JACIII Vol.19 No.6 pp. 833-842
doi: 10.20965/jaciii.2015.p0833


Robust Estimation of Camera Homography by Fuzzy RANSAC Algorithm with Reinforcement Learning

Toshihiko Watanabe*, Takeshi Kamai**, and Tomoki Ishimaru*

*Graduate School of Engineering, Osaka Electro-Communication University
18-8 Hatsu-cho, Neyagawa, Osaka 572-8530, Japan
**Icom Inc.
1-1-32 Kamiminami, Hirano-ku, Osaka 547-0003, Japan

June 5, 2015
August 18, 2015
Online released:
November 20, 2015
November 20, 2015
RANSAC, fuzzy set, reinforcement learning, robust estimation, computer vision

The computer vision approach involves many modeling problems in preventing noise caused by sensing units such as cameras and projectors. To improve computer vision modeling performance, a robust modeling technique must be developed for essential models in the system. The RANSAC and LMedS algorithms have been widely applied in such issues, but performance deteriorates as the noise ratio increases and the calculation time for algorithms tends to increase in actual applications. In this study, we propose a new fuzzy RANSAC algorithm for homography estimation based on the reinforcement learning concept. The performance of the algorithm is evaluated by modeling synthetic data and camera homography experiments. Their results found the method to be effective in improving calculation time, model optimality, and robustness in modeling performance.

  1. [1]  R. Hartly and A. Zisserman, “Multiple view geometry in computer vision,” Cambridge University Press, 2000.
  2. [2]  J. Sato, “Computer vision – geometry of vision –,” Corona Publishing, 1999.
  3. [3]  Z. Zhang, “A flexible new technique for camera calibration,” IEEE Trans. on PAMI, Vol.22, Issue.11, pp. 1330-1334, 2000.
  4. [4]  Z. Zhang, “A flexible new technique for camera calibration,” Microsoft Technical Report, MSR-TR-98-71, 1998.
  5. [5]  K. Deguchi, “Foundation of robot vision,” Corona Publishing, 2000.
  6. [6]  T. Watanabe and Y. Saito, “Camera modeling for 3d sensing using fuzzy modeling concept based on stereo vision,” J. of Advanced Computational Intelligence and Intelligent Informatics, Vo1.19, No.1, pp. 158-164, 2015.
  7. [7]  M. A. Fischler and R. C. Bolles, “Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography,” Communications of the ACM, Vol.24, No.6, pp. 381-395, 1981.
  8. [8]  T. Watanabe, “A fuzzy RANSAC algorithm based on reinforcement learning concept,” Proc. of the 2013 IEEE Int. Conf. on Fuzzy Systems, pp. 1-6, 2013.
  9. [9]  P. J. Rousseeuw and A. M. Leroy, “Robust regression and outlier detection,” John Wiley & Sons, 1987.
  10. [10]  Open CV, [Accessed September 5, 2015]
  11. [11]  J. Lee and G. Kim, “Robust estimation of camera homography using fuzzy RANSAC,” ICCSA 2007, LNCS 4705, Part I, pp. 992-1002, 2007.
  12. [12]  T. Botterill, S. Mills, and R. D. Green, “New conditional sampling strategies for speeded-up RANSAC,” BMVC 2009, pp. 1-11, 2009.
  13. [13]  R. Subbarao and P. Meer, “Beyond RANSAC: user independent robust regression, ” Computer Vision and Pattern Recognition Workshop, pp. 101-109, 2006.
  14. [14]  R. S. Sutton and A. G. Barto, “Reinforcement learning, ” MIT Press, 1998.
  15. [15]  T. Watanabe and H. Seki, “Modeling approach based on modular fuzzy model,” J. of Advanced Computational Intelligence and Intelligent Informatics, Vo1.16, No.5, pp. 653-661, 2012.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, IE9,10,11, Opera.

Last updated on Mar. 27, 2017