[1]李杭龙,杨涛,李济泽.基于单目视觉的单图标定算法[J].福建工程学院学报,2022,20(06):573-579.[doi:10.3969/j.issn.1672-4348.2022.06.011]
　LI Hanglong,YANG Tao,LI Jize.Research on single image calibration algorithm based on monocular vision[J].Journal of FuJian University of Technology,2022,20(06):573-579.[doi:10.3969/j.issn.1672-4348.2022.06.011]
点击复制

基于单目视觉的单图标定算法()
分享到：

《福建工程学院学报》[ISSN:2097-3853/CN:35-1351/Z]

卷:
第20卷
期数:
2022年06期
页码:
573-579
栏目:
出版日期:
2022-12-25

文章信息/Info

Title:
Research on single image calibration algorithm based on monocular vision
作者:
李杭龙; 杨涛; 李济泽
福建工程学院福建省智能加工技术及装备重点实验室（福建工程学院）
Author(s):
LI Hanglong;  YANG Tao;  LI Jize
Fujian Key Laboratory of Intelligent Machining Technology and Equipment
关键词:
单目视觉; 单图标定; 仿射变换; 畸变矫正; Halcon
Keywords:
monocular vision;  single graph calibration;  affine transformation;  distortion correction;  Halcon
分类号:
TP391.41
DOI:
10.3969/j.issn.1672-4348.2022.06.011
文献标志码:
A
摘要:
为了满足现代工业生产中精度要求高、操作快捷的要求，提出基于单目视觉的单图标定算法。通过采集一张棋盘格标定板图像，精确提取棋盘格角点坐标，使用仿射变换得到像素坐标系和世界坐标系的仿射变换矩阵，分析Halcon仿射变换矩阵和张氏标定法相机模型的对应关系，得到详细的相机内参，再对图像进行畸变矫正，得到像素当量。多次Halcon实验结果表明，提出的算法与其他方法相比，操作更加快捷，标定结果标准差可控制在0.02 mm 以内，能够满足现代工业生产需要。
Abstract:
In order to meet the requirement of high accuracy and fast operation in modern industrial production, a single image identification algorithm based on monocular vision was proposed. By collecting a checkerboard calibration board image, accurate extraction of checkerboard corner coordinates, affine transformation matrix of pixel coordinate system and world coordinate system was obtained by affine transformation. By analyzing the corresponding relationship between Halcon affine transformation matrix and Zhang’s calibration camera model, detailed camera internal parameters were obtained. Finally, the pixel equivalent was obtained by distortion correction of the image. Halcon experiments show that the proposed method is faster than other methods, and the standard deviation of calibration results can be controlled within 0.02 mm, which can meet the needs of modern industrial production.

参考文献/References:

[1] 汤小伟, 杨玉萍, 张磊, 等. 一种考虑畸变的摄像机线性标定方法[J]. 机械设计与制造, 2021（5）: 251-255. [2] TSAI R. A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses[J]. IEEE Journal on Robotics and Automation, 1987, 3（4）: 323-344.[3] ZHANG Z. A flexible new technique for camera calibration[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22（11）: 1330-1334.[4] 项志宇, 孙波. 折反射全向相机镜面位姿的自标定方法[J]. 光学学报, 2012, 32（4）: 161-168.[5] 彭妍, 郭君斌, 于传强, 等. 基于平面变换的高精度相机标定方法[J]. 北京航空航天大学学报, 2022, 48（7）: 1297-1303.[6] 娄群, 吕钧澔, 文立华, 等.基于亚像素边缘检测的高精度相机标定方法[J/OL].光学学报:1-16[2022-09-02].http:∥kns.cnki.net/kcms/detail/31.1252.o4.20220714.1356.160.html.[7] 杨幸芳, 黄玉美, 高峰, 等. 用于摄像机标定的棋盘图像角点检测新算法[J]. 仪器仪表学报, 2011, 32（5）: 1109-1113.[8] DATTA A, KIM J S, KANADE T. Accurate camera calibration using iterative refinement of control points[C]∥2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops. Kyoto, Japan: IEEE: 1201-1208.[9] 王丞, 田暄, 郭瑞, 等. 自适应Harris角点提取的点云粗配准算法[J]. 西安交通大学学报, 2022, 56（3）: 33-44.[10] 张建国, 陈维光, 莘明星, 等. 一种基于LabVIEW的摄像机非线性畸变标定方法[J]. 船舶工程, 2018, 40（12）: 64-68, 76.[11] 胡均平, 宋菲菲, 罗春雷, 等. 一种基于自适应角点检测的非量测畸变校正方法[J]. 激光与光电子学进展, 2021, 58（12）: 175-181.

更新日期/Last Update: 2022-12-25