Optimize Fundamental Matrix Estimation Based on RANSAC

Abstract:

Fundamental matrix estimation is a central problem in computer vision and forms the basis of tasks such as stereo imaging and structure from motion, and which is especially difficult since it is often based on correspondences that are spoilt by noise and outliers. The Random Sample Consensus (RANSAC) algorithm is a popular tool for robust estimation, primarily due to its ability to tolerate a tremendous fraction of outliers. In this article, we provide an approach for improve of RANSAC that has the benefit of offering fast and accurate RANSAC, and combine the M-estimation algorithm get the fundamental matrix. Experimental results are given that support the adopted approach and demonstrate the algorithm is a practical technique for fundamental matrix estimation.

• Periodical: Applied Mechanics and Materials (Volumes 50-51)
• Pages: 333-337
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.50-51.333
• Online since: February 2011
• Authors: Jun Zhou
• Keywords: Fundamental Matrix, Matching, RANSAC, Robust Estimation

References

[1] P.H.S. Torr and D.W. Murray : The development and comparison of robust methods for estimating the fundamental matrix, International Journal of Computer Vision , vol. 24 (3)(1997) , p.271.

[2] R. Hartley and A. Zisserman: Multiple View Geometry, Cambridge University Press(2000).

[3] H.C. Longuet-Higgins: A Computer Algorithm for Reconstructing a Scene from Two Projections, Nature, vol. 293(1981), no. 10, p.133.

DOI: 10.1038/293133a0

[4] R.I. Hartley: Estimation of Relative Camera Positions for Uncalibrated Cameras, Proc. Second European Conf. Computer Vision, Lecture Notes in Computer Science, vol. 588(1992), p.579.

DOI: 10.1007/3-540-55426-2_62

[5] R. Hartley: In Defense of the Eight-Point Algorithm, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19(1997), no. 6, p.580.

DOI: 10.1109/34.601246

[6] Z.Y. Zhang: Determining the epipolar geometry and its uncertainty: A review, Tech. Rep. 2927, Institut National de Recherche en Informatique et en Automatique(1996).

[7] Q.T. Luong and O.D. Faugeras: Determining the Fundamental matrix with planes: instability and new algorithms, Proceedings, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (1993), CVPR(93), p.489.

DOI: 10.1109/cvpr.1993.341085

[8] H. Chen and P. Meer: Robust Regression with Projection Based M-Estimators, Proc. IEEE Int'l Conf. Computer Vision (2003), p.878.

[9] E. Malis and E. Marchand: Experiments with robust estimation techniques in real-time robot vision, IEEE/RSJ International Conference on Intelligent Robots and Systems (2006), p.223.

DOI: 10.1109/iros.2006.282572

[10] O. Chum, J. Matas, and J. Kittler: Locally Optimized RANSAC, Proc. Ann. Symp. German Assoc. for Pattern Recognition (2003).

DOI: 10.1007/978-3-540-45243-0_31

[11] M. Fischler and R. Bolles: Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography, Comm. ACM, vol. 24(1981), no. 6, p.381.

DOI: 10.1145/358669.358692