Advertisement

Real-Time Pose Estimation Using Constrained Dynamics

  • Rune Havnung Bakken
  • Adrian Hilton
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7378)

Abstract

Pose estimation in the context of human motion analysis is the process of approximating the body configuration in each frame of a motion sequence. We propose a novel pose estimation method based on fitting a skeletal model to tree structures built from skeletonised visual hulls reconstructed from multi-view video. The pose is estimated independently in each frame, hence the method can recover from errors in previous frames, which overcomes some problems of tracking. Publically available datasets were used to evaluate the method. On real data the method performs at a framerate of \(\sim\!14\) fps. Using synthetic data the positions of the joints were determined with a mean error of \(\sim\!6\) cm.

Keywords

Pose estimation real-time model fitting 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bakken, R.H.: Using Synthetic Data for Planning, Development and Evaluation of Shape-from-Silhouette Based Human Motion Capture Methods. In: Proceedings of ISVC (2012)Google Scholar
  2. 2.
    Bakken, R.H., Hilton, A.: Real-Time Pose Estimation Using Tree Structures Built from Skeletonised Volume Sequences. In: Proceedings of VISAPP, pp. 181–190 (2012)Google Scholar
  3. 3.
    Buss, S.R.: Introduction to Inverse Kinematics with Jacobian Transpose, Pseudoinverse and Damped Least Squares Methods (2004) (unpublished manuscript), http://math.ucsd.edu/~sbuss/ResearchWeb
  4. 4.
    Caillette, F., Galata, A., Howard, T.: Real-time 3-D human body tracking using learnt models of behaviour. Computer Vision and Image Understanding 109(2), 112–125 (2008)CrossRefGoogle Scholar
  5. 5.
    Chen, Y.-L., Chai, J.: 3D Reconstruction of Human Motion and Skeleton from Uncalibrated Monocular Video. In: Zha, H., Taniguchi, R.-i., Maybank, S. (eds.) ACCV 2009, Part I. LNCS, vol. 5994, pp. 71–82. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  6. 6.
    Gkalelis, N., Kim, H., Hilton, A., Nikolaidis, N., Pitas, I.: The i3DPost multi-view and 3D human action/interaction database. In: Proceedings of the Conference for Visual Media Production, pp. 159–168 (2009)Google Scholar
  7. 7.
    Guerra-Filho, G.: A General Motion Representation - Exploring the Intrinsic Viewpoint of a Motion. In: Proceedings of GRAPP, pp. 347–352 (2012)Google Scholar
  8. 8.
    Kastenmeier, T., Vesely, F.: Numerical robot kinematics based on stochastic and molecular simulation methods. Robotica 14(03), 329–337 (1996)CrossRefGoogle Scholar
  9. 9.
    Menier, C., Boyer, E., Raffin, B.: 3D Skeleton-Based Body Pose Recovery. In: Proceedings of 3DPVT, pp. 389–396 (2006)Google Scholar
  10. 10.
    Michoud, B., Guillou, E., Bouakaz, S.: Real-Time and Markerless 3D Human Motion Capture Using Multiple Views. In: Elgammal, A., Rosenhahn, B., Klette, R. (eds.) Human Motion 2007. LNCS, vol. 4814, pp. 88–103. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  11. 11.
    Moeslund, T.B., Hilton, A., Krüger, V.: A survey of advances in vision-based human motion capture and analysis. Computer Vision and Image Understanding 104, 90–126 (2006)CrossRefGoogle Scholar
  12. 12.
    Moschini, D., Fusiello, A.: Tracking Human Motion with Multiple Cameras Using an Articulated Model. In: Gagalowicz, A., Philips, W. (eds.) MIRAGE 2009. LNCS, vol. 5496, pp. 1–12. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  13. 13.
    Poppe, R.: Vision-based human motion analysis: An overview. Computer Vision and Image Understanding 108(1-2), 4–18 (2007)CrossRefGoogle Scholar
  14. 14.
    Straka, M., Hauswiesner, S., Rüther, M., Bischof, H.: Skeletal Graph Based Human Pose Estimation in Real-Time. In: Proceedings of BMVC (2011)Google Scholar
  15. 15.
    Sundaresan, A., Chellappa, R.: Model-driven segmentation of articulating humans in Laplacian Eigenspace. IEEE Transactions on Pattern Analysis and Machine Intelligence 30(10), 1771–1785 (2008)CrossRefGoogle Scholar
  16. 16.
    Tang, W., Cavazza, M., Mountain, D., Earnshaw, R.: A constrained inverse kinematics technique for real-time motion capture animation. The Visual Computer 15(7-8), 413–425 (1999)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Rune Havnung Bakken
    • 1
  • Adrian Hilton
    • 2
  1. 1.Faculty of Informatics and e-LearningSør-Trøndelag University CollegeTrondheimNorway
  2. 2.Centre for Vision, Speech and Signal ProcessingUniversity of SurreyGuildfordUK

Personalised recommendations