基于随机抽样一致性算法的运动标定方法

doi:10.16731/j.cnki.1671-3133.2017.10.022

现代制造工程 ›› 2017, Vol. 445 ›› Issue (10): 115-120.doi: 10.16731/j.cnki.1671-3133.2017.10.022

• 仪器仪表/检测/监控 • 上一篇下一篇

基于随机抽样一致性算法的运动标定方法

杨硕^1,2, 李素华², 高峰³

1 上海交通大学自动化系,上海 200030;
2 昆山工研院新型平板显示技术中心有限公司,昆山 215300;
3 昆山国显光电有限公司,昆山 215300

收稿日期:2016-05-06 出版日期:2017-10-20 发布日期:2018-01-08
作者简介:杨硕,硕士研究生,中级工程师,主要从事运动控制和图像处理与标定方面的研究工作。 E-mail:yangshuo@visionox.com

Motion calibration method based on RANSAC algorithm

Yang Shuo^1,2, Li Suhua², Gao Feng³

1 Department of Automation,Shanghai Jiaotong University,Shanghai 200030,China;
2 Kunshan New Flat Panel Display Technology Center Co.Ltd., Kunshan 215300,Jiangsu,China;
3 Kunshan GOvisionox Optoelectronics Co.Ltd.,Kunshan 215300,Jiangsu,China

Received:2016-05-06 Online:2017-10-20 Published:2018-01-08

摘要/Abstract

摘要： 在邦定设备运动标定过程中收集到的对位平台旋转中心的样本数据包含有各种干扰,以至于利用其进行推导时过程复杂、结果精度低且鲁棒性不高。为了解决以上问题,提出一种基于随机抽样一致性算法的简单方法,该方法的构建基于样本数据分布密度模型,该模型进行一定次数的迭代筛选后,其最优解集合可进行精确推导。试验表明,在使用随机选取的10组样本数据的计算中,本方法平均计算时间为697.6s,标定精度在7.2pixel以内,并且有7组数据的结果均满足10 pixel的像素精度要求。整个标定结果达到国外同类型设备的先进水平,能够完全满足设备运行的要求。

关键词: 邦定设备, 运动标定, 随机一致抽样, 样本数据分布密度的模型

Abstract: The sample data of the rotating center of the alignment platform collected in the process of motion calibration for the bonding equipment has so many interferences,which cause a lot of problems like complexity,low accuracy and robustness in derivation process.In order to solve the problem, figures out a simple solution based on Random Sample Consensus(RANSAC)algorithm.By carrying out iteration screening several times with the solution based on the density distribution model of the sample data,we can derive the results on the basis of the optimum solution.The experimental results show that by using iterative calculation within 10 groups of random sample datum,it costs 697.6 seconds on average,and the calibration accuracy of this method is within 7.2 pixels. Besides,the results of the 7 datasets all meet the precision requirement of the 10 pixels.The results reach the same performance level of the Japan and South Korea’s equipment and absolutely conform to the requirements of the equipment operation.

Key words: bonding equipment, motion calibration, Random Sample Consensus(RANSAC), the density distribution model of the sample data

中图分类号:

TN873.93

杨硕, 李素华, 高峰. 基于随机抽样一致性算法的运动标定方法[J]. 现代制造工程, 2017, 445(10): 115-120.

Yang Shuo, Li Suhua, Gao Feng. Motion calibration method based on RANSAC algorithm[J]. Modern Manufacturing Engineering, 2017, 445(10): 115-120.

参考文献

[1] 常永亮.COG倒装设备的控制系统研究与优化[D].上海:上海交通大学,2010.
[2] 鲜飞.芯片封装技术的发展历程[J].印制电路信息,2009(6):65-70.
[3] ZHANG Z Y.A Flexible New Technique for Camera Calibration[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(11):1330-1334.
[4] ZHANG Z Y.Flexible Camera Calibration by Viewing a Plane from Unknown Orientation.Proceedings of International Conference on Computer Vision[C].Kerkyra,Greece:IEEE Press,1999:666-673.
[5] LENZ R K,TSAI R Y.Technology for Calibration of the Scale Factor and Image Centre for High Accuracy 3-D Machine Version Metrology[J].IEEE Trans on Pattern Analysis and Machine Intelligence,1988,10(5):68-75.
[6] TSAI R Y.A Versatile Camera Calibration Technique for High-Accuracy 3D Machine Version Metrology Using Off-the-Shelf TV Cameras and Lenses[J].IEEE Journal on Robotics & Automation,2003,3(4):323-344.
[7] 张建军.图像识别技术在全自动对位贴合机的应用[J].电子工艺技术,2010(4):226-229.
[8] INABA Takanori.Position Alignment System By XYθ Stage:JP2007018494A[P].2007-01-25.
[9] YAZAKI Tomohiro,INABA Takanori,MASUDA Katsutoshi,et al.Calibration Method,Positioning Method,Positioning Device,Calibration Program And Positioning Program:JP2003050106A[P].2003-02-21.
[10] 史红新.自动化液晶模块(COG)预压绑定视觉对位系统[J].制造业自动化,2014(14):151-158.
[11] WANG Lei,LI David,LIU Gang.Machine Vision System Calibration Using Inaccurate Calibration Targets:US20140267681A1[P].2014-09-18.
[12] 冯振华.新型大尺寸TFT_LCD玻璃研磨机的研制[D].西安:西安电子科技大学,2011.
[13] SUNGLOK Choi,TAEMIN Kim,WONPIL Yu.Performance Evaluation of RANSAC Family.British Machine Vision Conference[C].London,UK:DBLP,2009.
[14] FISCHLER M A,BOLLES R C.Random Sample Consensus:A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography[J].Communications of the ACM,1981,24 (6):381-395.
[15] CHUM O,MATAS J.Randomized RANSAC with T(d,d) Test[J].In Proceedings of the British Machine Vision Conference,2002(V2):448-457.
[16] 陈付幸,王润生.基于预检验的快速随机抽样一致性算法[J].软件学报,2005,16(8):1431-1438.
[17] 杨兵兵,胡士强.随机抽样一致消除特征错配的一种加速算法[J].电气自动化,2013,6(35):103-105.

基于随机抽样一致性算法的运动标定方法

Motion calibration method based on RANSAC algorithm

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics