Advertisement

Catadioptric Silhouette-Based Pose Estimation from Learned Models

  • Christian Reinbacher
  • Markus Heber
  • Matthias Rüther
  • Horst Bischof
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6688)

Abstract

The automated handling of objects requires the estimation of object position and rotation with respect to an actuator. We propose a system for silhouette-based pose estimation, which can be applied to a variety of objects, including untextured and slightly transparent objects. Pose estimation inevitably relies on previous knowledge of the object’s 3D geometry. In contrast to traditional view-based approaches our system creates the required 3D model solely from the object silhouettes and abandons the need to obtain a model beforehand. It is sufficient to rotate the object in front of the catadioptric camera system. Experimental results show that the pose estimation accuracy drops only slightly compared to a highly accurate input model. The whole system utilizes the parallel processing power of graphics cards, to deliver an auto calibration in 20s and reconstructions and pose estimations in 200ms.

Keywords

pose estimation model creation shape from silhouette catadioptric multi-view 

References

  1. 1.
    Byne, J., Anderson, J.: A CAD-based computer vision system. Image and Vision Computing 16(8), 533–539 (1998)CrossRefGoogle Scholar
  2. 2.
    Costa, M.S., Shapiro, L.G.: 3D object recognition and pose with relational indexing. Computer Vision and Image Understanding 79(3), 364–407 (2000)CrossRefzbMATHGoogle Scholar
  3. 3.
    Cyr, C., Kimia, B.: 3D object recognition using shape similiarity-based aspect graph. In: ICCV, pp. 254–261 (2001)Google Scholar
  4. 4.
    Fofi, D., Sliwa, T., Voisin, Y.: A comparative survey on invisible structured light. In: SPIE, vol. 5303, pp. 90–98 (May 2004)Google Scholar
  5. 5.
    Gluckman, J., Nayar, S.K.: Catadioptric stereo using planar mirrors. IJCV 44 (2001)Google Scholar
  6. 6.
    Heber, M., Ruether, M., Bischof, H.: Catadioptric multiview pose estimation for robotic pick and place. In: VISAPP, vol. 1, pp. 423–426 (2010)Google Scholar
  7. 7.
    Hernandez, C., Schmitt, F., Cipolla, R.: Silhouette coherence for camera calibration under circular motion. PAMI 29(2), 343–349 (2007)CrossRefGoogle Scholar
  8. 8.
    Hu, B., Brown, C., Nelson, R.: Multiple-view 3-D reconstruction using a mirror. Tech. rep., University of Rochester (May 2005)Google Scholar
  9. 9.
    Laurentini, A.: The visual hull concept for silhouette-based image understanding. PAMI 2 (1994)Google Scholar
  10. 10.
    Lorensen, W.E., Cline, H.E.: Marching cubes: A high resolution 3d surface construction algorithm. SIGGRAPH 21(4), 163–169 (1987)CrossRefGoogle Scholar
  11. 11.
    Nelder, J.A., Mead, R.: A simplex method for function minimization. The Computer Journal 7(4), 308–313 (1965)MathSciNetCrossRefzbMATHGoogle Scholar
  12. 12.
    Reinbacher, C., Ruether, M., Bischof, H.: Pose estimation of known objects by efficient silhouette matching. In: ICPR (2010)Google Scholar
  13. 13.
    Santner, J., Unger, M., Pock, T., Leistner, C., Saffari, A., Bischof, H.: Interactive texture segmentation using random forests and total variation. In: BMVC, London, UK (September 2009)Google Scholar
  14. 14.
    Scharstein, D., Szeliski, R.: High-accuracy stereo depth maps using structured light. In: CVPR, vol. 1, pp. 195–202 (June 2003)Google Scholar
  15. 15.
    Szeliski, R.: Rapid octree construction from image sequences. In: CVGIP, vol. 58, pp. 23–32 (1993)Google Scholar
  16. 16.
    Ulrich, M., Wiedemann, C., Steger, C.: CAD-based recognition of 3D objects in monocular images. In: ICRA, pp. 1191–1198 (2009)Google Scholar
  17. 17.
    Zhang, Z.: Flexible camera calibration by viewing a plane from unknown orientations. In: ICCV, pp. 666–673 (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Christian Reinbacher
    • 1
  • Markus Heber
    • 1
  • Matthias Rüther
    • 1
  • Horst Bischof
    • 1
  1. 1.Institute for Computer Graphics and VisionGraz University of TechnologyGrazAustria

Personalised recommendations