Probabilistic Pose Recovery Using Learned Hierarchical Object Models

  • Renaud Detry
  • Nicolas Pugeault
  • Justus Piater
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5329)


This paper presents a probabilistic representation for 3D objects, and details the mechanism of inferring the pose of real-world objects from vision. Our object model has the form of a hierarchy of increasingly expressive 3D features, and probabilistically represents 3D relations between these. Features at the bottom of the hierarchy are bound to local perceptions; while we currently only use visual features, our method can in principle incorporate features from diverse modalities within a coherent framework. Model instances are detected using a Nonparametric Belief Propagation algorithm which propagates evidence through the hierarchy to infer globally consistent poses for every feature of the model. Belief updates are managed by an importance-sampling mechanism that is critical for efficient and precise propagation. We conclude with a series of pose estimation experiments on real objects, along with quantitative performance evaluation.


Computer vision 3D object representation pose estimation Nonparametric Belief Propagation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bouchard, G., Triggs, B.: Hierarchical part-based visual object categorization. Computer Vision and Pattern Recognition 1, 710–715 (2005)Google Scholar
  2. 2.
    Detry, R., Piater, J.H.: Hierarchical integration of local 3D features for probabilistic pose recovery. In: Robot Manipulation: Sensing and Adapting to the Real World (Workshop at Robotics, Science and Systems) (2007)Google Scholar
  3. 3.
    Epshtein, B., Ullman, S.: Feature hierarchies for object classification. In: IEEE International Conference on Computer Vision (2005)Google Scholar
  4. 4.
    Fidler, S., Leonardis, A.: Towards scalable representations of object categories: Learning a hierarchy of parts. In: CVPR 2007 (2007)Google Scholar
  5. 5.
    Fukushima, K.: Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biological Cybernetics 36(4), 193–202 (1980)CrossRefzbMATHGoogle Scholar
  6. 6.
    Ihler, A.T., Sudderth, E.B., Freeman, W.T., Willsky, A.S.: Efficient multiscale sampling from products of Gaussian mixtures. In: Neural Information Processing Systems (2003)Google Scholar
  7. 7.
    Jordan, M.I., Weiss, Y.: Graphical models: Probabilistic inference. In: Arbib, M. (ed.) The Handbook of Brain Theory and Neural Networks, 2nd edn. MIT Press, Cambridge (2002)Google Scholar
  8. 8.
    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
  9. 9.
    Marr, D., Nishihara, H.K.: Representation and recognition of the spatial organization of three dimensional shapes. Proceedings of the Royal Society of London B 200, 269–294 (1978)CrossRefGoogle Scholar
  10. 10.
    Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Francisco (1988)zbMATHGoogle Scholar
  11. 11.
    Riesenhuber, M., Poggio, T.: Hierarchical models of object recognition in cortex. Nat. Neurosci. (1999)Google Scholar
  12. 12.
    Sudderth, E.B., Ihler, A.T., Freeman, W.T., Willsky, A.S.: Nonparametric belief propagation. In: CVPR 2001, p. 605 (2003)Google Scholar
  13. 13.
    Yedidia, J.S., Freeman, W.T., Weiss, Y.: Understanding belief propagation and its generalizations. Technical report, Mitsubishi Electric Research Laboratories (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Renaud Detry
    • 1
  • Nicolas Pugeault
    • 2
  • Justus Piater
    • 1
  1. 1.Université de LiègeLiègeBelgium
  2. 2.University of Southern Denmark, Odense, Denmark,The University of Edinburgh,EdinburghScotland, UK

Personalised recommendations