OBSTACLE DETECTION BY STEREO VISION, INTRODUCING THE PQ METHOD

H. J. Andersen, K. Kirk, T. L. Dideriksen, C. Madsen, M. B. Holte, T. Bak

Abstract

Safe, robust operation of an autonomous vehicle in cross-country environments relies on sensing of the surroundings. Thanks to the reduced cost of vision hardware, and increasing computational power, computer vision has become an attractive alternative for this task. This paper concentrates on the use of stereo vision for obstacles detection in cross-country environments where the ground surface can not be modeled as ramps, i.e. linear patches. Given a 3D reconstruction of the surrounding environment, obstacles are detected using the concept of compatible points. The concept classify points as obstacles if they fall within the volume of cone located with its apex at the point being evaluated. The cone may be adjusted adjusted according the physical parameters of the vehicle. The paper introduces a novel Projection and Quantification method that based on vehicle orientation rotates the 3D information onto an intuitive two dimensional surface plot and quantifies the information into bins adjusted to the specific application. In this way the search space for compatible points is significantly reduced. The new method is evaluated for a specific robotic application and the results are compared to previous results on a number of typical scenarios. Combined with an intuitive representation of obstacles in a two dimensional surface plot, the results indicate a significant reduction in the computational complexity for relevant scenarios.

References

  1. Badal, S., S. Ravela, S., Draper, B., and Hanson, A. (1994). A practical obstacle detection and avoidance system. In 2nd IEEE Workshop on Applications of Computer Vision, pages 97-104.
  2. Birchfield, S. and Tomasi, C. (1999). Depth discontinuities by pixel-to-pixel stereo. International Journal of Computer Vision, 35(3):269-293.
  3. Borenstein, J. and Koren, Y. (1998). Obstacle avoidance with ultrasonic sensors. IEEE Journal of Robotics and Automation, 4(2):213-218.
  4. Fusiello, A., Trucco, E., and Verri, A. (1997). Rectification with unconstrained stereo geometry. In Proceeding of the British Machine Vision Conference, pages 400- 409.
  5. Kochan, A. (2000). Robots for automating construction - an abundance of research. The Industrial Robot, 27(2):111-113.
  6. Langer, D., Mettenleiter, M., Hartl, F., and Frohlich, C. (1999). Imaging laser radar for 3-d surveying and cad modelling of real world environments. In Proceedings of the International Conference on Field and Service Robotics, pages 13-18.
  7. Manduchi, R., Castano, A., Talukder, A., and Matthies, L. (2005). Obstacle detection and terrain classification for autonomous off-road navigation. Autonomous Robots, 18:81-102.
  8. Roth, S. A. and Batavia, P. (2002). Evaluating path tracker performance for outdoor mobile robots. In Automation Technology for Off-Road Equipment.
  9. Se, S. and Brady, M. (1998). Stereo vision-based obstacle detection for partially sighted people. In Proceedings of Third Asian Conference on Computer Vision ACCV'98, pages 152-159.
  10. Stentz, A. T., Dima, C., Wellington, C., Herman, H., and Stager, D. (2002). A system for semi-autonomous tractor operations. Autonomous Robots, 13(1):87- 103.
  11. Trucco, E. and Verri, A. (1998). Introductory Techniques for 3-D Computer Vision. Prentice Hall.
Download


Paper Citation


in Harvard Style

J. Andersen H., Kirk K., L. Dideriksen T., Madsen C., B. Holte M. and Bak T. (2005). OBSTACLE DETECTION BY STEREO VISION, INTRODUCING THE PQ METHOD . In Proceedings of the Second International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO, ISBN 972-8865-30-9, pages 250-257. DOI: 10.5220/0001168602500257


in Bibtex Style

@conference{icinco05,
author={H. J. Andersen and K. Kirk and T. L. Dideriksen and C. Madsen and M. B. Holte and T. Bak},
title={OBSTACLE DETECTION BY STEREO VISION, INTRODUCING THE PQ METHOD},
booktitle={Proceedings of the Second International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,},
year={2005},
pages={250-257},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001168602500257},
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 2: ICINCO,
TI - OBSTACLE DETECTION BY STEREO VISION, INTRODUCING THE PQ METHOD
SN - 972-8865-30-9
AU - J. Andersen H.
AU - Kirk K.
AU - L. Dideriksen T.
AU - Madsen C.
AU - B. Holte M.
AU - Bak T.
PY - 2005
SP - 250
EP - 257
DO - 10.5220/0001168602500257