主办:陕西省汽车工程学会
ISSN 1671-7988  CN 61-1394/TH
创刊:1976年

汽车实用技术 ›› 2025, Vol. 50 ›› Issue (10): 41-47.DOI: 10.16638/j.cnki.1671-7988.2025.010.008

• 智能网联汽车 • 上一篇    

激光雷达与相机跨模态联合自动标定

陆雨薇 1,2,唐文涛 1,李远智 3,魏楚淦 1   

  1. 1.广西科技大学 广西汽车零部件与整车技术重点实验室;2.上汽通用五菱汽车股份 有限公司 广西新能源汽车实验室;3.柳州沪信汽车科技有限公司
  • 发布日期:2025-05-27
  • 通讯作者: 陆雨薇
  • 作者简介:陆雨薇(1987-),女,博士,副教授,研究方向为机械视觉、自动化、算法设计
  • 基金资助:
    高精度高寿命轻量化模具关键技术研发及应用(桂科 AB24010188);广西科技计划《中国-东盟绿色车辆研 究院搭建与能力建设》(桂科 AA24206060);广西科技大学研究生教育创新计划项目“基于视觉跟踪的智能 仓储运输车系统”(GKYC202310)

Automatic Cross-Modal Joint Calibration of LiDAR and Cameras

LU Yuwei1,2 , TANG Wentao1 , LI Yuanzhi3 , WEI Chugan1   

  1. 1.Guangxi Key Laboratory of Automobile Components and Vehicle Technology, Guangxi University of Science and Technology; 2.Guangxi New Energy Vehicle Laboratory, SAIC-GM-Wuling Automobile Company Limited; 3.Liuzhou Huxin Automotive Technology Company Limited
  • Published:2025-05-27
  • Contact: LU Yuwei

摘要: 随着自动驾驶与机器人技术的快速发展,多传感器融合技术愈发重要,尤其是激光雷 达与相机的外参标定变得至关重要。文章提出一种结合激光雷达中非重复扫描方式与相机的 自动外参标定方法,通过使用特制的镂空棋盘格标定板,结合点云与图像的几何特征进行提 取与匹配。实验结果表明,上述方法可以有效提取三维角点与二维图像点,并进行自动化标 定。此外,与传统方法相比,该方法在标定精度、效率和适用性方面表现出显著优势,研究 结果为移动机器人和智能驾驶车辆的精确导航与环境感知提供了有力支持。

关键词: 激光雷达;相机;联合标定;智能驾驶

Abstract: With the rapid development of autonomous driving and robotics technology, multi-sensor fusion technology is becoming increasingly important. especially the external parameter calibration of LiDAR and cameras, has become crucial. The article proposes an automatic external parameter calibration method that combines the non-repetitive scanning mode of LiDAR with the camera. By using a specially designed hollowed- out checkerboard calibration board and combining the point cloud with the geometric features of the image for extraction and matching. The experimental results show that the above-mentioned method can effectively extract three-dimensional corner points and two-dimensional image points and perform automated calibration. Furthermore, compared with traditional methods, this method shows significant advantages in terms of calibration accuracy, efficiency and applicability. The research results provide strong support for the precise navigation and environmental perception of mobile robots and intelligent driving vehicles.

Key words: LiDAR; camera; joint calibration; intelligent driving