激光雷达与相机外参标定方法研究综述

Research review on extrinsic calibration methods for LiDAR and cameras

摘要

激光雷达(LiDAR)与相机的外参标定是实现多模态感知融合的关键步骤,直接影响自动驾驶、机器人等系统在环境感知、三维重建和目标定位等任务中的精度与稳定性.研究系统梳理并分析现有LiDAR-相机外参标定方法,按传统几何标定方法、基于特征匹配的无标定物方法及深度学习方法进行分类阐述.通过对比各类方法的技术原理、实验流程、精度表现及其在不同应用场景下的优劣,揭示当前标定方法在自动化程度、环境依赖性及鲁棒性等方面面临的挑战.同时,对联合标定未来发展方向进行展望,涵盖自监督学习、动态场景下的在线标定及多传感器联合优化等内容,为后续研究提供理论参考.

Abstract

Extrinsic calibration between LiDAR and cameras is a critical step in achieving multimodal perception fusion, directly affecting the accuracy and stability of the systems such as autonomous driving and robotics in tasks like environmental perception, 3D reconstruction, and target localization. The existing LiDAR-camera extrinsic calibration methods are systematically reviewed and analyzed, categorized and elaborated according to traditional geometric calibration methods, feature-matching-based calibration-free methods and deep learning-based methods. By comparing the technical principles, experimental procedures, accuracy performance, and pros and cons of various methods in different application scenarios, the study reveals the challenges faced by current calibration methods in terms of automation level, environmental dependence and robustness. Additionally, it looks into the future development directions of joint calibration, including self-supervised learning, online calibration in dynamic scenarios and multi-sensor joint optimization, which provides theoretical reference for subsequent research.

关键词

激光雷达 / 相机标定 / 外参估计 / 几何方法 / 深度学习 / 多传感器融合

Key words

LiDAR / camera calibration / extrinsic parameter estimation / geometric methods / deep learning / multi-sensor fusion

参考文献

[1] 刘今越, 唐旭, 贾晓辉, 等. 三维激光雷达—相机间外参的高效标定方法[J]. 仪器仪表学报, 2019, 40(11): 64-72.

[2] 郑旺, 于红绯, 吕晋. 基于线特征的激光雷达与相机外参标定[J]. 激光与光电子学进展, 2024, 61(22): 204-211.

[3] PANDEY G, MCBRIDE J R, SAVARESE S, et al. Automatic Extrinsic Calibration of Vision and Lidar by Maximizing Mutual Information[J]. Journal of Field Robotics, 2015, 32(5): 696-722.

[4] 王世强, 孟召宗, 高楠, 等. 激光雷达与相机融合标定技术研究进展[J]. 红外与激光工程, 2023, 52(8): 119-132.

[5] 仇志江, 张林, 姚垚, 等. 三维点云场景语义分割研究进展[J]. 中国图象图形学报, 2025, 30(7): 2325-2342.

[6] 王浩. 基于三维扫描技术的建筑物点云数据处理方法研究[J]. 测绘与空间地理信息, 2025, 48(6): 188-191.

[7] 张彬, 熊传兵. 基于体素下采样和关键点提取的点云自动配准[J]. 激光与光电子学进展, 2020, 57(4): 109-117.

[8] 陆军, 王文豪, 杜宏劲. 基于特征融合和网络采样的点云配准[J]. 智能系统学报, 2025, 20(3): 621-630.

[9] WANG Q, TAN Y, MEI Z Y. Computational Methods of Acquisition and Processing of 3D Point Cloud Data for Construction Applications[J]. Archives of Computational Methods in Engineering, 2020, 27: 479-499.

[10] ZHANG Q, PLESS R. Extrinsic calibration of a camera and laser range finder[C]// Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway: IEEE, 2004(3): 2301-2306.

[11] GEIGER A, MOOSMANN F, Car O, et al. Automatic camera and range sensor calibration using a single shot[C]// 2012 IEEE International Conference on Robotics and Automation (ICRA). Piscataway: IEEE, 2012: 3936-3943.

[12] DHALL A, CHELANI K, RADHAKRISHNAN V, et al. LiDAR—camera calibration using 3D—3D point correspondences[J/OL]. (2017—05—27)[2025—05—04]. https://arxiv.org/pdf/1705.09785.

[13] WANG W M, SAKURADA K, KAWAGUCHI N. Reflectance intensity assisted automatic and accurate extrinsic calibration of 3d lidar and panoramic camera using a printed chessboard[J]. Remote Sensing, 2017, 9(8): 851.

[14] 董方新, 蔡军, 解杨敏. 立体视觉和三维激光系统的联合标定方法[J]. 仪器仪表学报, 2017, 38(10): 2589-2596.

[15] 俞德崎, 李广云, 王力, 等. 一种基于三维特征点集的激光雷达与相机配准方法[J]. 测绘通报, 2018(11): 40-45.

[16] BELTRÁN J, GUINDEL C, DE LA ESCALERA A, et al. Automatic extrinsic calibration method for lidar and camera sensor setups[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(10): 17677-17689.

[17] 王庆, 谭镕轩, 冯悠扬, 等. 基于三维标定板的相机—激光雷达联合标定方法[J]. 中国惯性技术学报, 2023, 31(1): 100-106.

[18] 祝飞, 范佳, 黄玉春, 等. 融合多种棋盘格约束的面阵相机和线激光外参标定[J]. 武汉大学学报(信息科学版), 2019, 44(10): 1524-1529.

[19] CHEN Z, ZHUO L, SUN K Q, et al. Extrinsic calibration of a camera and a laser range finder using point to line constraint[J]. Procedia Engineering, 2012, 29: 4348-4352.

[20] TÓTH T, PUSZTAI Z, HAJDER L. Automatic LiDAR—Camera Calibration of Extrinsic Parameters Using a Spherical Target[C]// 2020 IEEE International Conference on Robotics and Automation (ICRA). Piscataway: IEEE, 2020: 8580-8586.

[21] GONG X J, LIN Y, LIU J L. 3D LIDAR—Camera Extrinsic Calibration Using an Arbitrary Trihedron[J]. Sensors, 2013, 13(2): 1902-1918.

[22] HUANG K H, STACHNISS C. Extrinsic multi—sensor calibration for mobile robots using the Gauss—Helmert model[C]// 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Vancouver, BC: IEEE, 2017: 1490-1496.

[23] TAYLOR Z, NIETO J. Motion—based calibration of multimodal sensor arrays[C]// 2015 IEEE International Conference on Robotics and Automation (ICRA). Seattle: IEEE, 2015: 4843-4850.

[24] ISHIKAWA R, OISHI T, IKEUCHI K. LiDAR and Camera Calibration Using Motions Estimated by Sensor Fusion Odometry[C]// 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Madrid: IEEE, 2018: 7342-7349.

[25] 杨超, 李天剑, 胡欢, 等. 基于非线性优化的激光雷达在线标定算法[J]. 计算机工程与设计, 2021, 42(7): 1919-1925.

[26] LI J Z, HU M J, LIU S, et al. Improved LiDAR—Camera Calibration Based on Hand—Eye Model Under Motion Limitation[J]. IEEE Sensors Journal, 2023, 23: 18634-18643.

[27] PANDEY G, MCBRIDE J R, SAVARESE S, et al. Automatic targetless extrinsic calibration of a 3D LiDAR and camera by maximizing mutual information[C]// AAAI Conference on Artificial Intelligence (AAAI). Menlo Park: AAAI Press, 2012: 2053-2059.

[28] 刘万里, 刘扬, 张学亮. 融合互信息和多特征约束的激光雷达与相机外参标定方法[J]. 仪器仪表学报, 2025, 46(1): 29-41.

[29] SCHNEIDER N, PIEWAK F, STILLER C, et al. RegNet: Multimodal sensor registration using deep neural networks[C]// Proceedings of the 2017 IEEE Intelligent Vehicles Symposium (IV). Los Angeles: IEEE, 2017: 1803-1810.

[30] IYER G, RAM R K, MURTHY J K, et al. CalibNet: Geometrically Supervised Extrinsic Calibration using 3D Spatial Transformer Networks[C]// 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Madrid: IEEE, 2018: 1110-1117.

[31] LV X D, WANG B Y, DOU Z W, et al. LCCNet: LiDAR and Camera Self—Calibration using Cost Volume Network[C]// 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Nashville: IEEE, 2021: 2888-2895.

[32] XIAO Y X, LI Y, MENG C Z, et al. CalibFormer: A Transformer—based Automatic LiDAR—Camera Calibration Network[C]// 2024 IEEE International Conference on Robotics and Automation (ICRA). Piscataway: IEEE, 2023: 16714-16720.

[33] JING X, DING X Q, XIONG R, et al. DXQ—Net: Differentiable LiDAR—Camera Extrinsic Calibration Using Quality—aware Flow[C]// 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Kyoto: IEEE, 2022: 6235-6241.

[34] 史鹏涛, 危康乐, 吴昊, 等. 自动驾驶环境下基于语义分割的激光雷达与相机外参标定方法[J]. 激光与光电子学进展, 2024, 61(24): 306-311.