基于柱状物点云语义特征的相机激光联合标定算法

朱添翼; 张羊阳; 刘江波; 丁钊; 曹军

您当前的位置：

首页 >

文章列表页 >

基于柱状物点云语义特征的相机激光联合标定算法

光学传感与测量 | 更新时间：2026-05-20

- 基于柱状物点云语义特征的相机激光联合标定算法
- Joint calibration algorithm for camera and lidar based on semantic features of cylindrical object point clouds
- 光学技术 2026年52卷第3期页码：302-307
- 作者机构：
  
  安徽江淮汽车集团股份有限公司规划控制设计部，安徽合肥 230601
- 作者简介：
  
  朱添翼（1992— ），男，中级工程师，从事摄影测量与遥感和多传感器融合研究。zhu.ty@qq.com
- 基金信息：
- DOI：
  中图分类号： TP751
- 收稿：2026-03-06，
  
  修回：2026-04-14，
  
  纸质出版：2026-05-20
- 稿件说明：
移动端阅览
朱添翼,张羊阳,刘江波等.基于柱状物点云语义特征的相机激光联合标定算法[J].光学技术,2026,52(03):302-307.

ZHU Tianyi,ZHANG Yangyang,LIU Jiangbo,et al.Joint calibration algorithm for camera and lidar based on semantic features of cylindrical object point clouds[J].OPTICAL TECHNIQUE,2026,52(03):302-307.
朱添翼,张羊阳,刘江波等.基于柱状物点云语义特征的相机激光联合标定算法[J].光学技术,2026,52(03):302-307. DOI：

ZHU Tianyi,ZHANG Yangyang,LIU Jiangbo,et al.Joint calibration algorithm for camera and lidar based on semantic features of cylindrical object point clouds[J].OPTICAL TECHNIQUE,2026,52(03):302-307. DOI：

摘要

多传感器精确标定是实现智能驾驶环境感知的基础，其中激光雷达与相机联合标定是关键环节。传统方法依赖人工布设标定板，存在操作繁琐、场景适应性差等问题；同时，激光点云数据量大，与视觉特征匹配效率低下，制约了标定系统的自动化与实时性。针对上述挑战，文章提出一种基于自然场景柱状物语义特征的激光雷达与相机联合标定算法。首先，利用点云语义分割技术提取环境中的柱状物（如路灯、树干等），并以其边缘点作为3D特征；同时，采用SURF算法提取图像中对应区域的边缘点特征。通过将柱状物点云反投影至图像平面，建立鲁棒的2D-3D对应关系，并基于特征匹配优化求解外参矩阵。方法的核心创新在于：（1）摆脱对标定板的依赖，利用普遍存在的柱状地物实现自适应标定，大幅提升标定便捷性；（2）引入语义分割降低点云处理维度，结合边缘点特征描述，在保证精度的前提下显著提高匹配效率；（3）通过反投影与特征匹配的迭代优化，增强了算法对复杂光照和遮挡的鲁棒性。在KITTI数据集上的实验结果表明，所提算法在标定精度上优于传统线元素标定，但标定效率提升约95%，且无需人工干预，为自动驾驶多传感器在线标定提供了一种高效、实用的解决方案。

Abstract

Accurate multi-sensor calibration is fundamental for environment perception in intelligent driving

with the joint calibration of LiDAR and camera being a critical component. Traditional methods rely on manually placed calibration boards

which suffer from cumbersome operation and poor scene adaptability. Additionally

the large volume of LiDAR point cloud data and the inefficiency of matching with visual features constrain the automation and real-time performance of calibration systems. To address these challenges

a joint calibration algorithm for LiDAR and camera based on the semantic features of pole-shaped objects in natural scenes is proposed. First

point cloud semantic segmentation technology is employed to extract pole-shaped objects （e.g.

streetlights

tree trunks） from the environment

using their edge points as 3D features. Concurrently

the SURF algorithm is applied to extract edge point features from corresponding regions in the image. By back-projecting the point cloud of pole-shaped objects onto the image plane

robust 2D-3D correspondences are established

and the extrinsic parameter matrix is optimized through feature matching. The core innovations of this method are: （1） It eliminates dependence on calibration boards by leveraging ubiquitously available pole-shaped landmarks for adaptive calibration

significantly enhancing convenience; （2） It introduces semantic segmentation to reduce the dimensionality of point cloud processing

combined with edge point feature description

which markedly improves matching efficiency without compromising accuracy; （3） Through iterative optimization of back-projection and feature matching

the algorithm's robustness to complex lighting and occlusion is strengthened. Experimental results on the KITTI dataset demonstrate that the proposed algorithm surpasses traditional automatic line-based calibration in accuracy while improving calibration efficiency by approximately 95%. It operates without manual intervention

offering an efficient and practical solution for online multi-sensor calibration in autonomous driving.

关键词

Keywords

references

Clavijo M , Jiménez Felipe , et al . The development and prospects of autonomous driving technology [J ] . Applied Sciences 2023 , 13 （ 9 ）: 2076 — 3417 .

Yang B , Li J , Zeng T . A review of environmental perception technology based on multi-sensor information fusion in autonomous driving [J ] . World Electric Vehicle Journal , 2025 , 16 （ 1 ）: 20 .

林俊钦 , 胡晓明 , 闫达远 . 场景轮廓的动态规划立体匹配算法 [J ] . 光学技术 , 2013 （ 1 ）: 5 .

Lin Junqin , Hu Xiaoming , Yan Dayuan . Dynamic programming stereo matching algorithm for scene profiles [J ] . Optical Technology , 2013 （ 1 ）: 5 .

周铖君 . 基于多传感器融合的智能小车导航技术研究 [D ] . 南京 : 南京信息工程大学 , 2024 .

Zhou Chengjun . Research on navigation technology of intelligent vehicle based on multi-sensor fusion [D ] . Nanjing : Nanjing University of Information Science and Technology , 2024 .

支帅 , 韩世豪 , 丁国鹏 , 等 . 立体视觉与激光测距仪联合标定方法 [J ] . 红外与激光工程 , 2025 , 54 （ 8 ）: 147 — 158 .

Zhi Shuai , Han Shihao , Ding Guopeng , et al . A joint calibration method of stereo vision and laser rangefinder [J ] . Infrared and Laser Engineering , 2025 , 54 （ 8 ）: 147 — 158 .

王晶 , 方俊永 , 刘学 , 等 . 一种不同地面分辨率图像的拼接算法 [J ] . 光学技术 , 2014 （ 4 ）: 7 .

Wang Jing , Fang Junyong , Liu Xue , et al . A mosaic algorithm for images with different ground resolutions [J ] . Optical Technique , 2014 （ 4 ）: 7 .

Lyu X , Liu S , Qiao R , et al . Camera, LiDAR, and IMU spatiotemporal calibration: methodological review and research perspectives [J ] . Sensors , 2025 , 25 （ 17 ）: 5409 .

Zhang H , Li S , Zhu X , et al . 3D LiDAR and monocular camera calibration: A review [J ] . IEEE Sensors Journal , 2025 , 25 （ 7 ）: 10530 — 10555 .

Zhang Q , Pless R . Extrinsic calibration of a camera and laser range finder （improves camera calibration） [C ] // 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems . Sendai : IEEE , 2004 : 2301 — 2306 .

Geiger A , Moosmann F , Car Ö , et al . Automatic camera and range sensor calibration using a single shot [C ] // 2012 IEEE International Conference on Robotics and Automation . Saint Paul : IEEE , 2012 : 3936 — 3943 .

Wu H , Liu Y , Huang H , et al . Targetless external reference calibration of LiDAR and camera in autonomous driving environment [J ] . IEEE Transactions on Instrumentation and Measurement , 2024 , 73 : 1 — 9 .

Pusztai Z , Hajder L . Accurate calibration of LiDAR-camera systems using ordinary boxes [C ] // 2017 IEEE International Conference on Computer Vision Workshops . Venice : IEEE , 2017 : 394 — 402 .

Park Y , Yun S , Won C S , et al . Calibration between color camera and 3D LIDAR instruments with a polygonal planar board [J ] . Sensors , 2014 , 14 （ 3 ）: 5333 — 5353 .

Dhall A , Chelani K , Radhakrishnan V , et al . LiDAR-camera calibration using 3D-3D point correspondences [EB/OL ] . （ 2017-05-26 ）[ 2026-03-07 ] .

Zhou L , Li Z , Kaess M . Automatic extrinsic calibration of a camera and a 3D LiDAR using line and plane correspondences [C ] // 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems （IROS） . IEEE , 2018 : 5562 — 5569

Yuan X , Wang S , Xie Y , et al . Object-based semantic fusion algorithm of Lidar and camera via inverse projection [J ] . IEEE Transactions on Instrumentation and Measurement , 2025 , 74 : 1 — 15 .

Umam M K S , Yoo J , Utama I B K Y , et al . TransCalib: Automated extrinsic calibration of LiDAR-camera fusion using convolutional transformer for targetless self-alignment [J ] . IEEE Access , 2025 , 13 : 171185 — 171200 .

Xiong F , Zhang Z , Kong Y , et al . MSANet: LiDAR-camera online calibration with multi-scale fusion and attention mechanisms [J ] . Remote Sensing , 2024 , 16 （ 22 ）: 4233 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

一种激光雷达轴棱锥光学空间滤波器

双向博弈平行反卷积网络下的饮片高光谱测量鉴别

基于改进希尔伯特-黄变换的单帧相位解调技术

反射镜膜层折射率对Golay3稀疏孔径光学系统偏振成像特性的影响研究

基于优化暗通道先验算法的烟雾浓度测量方法研究