Motion Detection and Velocity Estimation for Obstacle Avoidance using 3D Point Clouds

Sobers L. X. Francis, Sreenatha G. Anavatti, Matthew Garratt

2012

Abstract

This paper proposes a novel three dimensional (3D) velocity estimation method by using differential flow techniques for the dynamic path planning of Autonomous Ground Vehicles (AGV) in cluttered environment. We provide a frame work for the computation of dense and non rigid 3D flow vectors from the range data, obtained from the time-of-flight camera. Combined Lucas/Kanade and Horn/schunck approach is used to estimate the velocity of the dynamic obstacles. The trajectory of the dynamic obstacle is predicted from the direction of 3D flow field and the estimated velocity. By experiments, the utility of the approach is demonstrated with the results.

References

  1. Ahlskog, M. (2007). 3D Vision. Master's thesis, Department of Computer Science and Electronics, Mlardalen University.
  2. B D Lucas, T. K. (1981). An iterative image restoration technique with an application to stereo vision. In 5th International Joint Conference on Artificial Intelligence, pages 674-679.
  3. Barron, J., Fleet, D., Beauchemin, S., and Burkitt, T. (1992). Performance of optical flow techniques. In Computer Vision and Pattern Recognition, 1992. Proceedings CVPR 7892., 1992 IEEE Computer Society Conference on, pages 236 -242.
  4. Barron, J. L. and Thacker, N. A. (2005). Tutorial: computing 2D and 3D optical flow. In Tina Memo, number 2004-012.
  5. Bauer, N., Pathirana, P., and Hodgson, P. (2006). Robust Optical Flow with Combined Lucas-Kanade/HornSchunck and Automatic Neighborhood Selection. In Information and Automation, 2006. ICIA 2006. International Conference on, pages 378 -383.
  6. Bruhn, A., Weickert, J., and Schnörr, C. (2005). Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods. Int. J. Comput. Vision, 61(3):211-231.
  7. Holte, M., Moeslund, T., and Fihl, P. (2010). View-invariant gesture recognition using 3D optical flow and harmonic motion context. Computer Vision and Image Understanding, 114(12):1353 - 1361.
  8. Horn, B. K. P. and Schunck, B. G. (1981). Determining optical flow. Artifical Intelligence, 17:185-203.
  9. Iwadate, Y. (2010). Outline of three-dimensional image processing.
  10. Lange, R. (2000). 3D time-of-flight distance measurement with custom solid-state image sensors in CMOS/CCDtechnology. PhD thesis, Dep. of Electrical Engineering and Computer Science, University of Siegen.
  11. Schmidt, M., Jehle, M., and Jahne, B. (2008). Range flow estimation based on photonic mixing device data. Int. J. Intell. Syst. Technol. Appl., 5(3/4):380-392.
  12. Spies, H., Jahne, B., and Barron, J. (2002). Range flow estimation. Computer Vision and Image Understanding, 85(3):209-231.
  13. Vedula, S., Rander, P., Collins, R., and Kanade, T. (2005). Three-dimensional scene flow. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 27(3):475 -480.
  14. Weingarten, J. W., Gruener, G., and Siegwart, R. (2004). A state-of-the-art 3D sensor for robot navigation. In Intelligent Robots and Systems. In In IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, volume 3, pages 2155-2160.
  15. Yin, Xiang; Noguchi, N. (2011). Motion detection and tracking using the 3d-camera. In 18th IFAC World Congress, volume 18, pages 14139-14144.
Download


Paper Citation


in Harvard Style

L. X. Francis S., G. Anavatti S. and Garratt M. (2012). Motion Detection and Velocity Estimation for Obstacle Avoidance using 3D Point Clouds . In Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO, ISBN 978-989-8565-22-8, pages 255-259. DOI: 10.5220/0004037502550259


in Bibtex Style

@conference{icinco12,
author={Sobers L. X. Francis and Sreenatha G. Anavatti and Matthew Garratt},
title={Motion Detection and Velocity Estimation for Obstacle Avoidance using 3D Point Clouds},
booktitle={Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,},
year={2012},
pages={255-259},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004037502550259},
isbn={978-989-8565-22-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,
TI - Motion Detection and Velocity Estimation for Obstacle Avoidance using 3D Point Clouds
SN - 978-989-8565-22-8
AU - L. X. Francis S.
AU - G. Anavatti S.
AU - Garratt M.
PY - 2012
SP - 255
EP - 259
DO - 10.5220/0004037502550259