Extraction of Multi–modal Object Representations in a Robot Vision System

Nicolas Pugeault, Emre Baseski, Dirk Kraft, Florentin Wörgötter, Norbert Krüger

Abstract

We introduce one module in a cognitive system that learns the shape of objects by active exploration. More specifically, we propose a feature tracking scheme that makes use of the knowledge of a robotic arm motion to: 1) segment the object currently grasped by the robotic arm from the rest of the visible scene, and 2) learn a representation of the 3D shape without any prior knowledge of the object. The 3D representation is generated by stereo–reconstruction of local multi–modal edge features. The segmentation between features belonging to the object those describing the rest of the scene is achieved using Bayesian inference. We then show the shape model extracted by this system from various objects.

References

  1. C. Borst, M. Fischer, and G. Hirzinger. A fast and robust grasp planner for arbitrary 3D objects. In IEEE International Conference on Robotics and Automation, pages 1890-1896, Detroit, Michigan, May 1999.
  2. J. Sommerfeld D. Aarno, D. Kragic, N. Pugeault, S. Kalkan, F. Wörgötter, D. Kraft, and N. Krüger. Early reactive grasping with second order 3d feature relations. IEEE Conference on Robotics and Automation (submitted), 2007. submitted.
  3. James H. Elder. Are edges incomplete ? International Journal of Computer Vision, 34:97- 122, 1999.
  4. Ch. Geib, K. Mourao, R. Petrick, N. Pugeault, M. Steedman, N. Krüger, and F. Wörgötter. Object action complexes as an interface for planning and robot control. Workshop Toward Cognitive Humanoid Robots at IEEE-RAS International Conference on Humanoid Robots (Humanoids 2006), 2006.
  5. R.I. Hartley and A. Zisserman. Multiple View Geometry in Computer Vision. Cambridge University Press, 2000.
  6. N. Krüger, M. Van Hulle, and F. Wörgötter. Ecovision: Challenges in early-cognitive vision. International Journal of Computer Vision, submitted.
  7. N. Kr üger, M. Lappe, and F. Wörgötter. Biologically motivated multi-modal processing of visual primitives. Interdisciplinary Journal of Artificial Intelligence & the Simulation of Behavious, AISB Journal, 1(5):417-427, 2004.
  8. D.G. Lowe. Three-dimensional object recognition from single two images. Artificial Intelligence, 31(3):355-395, 1987.
  9. A.T. Miller, S. Knoop, H.I. Christensen, and P.K. Allen. Automatic grasp planning using shape primitives. In IEEE International Conference on Robotics and Automation, volume 2, pages 1824-1829, 2003.
  10. P. Fitzpatrick and G. Metta. Grounding vision through experimental manipulation. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 361:2165-2185, 2003.
  11. N. Pugeault, F. Wörgötter, and N. Krüger. Multi-modal scene reconstruction using perceptual grouping constraints. In Proceedings of the 5th IEEE Computer Society Workshop on Perceptual Organization in Computer Vision, New York City June 22, 2006 (in conjunction with IEEE CVPR 2006), 2006.
  12. B. Rosenhahn, O. Granert, and G. Sommer. Monocular pose estimation of kinematic chains. In L. Dorst, C. Doran, and J. Lasenby, editors, Applied Geometric Algebras for Computer Science and Engineering, pages 373-383. Birkhäuser Verlag, 2001.
Download


Paper Citation


in Harvard Style

Pugeault N., Baseski E., Kraft D., Wörgötter F. and Krüger N. (2007). Extraction of Multi–modal Object Representations in a Robot Vision System . In Robot Vision - Volume 1: Robot Vision, (VISAPP 2007) ISBN 978-972-8865-76-4, pages 126-135. DOI: 10.5220/0002068501260135


in Bibtex Style

@conference{robot vision07,
author={Nicolas Pugeault and Emre Baseski and Dirk Kraft and Florentin Wörgötter and Norbert Krüger},
title={Extraction of Multi–modal Object Representations in a Robot Vision System},
booktitle={Robot Vision - Volume 1: Robot Vision, (VISAPP 2007)},
year={2007},
pages={126-135},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002068501260135},
isbn={978-972-8865-76-4},
}


in EndNote Style

TY - CONF
JO - Robot Vision - Volume 1: Robot Vision, (VISAPP 2007)
TI - Extraction of Multi–modal Object Representations in a Robot Vision System
SN - 978-972-8865-76-4
AU - Pugeault N.
AU - Baseski E.
AU - Kraft D.
AU - Wörgötter F.
AU - Krüger N.
PY - 2007
SP - 126
EP - 135
DO - 10.5220/0002068501260135