effective integration of 4D radar with cameras requires accurate extrinsic calibration, and the development of radar-based perception algorithms demands large-scale annotated datasets. However, existing calibration methods often employ separate targets optimized for either visual or radar modalities, complicating correspondence establishment. Furthermore, manually labeling sparse radar data is labor-intensive and unreliable. To address these challenges, we propose 4D-CAAL, a unified framework for 4D radar-camera calibration and auto-labeling. Our approach introduces a novel dual-purpose calibration target design, integrating a checkerboard pattern on the front surface for camera detection and a corner reflector at the center of the back surface for radar detection. We develop a robust correspondence matching algorithm that aligns the checkerboard center with the strongest radar reflection point, enabling accurate extrinsic calibration. Subsequently, we present an auto-labeling pipeline that leverages the calibrated sensor relationship to transfer annotations from camera-based segmentations to radar point clouds through geometric projection and multi-feature optimization. Extensive experiments demonstrate that our method achieves high calibration accuracy while significantly reducing manual annotation effort, thereby accelerating the development of robust multi-modal perception systems for autonomous driving.