首页 > 论文 > 光学学报 > 38卷 > 8期(pp:815004--1)

基于非度量校正的大视场图像匹配参数标定法

Calibration Method for Large Field of View Image Matching Parameters Based on Non-Metric Correction

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对工业环境下拍摄的大视场图像受噪声与畸变影响较大,使用传统匹配参数计算方法的精度无法满足现场测量需求的问题,提出一种基于非度量校正的大视场图像匹配参数标定算法。设计了一种共线特征点布置方案,基于非度量校正完成了特征点坐标的畸变校正,并提出基于该布置方案的特征点识别匹配算法,通过分区域抽样一致性法实现匹配参数的高精度标定。实验结果表明,该算法匹配精度相较于传统方法提高了51%以上,能够满足工业环境下大视场图像匹配参数所需的精度要求。

Abstract

In order to solve the problem that images shot under industrial environment is considerably influenced by noise and distortion, precision of traditional algorithms for calibrating matching parameters cannot meet field measurement demand, a new method for calibrating large field of view image matching parameters based on non-metric correction is proposed. A layout plan of colinear feature points is designed, and based on non-metric correction, image coordinates of colinear feature points can be undistorted, which can be recognized and matched automatically with the aid of layout plan. Modified random sampling consensus algorithm based on regional division is proposed, and matching parameters can be calibrated. Experimental results show that matching precision is increased by 51% at least, which meets precision requirements under industrial environment.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:O438

DOI:10.3788/aos201838.0815004

所属栏目:“机器视觉检测与应用”专题

基金项目:国家973计划(2014CB046504)、国家自然科学基金优秀青年科学基金项目(51622501)、国家自然科学基金创新研究群体项目(51621064)

收稿日期:2018-04-23

修改稿日期:2018-05-19

网络出版日期:2018-06-07

作者单位    点击查看

张致远:大连理工大学机械工程学院, 辽宁 大连 116024
刘巍:大连理工大学机械工程学院, 辽宁 大连 116024
张洋:大连理工大学机械工程学院, 辽宁 大连 116024
逯永康:大连理工大学机械工程学院, 辽宁 大连 116024
邸宏图:大连理工大学机械工程学院, 辽宁 大连 116024
叶帆:大连理工大学机械工程学院, 辽宁 大连 116024
贾振元:大连理工大学机械工程学院, 辽宁 大连 116024

联系人作者:刘巍(2007@dlut.edu.cn); 张致远(zzy5025095@mail.dlut.edu.cn);

【1】Li G D, Tian G H, Wang H J, et al. Euclidean epipolar rectification frame of weakly calibrated stereo pairs[J]. Optics and Precision Engineering, 2014, 22(7): 1955-1961.
李国栋, 田国会, 王洪君, 等. 弱标定立体图像对的欧氏极线校正框架[J]. 光学 精密工程, 2014, 22(7): 1955-1961.

【2】Long C Y, Zhu J G, Guo Y, et al. Correspondence method based on spatial intersection in portable visual metrology[J]. Acta Optica Sinica, 2014, 34(8): 0815001.
隆昌宇, 邾继贵, 郭寅, 等. 移动视觉测量中基于空间交会的匹配方法[J]. 光学学报, 2014, 34(8): 0815001.

【3】Tang Y H, Hu X F, Lu H Z. Fast and robust fundamental matrix estimation based on SSDA[J]. Optics and Precision Engineering, 2011, 19(11): 2759-2766.
唐永鹤, 胡旭峰, 卢焕章. 应用序贯相似检测的基本矩阵快速鲁棒估计[J]. 光学 精密工程, 2011, 19(11): 2759-2766.

【4】Deriche R, Zhang Z, Luong Q T, et al. Robust recovery of the epipolar geometry for an uncalibrated stereo rig[C]∥European Conference on Computer Vision (ECCV), 1994: 567-576.

【5】Armangué X, Salvi J. Overall view regarding fundamental matrix estimation[J]. Image andVision Computing, 2003, 21(2): 205-220.

【6】Hartley R I. In defense of the eight-point algorithm[J]. IEEE Transactions onPattern Analysis and Machine Intelligence, 1997, 19(6): 580-593.

【7】Zhang Z Y. Determining the epipolar geometry and its uncertainty: a review[J]. International Journal of Computer Vision, 1998, 27(2): 161-195.

【8】Torr P H S, Murray D W. The development and comparison of robust methods for estimating the fundamental matrix[J]. International Journal of Computer Vision, 1997, 24(3): 271-300.

【9】Torr P H S. Bayesian model estimation and selection for epipolar geometry and generic manifold fitting[J]. International Journal of Computer Vision, 2002, 50(1): 35-61.

引用该论文

Zhang Zhiyuan,Liu Wei,Zhang Yang,Lu Yongkang,Di Hongtu,Ye Fan,Jia Zhenyuan. Calibration Method for Large Field of View Image Matching Parameters Based on Non-Metric Correction[J]. Acta Optica Sinica, 2018, 38(8): 0815004

张致远,刘巍,张洋,逯永康,邸宏图,叶帆,贾振元. 基于非度量校正的大视场图像匹配参数标定法[J]. 光学学报, 2018, 38(8): 0815004

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF