Real-Time Volumetric Reconstruction and Tracking of Hands in a Desktop Environment

  • Christoph John
  • Ulrich Schwanecke
  • Holger Regenbrecht
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5702)

Abstract

A probabilistic framework for vision based volumetric reconstruction and marker free tracking of hand and face volumes is presented, which exclusively relies on off-the-shelf hardware components and can be applied in standard office environments. Here a 3D reconstruction of the interaction environment (user-space) is derived from multiple camera viewpoints which serve as input sources for mixture particle filtering to infer position estimates of hand and face volumes. The system implementation utilizes graphics hardware to comply with real-time constraints on a single desktop computer.

Keywords

Probabilistic Shape From Silhouette Mixture Particle Filtering 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    IEEE Recommended Practice for Electric Power Systems in Commercial Buildings, p. 388 (1990)Google Scholar
  2. 2.
    Caetano, T., Olabarriaga, S., Barone, D.: Performance evaluation of single and multiple-gaussian models for skin color modeling. In: XV Brazilian Symposium on Computer Graphics and Image Processing, Proceedings, pp. 275–282 (2002)Google Scholar
  3. 3.
    Koller, D., Weber, J., Huang, T., Malik, J., Ogasawara, G., Rao, B., Russell, S.: Towards robust automatic traffic scene analysis in real-time. In: Proceedings of the International Conference on Pattern Recognition (1994)Google Scholar
  4. 4.
    Landabaso, J., Pardas, M.: A unified framework for consistent 2-d/3-d foreground object detection. IEEE Transactions on Circuits and Systems for Video Technology 18(8), 1040–1051 (2008)CrossRefGoogle Scholar
  5. 5.
    Landabaso, J.L., Pardàs, M.: Shape from Inconsistent Silhouette. Accepted for publication in Journal of Computer Vision and Image Understanding (2008)Google Scholar
  6. 6.
    Minka, T.: The ‘summation hack’ as an outlier model. Unpublished manuscript (2003), http://research.microsoft.com/~minka
  7. 7.
    Vermaak, J., Doucet, A., Perez, P.: Maintaining multi-modality through mixture tracking. In: ICCV 2003, vol. 2, p. 1110 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Christoph John
    • 1
    • 2
  • Ulrich Schwanecke
    • 2
  • Holger Regenbrecht
    • 1
  1. 1.University of OtagoNew Zealand
  2. 2.University of Applied Sciences WiesbadenGermany

Personalised recommendations