Date: 2006, 3.7 (Tue) 15:50-16:20
Speaker: Kae Doki
Author: Kae Doki, Naohiro Isetani, Akihirot Torii, Akiteru Ueda
Title: Generation of Size-Variable Image Template for Self-Position Estimation Considering Position Shift
Keywords: Image Template Generation, Vision for Autonomous Mobile Robot,
Self-Position Estimation, Genetic Algorithm, Normalized Correlation Coefficient
Type: Organized Session

Affiliation: Intelligent Mechanical Engineering Course, Dept. of Mechanical Engineering, Aichi Institute of Technology
Position: Assistant Professor
Collaborator/Adviser: Akihiro Torii, Power Electronics Laboratory
Disciplines: Robotics, Intelligent Control System, Motion Planning, Artificial Intelligence
Societies and Conferences: IEEE, Robotics Society of Japan(RSJ), Institute of Electrical Engineers of Japan(IEEJ), IEEE International Conference on Robotics and Automation, IEEE/RSJ International Conference on Intelligent Robotics and Systems

Bibliography: Kae Doki, Naohiro Isetani, Akihiro Torii, and Akiteru Ueda, "Generation of Size-Variable Image Template for Self-Position Estimation Considering Position Shift", Intelligent Autonomous Systems 9 T. Arai et al. (Eds.) IOS Press, pp.999--1006, 2006.

Abstract:
We propose a new image template generation method for the self-position estimation of an autonomous mobile robot. In the proposed method, an image template is generated with Genetic Algorithm. In the proposed method of the self-position estimation, the size of the image template can be varied in order to change the time for the self-position estimation according to the situation around the robot. Therefore, the image template is searched by GA search as the size of the image is varied. The position of the robot is estimated by matching the input image with the stored image templates which indicate certain positions using the normalized correlation coefficient as a criterion
This method is sensitive to the position shift of the image. Therefore, in order to realize the robust self-position estimation for the position shift, the amount of the position shift between the image template and the input image is compensated before the template matching. In order to show the usefulness of the proposed method, some experiment
are performed in this paper. Its usefulness are verified through these experimental results.

References:
[1] K.Fujisawa, T.Aoki, S.Hayakawa, T.Suzuki, S.Okuma, A real-time search for autonomous mobile robots, Journal of the Robotics Society of Japan, Vol.17, No.4, pp.503-512, 1999.
[2] K.Doki, H.Tsutsumi, A.Torii, A.Ueda, Self-position Estimation of Autonomous Mobile Robot with Vision using Matching-time Variable Image Template, Proc. of the Sixth IASTED International Conference on Intelligent Systems and Control, 446-089(CD-ROM), 2004.
[3] K.Doki, H.Tsutsumi, A.Torii, A.Ueda, Generation of Matching-Time Variable Image Template for Vision of Autonomous Mobile Robot, Proc. of the 8th World Multi-Conference on Systemics, Cybernetics, and Informatics, Vol.VIII, pp.178-183, 2004.
[4] K.Doki, A.Torii, A.Ueda, Environment Representation Method Suitable for Action Acquisition ofan Autonomous Mobile Robot, Proc. of International Conference on Computer,Communication and Control Technologies,Vol.5, pp.283-288,2003.
[5] Y.Abe et.al, Vision Based Navigation System by Variable Template Matching for Autonomous Mobile Robot, Proc. of the 1998 IEEE International Conference on Robotics & Automation, pp.952-957, 1998.
[6] S.Zilberstein et al. Anytime Sensing, Planning and Action: A Practical Model for Robot Control", the ACM magazine, 1996.
[7] Y.Satoh et.al, Robust Image Registration Using Selective Correlation Coefficient,
Trans. of IEE Japan, Vol. 121-C, No.4, pp.1-8, 2001.
[8] D.E. Goldberg, Genetic Algorithms", Addison-Wesley, 1989.
[9] S. Mallat, A theory for Multiresolution Signal Decomposition: The Wavelet Representation, IEEE Trans. Pattern Anal. & Mach. Intell., Vol.11, No.7, pp.674-693, 1989.