3D Hand Tracking by Rapid Stochastic Gradient Descent Using a Skinning Model

M. Bray, E. Koller-Meier, P. Müller, L. Van Gool, and N. N. Schraudolph. 3D Hand Tracking by Rapid Stochastic Gradient Descent Using a Skinning Model. In First European Conference on Visual Media Production (CVMP), pp. 59–68, London, 2004.
Latest version

Download

2.7MB	601.2kB	4.0MB

Abstract

The main challenge of tracking articulated structures like hands is their large number of degrees of freedom (DOFs). A realistic 3D model of the human hand has at least 26 DOFs. The arsenal of tracking approaches that can track such structures fast and reliably is still very small. This paper proposes a tracker based on Stochastic Meta-Descent (SMD) for optimizations in such high-dimensional state spaces. This new algorithm is based on a gradient descent approach with adaptive and parameter-specific step sizes. The SMD tracker facilitates the integration of constraints, and combined with a stochastic sampling technique, can get out of spurious local minima. Furthermore, the integration of a deformable hand model based on linear blend skinning and anthropometrical measurements reinforce the robustness of our tracker. Experiments show the efficiency of the SMD algorithm in comparison with common optimization methods.

BibTeX Entry

@inproceedings{BraKolMueVanetal04,
     author = {Matthieu Bray and Esther Koller-Meier and Pascal M\"uller
               and Luc Van~Gool and Nicol N. Schraudolph},
      title = {\href{http://nic.schraudolph.org/pubs/BraKolMueVanetal04.pdf}{
               {3D} Hand Tracking by Rapid Stochastic Gradient Descent
               Using a Skinning Model}},
      pages = {59--68},
  booktitle = {First European Conference on Visual Media Production (CVMP)},
    address = {London},
       year =  2004,
   b2h_type = {Other},
  b2h_topic = {>Stochastic Meta-Descent, Computer Vision},
   b2h_note = {<a href="b2hd-BraKolMueSchetal05.html">Latest version</a>},
   abstract = {
    The main challenge of tracking articulated structures like hands
    is their large number of degrees of freedom (DOFs). A realistic 3D
    model of the human hand has at least 26 DOFs. The arsenal of tracking
    approaches that can track such structures fast and reliably is still
    very small.
    This paper proposes a tracker based on Stochastic Meta-Descent
    (SMD) for optimizations in such high-dimensional state spaces. This
    new algorithm is based on a gradient descent approach with adaptive
    and parameter-specific step sizes. The SMD tracker facilitates the
    integration of constraints, and combined with a stochastic sampling
    technique, can get out of spurious local minima. Furthermore,
    the integration of a deformable hand model based on linear blend
    skinning and anthropometrical measurements reinforce the robustness
    of our tracker. Experiments show the efficiency of the SMD algorithm
    in comparison with common optimization methods.
}}