STEREO IMAGE BASED COLLISION PREVENTION USING THE CENSUS TRANSFORM AND THE SNOW CLASSIFIER

Christian Küblbeck, Roland Ach, Andreas Ernst

Abstract

In this paper we present an approach for a mobile robot to avoid obstacles by using a stereo-camera system mounted on it. We use the “census transformation” to generate the features for the correspondence search. We train two SNoW (Spare Network of Winnovs)-classifiers, one for the decision wether to move straight forward or to evade and a second one for deciding whether to turn left or right when evading. For training we use a sample set collected by manually moving around with the robot platform. We evaluate the performance of the whole recognition chain (feature generation and classification) using ROC-curves. Real world experiments show the mobile robot to safely avoid obstacles. Problems still arise when approaching steps or low obstacles due to limitations in the camera setup. We propose to solve this problem using a stereo camera system capable of pan and tilt movements.

References

  1. D.M. Gavrila, J. G. and Munder, S. (2004). Vision-based pedestrian detection: The protector system. Daimler Chrysler Research , Ulm.
  2. Kohtaro Sabe, Masaki Fukuchi, J.-S. G., Ohashi, T., Kawamoto, K., and Yoshigahara, T. (2004). Obstacle avoidance and path planning for humanoid robots using stereo vision. Sony Corporation, Tokyo.
  3. Libuda, L. and Kraiss, K.-F. (2004). Identification of natural landmarks for vision based navigation. Technische Universität Aachen.
  4. Masako Kumano, A. O. and Yuta, S. (2000). Obstacle avoidance of autonomous mobile robot using stereo vision sensor. University of Tsukuba.
  5. Reid Simmons, Lars Henriksen, L. C. and Whelan, G. (1996). Obstacle avoidance and safeguarding for a lunar rover. Carnegie Mellon University.
  6. Ruhr-Universität, B. (1997). Arnold, ein autonomer service-roboter. http://www.neuroinformatik.ruhruni-bochum.de/ini/PROJECTS/NEUROS/ff97- katalog/arnold d.html.
  7. Yang, M.-H., Roth, D., and Ahuja, N. (2000). A snowbased face detector. In Advances in Neural Information Processing Systems 12 (NIPS 12), pages 855- 861. MIT Press.
Download


Paper Citation


in Harvard Style

Küblbeck C., Ach R. and Ernst A. (2005). STEREO IMAGE BASED COLLISION PREVENTION USING THE CENSUS TRANSFORM AND THE SNOW CLASSIFIER . In Proceedings of the Second International Conference on Informatics in Control, Automation and Robotics - Volume 4: ICINCO, ISBN 972-8865-30-9, pages 447-454. DOI: 10.5220/0001184804470454


in Bibtex Style

@conference{icinco05,
author={Christian Küblbeck and Roland Ach and Andreas Ernst},
title={STEREO IMAGE BASED COLLISION PREVENTION USING THE CENSUS TRANSFORM AND THE SNOW CLASSIFIER},
booktitle={Proceedings of the Second International Conference on Informatics in Control, Automation and Robotics - Volume 4: ICINCO,},
year={2005},
pages={447-454},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001184804470454},
isbn={972-8865-30-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Second International Conference on Informatics in Control, Automation and Robotics - Volume 4: ICINCO,
TI - STEREO IMAGE BASED COLLISION PREVENTION USING THE CENSUS TRANSFORM AND THE SNOW CLASSIFIER
SN - 972-8865-30-9
AU - Küblbeck C.
AU - Ach R.
AU - Ernst A.
PY - 2005
SP - 447
EP - 454
DO - 10.5220/0001184804470454