Abstract
In this article, techniques in design of a vision system for walking machines are considered and solutions to some problems particularly connected to walking are proposed. Unlike a wheeled robot, a walking robot represents a rather long kinematic chain connecting its camera system to the ground. The camera orientation obtained by internal sensors is not sufficiently accurate, because of the variable kinematics of a walking robot and the vibrations caused by walking. However, this information is very useful for efficient scene interpretation. The algorithm proposed in this article estimates the orientation of the camera system using the pose of recognized objects. Since the information of the camera orientation is not available prior to object recognition, the objects have to be recognized by certain features invariant to rotations and translations in 6 DoF.
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
Preview
Unable to display preview. Download preview PDF.
References
A. Califano and R. Mohan. Multidimensional Indexing for Recognizing Visual Shapes. IEEE Trans. on PAMI, pages 373–392, April 1994.
C. Eberst, M. Barth, K. Lutz, A. Mair, S. Schmidt, and G. Färber. Robust Video-Based Object Recognition Integrating Highly Redundant Cues for Indexing and Verification. In Proceedings of the IEEE Int. Conf. on Robotics and Automation, pages 3757–3763, San Francisco, California, 2000.
J.F. Seara, G. Schmidt, and O. Lorch. ViGWaM Active Vision System— Gaze Control for Goal-Oriented Walking. In Proc. of the Intl. Conf. on Climbing and Walking Robots (CLAWAR), Karlsruhe, Germany, September 2001.
O.D. Faugeras and M. Hebert. The Representation, Recognition, and Locating of 3-D Objects. The Int. Journal of Robotics Research, 5(3):27–52, Fall 1986.
S. Kagami, J. J. Kuffner Jr., K. Nishiwaki, T. Sugihara, T. Michikata, T. Aoyama, M. Inaba, and H. Inoue. Design and Implementation of Remotely Operation Interface for Humanoid Robot. In Proceedings of the IEEE Int. Conf. on Robotics and Automation, pages 401–406, Seoul, Korea, 2001.
O. Lorch, M. Buss, F. Freyberger, and G. Schmidt. Aspekte der bildverarbeitungsgestützten Lokomotion humanoider Laufmaschinen. In G. Schmidt, U. Hanebeck, and F. Freyberger, Editors, Tagungsband zum 15. Fachgespräch AMS, pages 22–32, München, Germany, November 1999. Springer Verlag.
D.G. Lowe. Perceptual Organization and Visual Recognition. Kluwer Academic Publishers, Boston/Dordrecht/Lancaster, 1 edition, 1995.
D.J. Pack. Perception-Based Control for a Quadruped Walking Robot. In Proceedings of the IEEE Int. Conf. on Robotics and Automation, pages 2994–3001, Minneapolis, Minnesota, 1996.
D. Shin, A. Takanishi, T. Yoshigahara, T. Takeya, S. Ohteru, and I. Kato. Realization of Obstacle Avoidance by Biped Walking Robot Equiped with Vision System. In Proceedings of the IEEE/RSJ Int. Conf. Intelligent Robots and Systems, pages 268–275, Tsukuba, Japan, 1989.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cupec, R., Lorch, O., Schmidt, G. (2001). Object Recognition and Estimation of Camera Orientation for Walking Machines. In: Levi, P., Schanz, M. (eds) Autonome Mobile Systeme 2001. Informatik aktuell. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-56787-2_1
Download citation
DOI: https://doi.org/10.1007/978-3-642-56787-2_1
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42552-6
Online ISBN: 978-3-642-56787-2
eBook Packages: Springer Book Archive