|Table of Contents|

[1] Zhang Weizhong, Zhang Liyan, Wang Xiaoping, et al. Non-iterative image feature matching algorithmbased on reference point correspondences [J]. Journal of Southeast University (English Edition), 2007, 23 (2): 190-195. [doi:10.3969/j.issn.1003-7985.2007.02.008]
Copy

Non-iterative image feature matching algorithmbased on reference point correspondences()
一种非迭代的同名标记点图像特征匹配算法
Share:

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:
23
Issue:
2007 2
Page:
190-195
Research Field:
Computer Science and Engineering
Publishing date:
2007-06-30

Info

Title:
Non-iterative image feature matching algorithmbased on reference point correspondences
一种非迭代的同名标记点图像特征匹配算法
Author(s):
Zhang Weizhong1 2 Zhang Liyan2 Wang Xiaoping2 Ding Zhian2 Zhou Ling2
1College of Information Engineering, Qingdao University, Qingdao 266071, China
2Research Center of CAD/CAM Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
张维中1 2 张丽艳2 王小平2 丁志安2 周玲2
1青岛大学信息工程学院, 青岛 266071; 2南京航空航天大学CAD/CAM工程研究中心, 南京 210016
Keywords:
reference points detection coded and non-coded target subpixel gray scale centroid point correspondence
标记点检测 编码和非编码元 亚像素 质心定位方法 同名点匹配
PACS:
TP391
DOI:
10.3969/j.issn.1003-7985.2007.02.008
Abstract:
Based on the coded and non-coded targets, the targets are extracted from the images according to their size, shape and intensity etc., and thus an improved method to identify the unique identity(ID)of every coded target is put forward and the non-coded and coded targets are classified.Moreover, the gray scale centroid algorithm is applied to obtain the subpixel location of both uncoded and coded targets.The initial matching of the uncoded target correspondences between an image pair is established according to similarity and compatibility, which are based on the ID correspondences of the coded targets.The outliers in the initial matching of the uncoded target are eliminated according to three rules to finally obtain the uncoded target correspondences.Practical examples show that the algorithm is rapid, robust and is of high precision and matching ratio.
利用编码元和非编码元, 根据标记点的尺寸、形状及灰度变化等特征提取目标, 然后利用非编码元与编码元的不同形状与灰度特征, 提出一种改进的编码元自动身份识别方法, 同时实现非编码元与编码元的分类;并利用质心定位方法抽取标记点中心位置, 抽取的中心具有亚像素级.在利用编码元的身份信息实现同名编码元匹配的基础上, 由相似性和相容性确定非编码元的初始匹配, 通过3个准则从非编码元的初始匹配中剔除误匹配, 最终得到同名非编码元的匹配结果.经实验验证, 该算法速度快、匹配率高、鲁棒性好.

References:

[1] Kanade T, Okutomi M.A stereo matching algorithm with an adaptive window: theory and experiment[J].IEEE Trans on Pattern and Machine Intelligence, 1994, 16(9):920-932.
[2] Stefano L D, Marchionni M, Mattoccia S.A fast area-based stereo matching algorithm[J].Image and Vision Computing, 2004, 22(12):983-1005.
[3] Mount D M, Netanyahu N S, Moigne J L.Efficient algorithms for robust feature matching[J].Pattern Recognition, 1999, 8(6):17-38.
[4] Carcassoni M, Hancock E R.Correspondence matching with modal clusters[J].IEEE Trans on Pattern Analysis and Machine Intelligence, 2003, 25(12):1609-1615.
[5] Zhang Z, Deriche R, Faugeras O, et al.A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry. Rapport de Recherche n.2273 [R].Shophia-Antipoles:Unité de Recherce INRIA, 1994.
[6] Galo M, Tozzi C L.Feature-point based matching:a sequential approach based on relaxation labeling and relative orientation[J].Journal of WSCG, 2004, 12(1):1-8.
[7] Keith F, Anthon V, Ndimi B.An Inexpensive, automatic and accurate camera calibration method[C]//Proceedings of the Thirteenth Annual Symposium of the Pattern Recognition Association of South Africa.Cape Town, 2002:1205-1211.
[8] Xu J, Fang Z P, Malcolm A A, et al.A robust close-range photogrammetric system for industrial metrology[C]//Proc of the 7th International Conference on Control, Automation, Robotics and Vision.Singapore, 2002:114-119.
[9] Zhou Ling. Research on key technology of 3-D reconstruction based on multiple images by using one hand-held digital camera[D].Nanjing:Research Center of CAD/CAM Engineering of Nanjing University of Aeronautics and Astronautics, 2006.(in Chinese)

Memo

Memo:
Biography: Zhang Weizhong(1963—), male, professor, zhangwz-01@163.com.
Last Update: 2007-06-20