基于静止和运动两种状态的自动导引车视觉标定

中国机械工程 ›› 2012, Vol. 23 ›› Issue (6): 703-707,724.

基于静止和运动两种状态的自动导引车视觉标定

喻俊;楼佩煌;武星;王龙军

南京航空航天大学,南京,210016

出版日期:2012-03-26 发布日期:2012-04-13
基金资助:
国家自然科学基金资助项目（61105114）；江苏省精密与微细制造技术重点实验室基金资助项目（JSPM200701);江苏省自动化装备工程技术研究中心基金资助项目（BM2006806）
National Natural Science Foundation of China（No. 61105114）

Vision Calibration for AGV Based on Static and Motion Two States

Yu Jun;Lou Peihuang;Wu Xing;Wang Longjun

Nanjing University of Aeronautics and Astronautics,Nanjing,210016

Online:2012-03-26 Published:2012-04-13
Supported by:
National Natural Science Foundation of China（No. 61105114）

摘要/Abstract

摘要：

针对一种双向型视觉导引自动导引车,提出一种基于静止和运动两种状态的视觉标定方法。首先采用静止状态下平面模板标定法标定出摄像机的内部参数、径向畸变参数和外部参数,再建立一种针对三种图像失真的联合校正模型,最后,在两种运动状态下标定出失真校正后的图像坐标系相对自动导引车坐标系的旋转和平移参数。实验结果表明该方法具有柔性好、精度高的特点。

关键词: 自动导引车, 相机标定, 图像校正, 图像失真

Abstract:

A vision calibration technique based on two states of static and motion was proposed for a vision-based bidirectional AGV.First,internal parameters,radial distortion parameters and external
parameters were estimated using planar pattern in static scene,and then an union model of correcting distortions was designed for three individual image distortion models.Finally,rotation and translation parameters between corrected image and AGV coordinate system can be calibrated in two motion cases.Experimental results show that the technique has good flexibility and high precision.

Key words: automated guided vehicle(AGV), camera calibration, image correction, image distortion

中图分类号:

TP242.2

喻俊, 楼佩煌, 武星, 王龙军. 基于静止和运动两种状态的自动导引车视觉标定[J]. 中国机械工程, 2012, 23(6): 703-707,724.

YU Dun, LOU Pei-Huang, WU Xing, WANG Long-Jun. Vision Calibration for AGV Based on Static and Motion Two States[J]. China Mechanical Engineering, 2012, 23(6): 703-707,724.

参考文献

[1]Iris F A.Vis,Survey of Research in the Design and Control of Automated Guided Vehicle Systems[J].European Journal of Operational Research,2006,170(3):677-709.
[2]Salvi J,Armangue X,Batlle J.A Comparative Re-view of Camera Calibrating Methods with Accuracy Evaluation[J].Pattern Recognition,2001,35:1617-1635.
[3]李华[1],吴福朝[2],等.基于主动视觉系统的摄像机自定标方法研究[J].自动化学报,2001,27(6):752-762.
[4]Tordoff B,Murray D W.The Impact of Radial Dis-tortion on the Self-calibration of Rotating Cameras[J].Computer Vision and Image Understanding,2004,96:17-34.
[5]王荣本,徐友春.AGVS图象识别多分支路径的研究[J].中国图象图形学报：A辑,2000(8):632-637.
[6]Guillou E,Meneveaux D,Maisel E,et al.Using Van-ishing Points for Camera Calibration and Coarse3D Reconstruction from a Single Image[J].The Visual Computer,2000,16(7):396-410.
[7]陈无畏[1],李碧春[1],孙海涛[1],许张红[2],蒋浩丰[3].基于视觉导航的AGV模糊-最优控制研究[J].中国机械工程,2006,17(24):2546-2550.
[8]孙凤梅[1],胡占义[1,2].平面单应矩阵对摄像机内参数约束的一些性质[J].计算机辅助设计与图形学学报,2007,19(5):647-650.
[9]罗晨[1],朱利民[1],丁汉[1].标定模板与图像平面平行时的摄像机标定方法[J].中国机械工程,2005,16(17):1558-1560.
[10]Zhang Zhengyou.Flexible Camera Calibration by Viewing a Plane from Unknown Orientations[C]//Proceedings of the19997th IEEE Int.Con-ference on Computer Vision(ICCV’99).Kerkyra,1999:666-673.
[11]Tsai Y.A Versatile Camera Calibration Technique for High-accuracy3D Machine Vision Metrology Using Off-the Shelf TV Cameras and Lenses[J].IEEE Int.J.Robot.Automat.,1987,3:323-344.
[12]Diebel J.Representing Attitude:Euler Angles,Unit Quaternions,and Rotation Vectors[M].Stanford:Stanford University,2006.