Monocular Body Pose Estimation by Color Histograms and Point Tracking

  • Daniel Grest
  • Dennis Herzog
  • Reinhard Koch
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4174)


Accurate markerless motion capture systems rely on images that allow segmentation of the person in the foreground. While the accuracy of such approaches is comparable to marker based systems, the segmentation step makes strong restrictions to the capture environment, e.g. homogenous clothing or background, constant lighting etc. In our approach a template model is fitted to images by an Analysis-by-Synthesis method, which doesn’t need explicit segmentation or homogenous clothing and gives reliable results even with non-static cluttered background.


Motion Capture Body Model Motion Capture System Template Model Correct Correspondence 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Araujo, H., Carceroni, R., Brown, C.: A Fully Projective Formulation to Improve the Accuracy of Lowe’s Pose Estimation Algorithm. Comp. Vis. and Image Understanding 70(2) (1998)Google Scholar
  2. 2.
    Bray, M., Koller-Meier, E., Mueller, P., Van Gool, L., Schraudolph, N.N.: 3D Hand Tracking by Rapid Stochastic Gradient Descent Using a Skinning Model. In: CVMP. IEEE, Los Alamitos (2004)Google Scholar
  3. 3.
    Bregler, C., Malik, J.: Tracking people with twists and exponential maps. In: Proceeding IEEE CVPR, pp. 8–15 (1998)Google Scholar
  4. 4.
    Chong, E.K.P., Zak, S.H.: An Introduction to Optimization, 2nd edn., ch. 9. Wiley, Chichester (2001)MATHGoogle Scholar
  5. 5.
    Mündermann, L., et al.: Validation of a markerless motion capture system for the calculation of lower extremity kinematics. In: Proc. American Society of Biomechanics, Cleveland, USA (2005)Google Scholar
  6. 6.
    Evers-Senne, J.-F., Frahm, J.-M., Grest, D., Köser, K., Streckel, B., Woetzel, J., Woelk, J.-F.: Basic Image AlgorithmS (BIAS) open-source-library, C++ (2005),
  7. 7.
    Grest, D., Herzog, D., Koch, R.: Human Model Fitting from Monocular Posture Images. In: Proc. of VMV (November 2005)Google Scholar
  8. 8.
    Grest, D., Woetzel, J., Koch, R.: Nonlinear Body Pose Estimation from Depth Images. In: Kropatsch, W.G., Sablatnig, R., Hanbury, A. (eds.) DAGM 2005. LNCS, vol. 3663, pp. 285–292. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  9. 9.
    Kakadiaris, I., Metaxas, D.: Model-Based Estimation of 3D Human Motion. IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI) 22(12) (2000)Google Scholar
  10. 10.
    Murray, R.M., Li, Z., Sastry, S.S.: A Mathematical Introduction to Robotic Manipulation. CRC Press, Boca Raton (1994)MATHGoogle Scholar
  11. 11.
    Niskanen, M., Boyer, E., Horaud, R.: Articulated motion capture from 3-D points and normals. In: CVMP, London (2005)Google Scholar
  12. 12.
    Plänkers, R., Fua, P.: Model-Based Silhouette Extraction for Accurate People Tracking. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2351, pp. 325–339. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  13. 13.
    Rosenhahn, B., Kersting, U.G., Smith, A.W., Gurney, J.K., Brox, T., Klette, R.: A System for Marker-Less Human Motion Estimation. In: Kropatsch, W.G., Sablatnig, R., Hanbury, A. (eds.) DAGM 2005. LNCS, vol. 3663, pp. 230–237. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  14. 14.
    Tomasi, C., Kanade, T.: Detection and tracking of point features. Technical report, Carnegie Mellon University, Pittsburg, PA (1991)Google Scholar
  15. 15.
    Wettegren, B., Christensen, L.B., Rosenhahn, B., Granert, O., Krüger, N.: Image uncertainty and pose estimation in 3d euclidian space. In: Proceedings DSAGM, pp. 76–84 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Daniel Grest
    • 1
  • Dennis Herzog
    • 1
  • Reinhard Koch
    • 1
  1. 1.Multimedia Information ProcessingChristian-Albrechts-University KielGermany

Personalised recommendations