Abstract
The computer vision involves many modeling problems for preventing noise caused by sensing units such as cameras. In order to improve computer vision system performance, a robust modeling technique must be developed for essential models in the system. The RANSAC (Random Sample Consensus) and LMedS (Least Median of Squares) algorithms have been widely applied in such issues. However, the performance deteriorates as the noise ratio increases and the modeling time for algorithms tends to increase in industrial applications. As a promising technique, we proposed a new fuzzy RANSAC algorithm based on reinforcement learning concept for robust modeling. In this study, we investigated sampling strategies as an indispensable concept of reinforcement learning through modeling synthetic data of fuzzy modeling and camera homography experiments. Their results found the proposed ε-roulette strategy to be promising in improving calculation time, model optimality, and robustness in modeling performance.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hartly, R., Zisserman, A.: Multiple view geometry in computer vision. Cambridge University Press, Cambridge (2000)
Sato, J.: Computer Vision - Geometry of Vision. Corona Publishing, Tokyo (1999)
Zhang, Z.: A flexible new technique for camera calibration. IEEE Trans. PAMI 22(11), 1330–1334 (2000)
Deguchi, K.: Foundation of Robot Vision. Corona Publishing, Tokyo (2000)
Watanabe, T., Saito, Y.: Camera modeling for 3D sensing using fuzzy modeling concept based on stereo vision. J. Adv. Comput. Intell. Intell. Inform. 19(1), 158–164 (2015)
Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381–395 (1981)
Watanabe, T., Kamai, T., Ishimaru, T.: Robust estimation of camera homography by fuzzy RANSAC algorithm with reinforcement learning. J. Adv. Comput. Intell. Intell. Inform. 19(6), 833–842 (2015)
Rousseeuw, P.J., Leroy, A.M.: Robust Regression and Outlier Detection. Wiley, New York (1987)
Sutton, R.S., Barto, A.G.: Reinforcement Learning. MIT Press, Boston (1998)
Lee, J., Kim, G.: Robust estimation of camera homography using fuzzy RANSAC. In: Gervasi, O., Gavrilova, Marina L. (eds.) ICCSA 2007. LNCS, vol. 4705, pp. 992–1002. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-74472-6_81
Botterill, T., Mills, S., Green, R.D.: New conditional sampling strategies for speeded-up RANSAC. In: BMVC, pp. 1–11 (2009)
Subbarao, R., Meer, P.: Beyond RANSAC: user independent robust regression. In: Computer Vision and Pattern Recognition Workshop, pp. 101–109 (2006)
Watanabe, T., Seki, H.: Modeling approach based on modular fuzzy model. J. Adv. Comput. Intell. Intell. Inform. 16(5), 653–661 (2012)
Watanabe, T.: Chapter 1: a fuzzy RANSAC algorithm based on the reinforcement learning concept for modeling. In: Harvey, T., Mullis, D. (eds.) Fuzzy Modeling and Control – Methods, Applications and Research, pp. 1–22. Nova Science Publishers, New York (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Watanabe, T. (2019). Sampling Strategies for Fuzzy RANSAC Algorithm Based on Reinforcement Learning. In: Seki, H., Nguyen, C., Huynh, VN., Inuiguchi, M. (eds) Integrated Uncertainty in Knowledge Modelling and Decision Making. IUKM 2019. Lecture Notes in Computer Science(), vol 11471. Springer, Cham. https://doi.org/10.1007/978-3-030-14815-7_11
Download citation
DOI: https://doi.org/10.1007/978-3-030-14815-7_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-14814-0
Online ISBN: 978-3-030-14815-7
eBook Packages: Computer ScienceComputer Science (R0)