An Optimal Algorithm for Estimating Fundamental Matrix by Removing the Outliers

Li Qian Guo; Jun Bi Liao; Fang Ping Zhong; Xiang Yu; Jun Tao

doi:10.4028/www.scientific.net/AMR.989-994.1435

Paper Titles

Concentration and Distribution of Cr, Pb and Zn in the Jurassic Coals from Northern Shaanxi and Ningxia, China
p.1415

The Quantitative Model Research of Impact of Water Level Changes on Channel Capacity
p.1419

Porosity Inversion under the Sequence Stratigraphy Framework
p.1424

Analysis on Acidity and Alkalinity of Metallogenetic Environment in Penecontemporaneous Period on the Bauxite in WZD Area, Northern Guizhou, China
p.1428

An Optimal Algorithm for Estimating Fundamental Matrix by Removing the Outliers
p.1435

Complex Network Optimization Research of Personalization-Based Recommendation Algorithm
p.1441

Algorithm Study and Application of Personalized Intelligent Recommendation Engine
p.1445

Research on Marine Fuel Boiler Drum Water Level Model and Dynamic Analysis
p.1449

Studies on Broad-Sense Sample Method in Data Mining
p.1453

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 989-994An Optimal Algorithm for Estimating Fundamental...

An Optimal Algorithm for Estimating Fundamental Matrix by Removing the Outliers

Abstract:

The accurate estimation of the fundamental matrix is one of the most important steps in many computer vision applications such as 3D reconstruction, camera self-calibration, motion estimation and stereo matching. In this paper, an optimal fundamental matrix estimation method based on removing exceptional match points is proposed. Firstly, the initial mismatch is reduced by the bidirectional SIFT feature matching algorithm. Secondly, the partial concentration problem of random samples is solved by the bucket segmentation method. In order to obtain robustness, the fundamental matrix is estimated in a RANSAC framework according to the principle of minimizing the geometric distance. Finally, the iterate process improves the accuracy of the fundamental matrix by using the LM algorithm. Experimental results show that the proposed method can reduce the outlier’s interference better and improve the estimation precision of the fundamental matrix.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 989-994)

Pages:

1435-1440

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.989-994.1435

Citation:

Cite this paper

Online since:

July 2014

Authors:

Li Qian Guo*, Jun Bi Liao, Fang Ping Zhong, Xiang Yu, Jun Tao

Keywords:

Computer Vision, Epipolar Geometry, Fundamental Matrix, Non-Linear Optimization

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] R.I. Hartley, A. Zisserman: Mu1tip1e View Geometry in Computer Vision. (Second Edition, Cambridge University Press, Cambridge 2004).

Google Scholar

[2] H.X. Zhong: Research on Methods for Estimating the Fundamental Matrix. Doctor's Thesis of Jilin university, China (2005), pp.22-37.

Google Scholar

[3] R.I. Hartley: In defence of the 8-point algorithm. In: Proceedings of the 5th International Conference on Computer Vision, IEEE Computer Society Press, Boston (1995), p.1064–1070.

Google Scholar

[4] J. Zhang, Z.P. Hu, Z.Y. Ou: An Exceptional Points Removing Based Optimal Algorithm for Estimating Fundamental Matrix. J. Computer Engineering, vol. 31, no. 13 (2005), pp.12-15.

Google Scholar

[5] X.L. Xiao: New Fundamental Matrix Estimation Method Using Global Optimization. In: 2010 International Conference on Computer Application and System Modeling, vol. 7 (2010), p.402.

DOI: 10.1109/iccasm.2010.5620116

Google Scholar

[6] Y.J. Huang, W.J. Liu: A Method for Fundamental Matrix Estimation Using LQS. Journal of Image and Graphics, vol. 14, no. 10 (2009), p.2069-(2072).

Google Scholar