Abstract
We present a novel fully-automatic approach for estimating an articulated skeleton of a moving subject and its motion from body marker trajectories that have been measured with an optical motion capture system. Our method does not require a priori information about the shape and proportions of the tracked subject, can be applied to arbitrary motion sequences, and renders dedicated initialization poses unnecessary. To serve this purpose, our algorithm first identifies individual rigid bodies by means of a variant of spectral clustering. Thereafter, it determines joint positions at each time step of motion through numerical optimization, reconstructs the skeleton topology, and finally enforces fixed bone length constraints. Through experiments, we demonstrate the robustness and efficiency of our algorithm and show that it outperforms related methods from the literature in terms of accuracy and speed.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Builder, V.B.: http://www.vicon.com/products/bodybuilder.html
Builder, M.A.S.: http://www.motionanalysis.com/
Motion, S.: http://www.simi.com/
Schwartz, M.H., Rozumalski, A.: A new method for estimating joint parameters from motion data. Journal of Biomechanics 38(1), 107–116 (2005)
Gamage, S.S.H.U., Lasenby, J.: New least squares solutions for estimating the average centre of rotation and the axis of rotation. Journal of Biomechanics 35(1), 87–93 (2002)
Spiegelman, J.J., Woo, S.L.: A rigid-body method for finding centers of rotation and angular displacements of planar joint motion. Journal of Biomechanics 20(7), 715–721 (1987)
Cameron, J., Lasenby, J.: A real-time sequential algorithm for human joint localization. In: Proc. SIGGRAPH 2005, Posters(111) (2005)
Ringer, M., Lasenby, J.: A procedure for automatically estimating model parameters in optical motion capture. In: BMVC (2002)
O’Brien, J.F., Bodenheimer, R., Brostow, G., Hodgins, J.K.: Automatic joint parameter estimation from magnetic motion capture data. In: Graphics Interface, pp. 53–60 (2000)
Silaghi, M.-C., Plänkers, R., Boulic, R., Fua, P., Thalmann, D.: Local and global skeleton fitting techniques for optical motion capture. In: Magnenat-Thalmann, N., Thalmann, D. (eds.) CAPTECH 1998. LNCS (LNAI), vol. 1537, pp. 26–40. Springer, Heidelberg (1998)
Kirk, A.G., O’Brien, J.F., Forsyth, D.A.: Skeletal parameter estimation from optical motion capture data. In: CVPR 2005, pp. 782–788 (2005)
Ng, A., Jordan, M., Weiss, Y.: On spectral clustering: Analysis and an algorithm (2001)
Duda, R.O., Hart, P.E.: Pattern Classification, 2nd edn. Wiley, New York, London, Sydney (2001)
Horn, B.: Closed-form solution of absolute orientation using unit quaternions. Journal of the Optical Society of America 4(4), 629–642 (1987)
Kruskal, J.B.: On the shortest spanning subtree of a graph and the traveling salesman problem. Proceedings of the American Mathematical Society 7, 48–50 (1956)
Database, C.G.L.M.C.: http://mocap.cs.cmu.edu/
Byrd, R., Lu, P., Nocedal, J., Zhu, C.: A limited memory algorithm for bound constrained optimization. SIAM J. Sci. Comp. 16, 1190–1208 (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
de Aguiar, E., Theobalt, C., Seidel, HP. (2006). Automatic Learning of Articulated Skeletons from 3D Marker Trajectories. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2006. Lecture Notes in Computer Science, vol 4291. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11919476_49
Download citation
DOI: https://doi.org/10.1007/11919476_49
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-48628-2
Online ISBN: 978-3-540-48631-2
eBook Packages: Computer ScienceComputer Science (R0)