Pose Estimation of Randomly Organized Stator Housings

  • Thomas B. Moeslund
  • Jakob Kirkegaard
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3540)

Abstract

Machine vision is today a well-established technology in industry where especially conveyer belt applications are successful. A related application area is the situation where a number of objects are located in a bin and each has to be picked from the bin. This problem is known as the automatic bin-picking problem and has a huge market potential due to the countless situations where bin-picking is done manually. In this paper we address a general bin-picking problem present at a large pump manufacturer, Grundfos, where many objects with circular openings are handled each day. We pose estimate the objects by finding the 3D opening based on the elliptic projections into two cameras. The ellipses from the two cameras are handled in a unifying manner using graph theory together with an approach that links a pose and an ellipse via the equation for a general cone. Tests show that the presented algorithm can estimate the poses for a large variety of orientations and handle both noise and occlusions.

References

  1. 1.
    Balslev, I., Eriksen, R.D.: From belt picking to bin picking. Proceedings of SPIE - The International Society for Optical Engineering 4902, 616–623 (2002)Google Scholar
  2. 2.
    Berger, M., Bachler, G., Scherer, S.: Vision Guided Bin Picking and Mounting in a Flexible Assembly Cell. In: 13th International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems IEA/AIE 2000, New Orleans, Louisiana, USA (June 2000)Google Scholar
  3. 3.
    Faugeras, O.: Three-Dimensional Computer Vision - A Geometric Viewpoint, 1st edn. The MIT Press, CambridgeGoogle Scholar
  4. 4.
    Fitzgibbon, A.W., Pilu, M., Fisher, R.B.: Direct least-squares fitting of ellipses. IEEE Transactions on Pattern Analysis and Machine Intelligence 21(5), 476–480 (1999)CrossRefGoogle Scholar
  5. 5.
    Kirkegaard, J.: Pose estimation of randomly organised stator housings with circular features. Technical report, Aalborg University, Laboratory of Computer Vision and Media Technology (2005)Google Scholar
  6. 6.
    Kirkpatrick, S., Gelatt, C.D., Vecchi, M.P.: Optimization by simulated annealing. Science 220(4598), 671–680 (1983)CrossRefMathSciNetGoogle Scholar
  7. 7.
    Lowe, D.G.: Three-dimensional object recognition from single two-dimensional images. Artificial Intelligence 31(3), 355–395 (1987)CrossRefGoogle Scholar
  8. 8.
    Moeslund, T.B., Aagaard, M., Lerche, D.: 3D Pose Estimation of Cactus Leaves using an Active Shape Model. In: IEEE Workshop on Applications of Computer Vision (WACV), Breckenridge, Colorado (January 2005)Google Scholar
  9. 9.
    Motai, Y., Kosaka, A.: Concatenate feature extraction for robust 3d elliptic object localization. In: Applied Computing 2004 - Proceedings of the 2004 ACM Symposium on Applied Computing, vol. 1, pp. 21–28 (2004)Google Scholar
  10. 10.
    Pope, A.R.: Learning to recognize objects in images: Acquiring and using probabilistic models of appearance. Technical report, The University of British Columbia, Department of Computer Science (1995)Google Scholar
  11. 11.
    Rosin, P.L.: Nonparametric segmentation of curves into various representations. IEEE Transactions on Pattern Analysis and Machine Intelligence 17(12), 1140–1153 (1995)CrossRefGoogle Scholar
  12. 12.
    Safaee-Rad, R., Tchoukanov, I., Carless Smith, K., Benhabib, B.: Three-dimensional location estimation of circular features for machine vision. IEEE Transactions on Robotics and Automation 8(5), 624–640 (1992)CrossRefGoogle Scholar
  13. 13.
    Torras, C.: Computer Vision - Theory and Industrial Applications, 1st edn. Springer, Heidelberg (1992)Google Scholar
  14. 14.
    Trucco, E., Verri, A.: Introductory Techniques for 3D Computer Vision, 1st edn. Prentice-Hall, Englewood Cliffs (1998)Google Scholar
  15. 15.

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Thomas B. Moeslund
    • 1
  • Jakob Kirkegaard
    • 1
  1. 1.Laboratory of Computer Vision and Media TechnologyAalborg UniversityDenmark

Personalised recommendations