Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Shanliang Yao, Zhuoxiao Li, Runwei Guan, Kebin Cao, Meng Xia, Fuping Hu, Sen Xu, Yong Yue, Xiaohui Zhu, Weiping Ding, Ryan Wen Liu

TL;DR

This work proposes 4D-CAAL, a unified framework for 4D radar-camera calibration and auto-labeling, and presents 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.

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.

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

TL;DR

This work proposes 4D-CAAL, a unified framework for 4D radar-camera calibration and auto-labeling, and presents 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.

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.
Paper Structure (46 sections, 33 equations, 2 figures, 5 tables, 3 algorithms)

This paper contains 46 sections, 33 equations, 2 figures, 5 tables, 3 algorithms.

Table of Contents

  1. Introduction
  2. Related Work
  3. Target-Based Radar-Camera Calibration
  4. Integrated Calibration Board Designs
  5. 4D Radar-Specific Calibration
  6. Point-Based Auto-Labeling
  7. Multi-modal Assisted Auto-Labeling
  8. Label Quality Enhancement and Clutter Filtering
  9. Methodology
  10. 4D-CAAL Pipeline
  11. 4D Radar-Camera Calibration
  12. Calibration Platform
  13. Calibration Board Design
  14. Rigid Mounting Bracket Design
  15. Data Collection
  16. ...and 31 more sections

Figures (2)

  • Figure 1: Calibration board design. Our custom calibration target integrates a trihedral corner reflector with an A4-sized acrylic board featuring a checkerboard pattern. The camera is calibrated by associating the detected checkerboard center with the known 3D coordinates of the corner reflector.
  • Figure 2: Rigid Mounting Bracket. The high‑strength steel bracket ensures precise sensor alignment and includes standardized lower holes for vehicle integration.