Probabilistic Object Models for Pose Estimation in 2D Images

  • Damien Teney
  • Justus Piater
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6835)

Abstract

We present a novel way of performing pose estimation of known objects in 2D images. We follow a probabilistic approach for modeling objects and representing the observations. These object models are suited to various types of observable visual features, and are demonstrated here with edge segments. Even imperfect models, learned from single stereo views of objects, can be used to infer the maximum-likelihood pose of the object in a novel scene, using a Metropolis-Hastings MCMC algorithm, given a single, calibrated 2D view of the scene. The probabilistic approach does not require explicit model-to-scene correspondences, allowing the system to handle objects without individually-identifiable features. We demonstrate the suitability of these object models to pose estimation in 2D images through qualitative and quantitative evaluations, as we show that the pose of textureless objects can be recovered in scenes with clutter and occlusion.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Collet, A., Berenson, D., Srinivasa, S., Ferguson, D.: Object recognition and full pose registration from a single image for robotic manipulation. In: ICRA (2009)Google Scholar
  2. 2.
    Collet, A., Srinivasa, S.S.: Efficient multi-view object recognition and full pose estimation. In: ICRA, pp. 2050–2055 (2010)Google Scholar
  3. 3.
    Detry, R.: A probabilistic framework for 3D visual object representation: Experimental data (2009), http://intelsig.org/publications/Detry-2009-PAMI/
  4. 4.
    Detry, R., Piater, J.: Continuous surface-point distributions for 3D object pose estimation and recognition. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010, Part III. LNCS, vol. 6494, pp. 572–585. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  5. 5.
    Detry, R., Pugeault, N., Piater, J.: A probabilistic framework for 3D visual object representation. IEEE Trans. PAMI 31(10), 1790–1803 (2009)CrossRefGoogle Scholar
  6. 6.
    Ekvall, S., Hoffmann, F., Kragic, D.: Object recognition and pose estimation for robotic manipulation using color cooccurrence histograms. In: IROS (2003)Google Scholar
  7. 7.
    Gordon, I., Lowe, D.G.: What and where: 3D object recognition with accurate pose. In: Toward Category-Level Object Recognition, pp. 67–82 (2006)Google Scholar
  8. 8.
    Hsiao, E., Collet, A., Hebert, M.: Making specific features less discriminative to improve point-based 3D object recognition. In: CVPR, pp. 2653–2660 (2010)Google Scholar
  9. 9.
    Klein, G., Drummond, T.: Robust visual tracking for non-instrumented augmented reality. In: ISMAR, Tokyo, pp. 113–122 (October 2003)Google Scholar
  10. 10.
    Kraft, D., Krüger, N.: Object sequences (2009), http://www.mip.sdu.dk/covig/sequences.html
  11. 11.
    Kragic, D., Miller, A.T., Allen, P.K.: Real-time tracking meets online grasp planning. In: ICRA, pp. 2460–2465 (2001)Google Scholar
  12. 12.
    Krüger, N., Wörgötter, F.: Multi-modal primitives as functional models of hyper-columns and their use for contextual integration. In: De Gregorio, M., Di Maio, V., Frucci, M., Musio, C. (eds.) BVAI 2005. LNCS, vol. 3704, pp. 157–166. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  13. 13.
    Mittrapiyanuruk, P., DeSouza, G.N., Kak, A.C.: Calculating the 3D pose of rigid objects using active appearance models. In: ICRA, pp. 5147–5152 (2004)Google Scholar
  14. 14.
    Pless, R.: Using many cameras as one. In: CVPR (2), pp. 587–593 (2003)Google Scholar
  15. 15.
    Pope, A.R., Lowe, D.G.: Probabilistic models of appearance for 3D object recognition (2000)Google Scholar
  16. 16.
    Pugeault, N.: Early Cognitive Vision: Feedback Mechanisms for the Disambiguation of Early Visual Representation. VDM Verlag Dr. Müller (2008)Google Scholar
  17. 17.
    Rothganger, F., Lazebnik, S., Schmid, C., Ponce, J.: 3D object modeling and recognition using local affine-invariant image descriptors and multi-view spatial constraints. Int. J. Comput. Vision 66(3), 231–259 (2006)CrossRefGoogle Scholar
  18. 18.
    Sudderth, E.B.: Graphical models for visual object recognition and tracking. Ph.D. thesis, Massachusetts Institute of Technology, Cambridge, MA, USA (2006)Google Scholar
  19. 19.
    Vacchetti, L., Lepetit, V., Fua, P.: Stable real-time 3D tracking using online and offline information. IEEE Trans. PAMI 26(10), 1385–1391 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Damien Teney
    • 1
  • Justus Piater
    • 2
  1. 1.University of LiègeBelgium
  2. 2.University of InnsbruckAustria

Personalised recommendations