Sciweavers

Share
IVC
2007

Fast stochastic optimization for articulated structure tracking

10 years 4 months ago
Fast stochastic optimization for articulated structure tracking
Recently, an optimization approach for fast visual tracking of articulated structures based on Stochastic Meta-Descent (SMD) [7] has been presented. SMD is a gradient descent with local step size adaptation that combines rapid convergence with excellent scalability. Stochastic sampling helps to avoid local minima in the optimization process. We have extended the SMD algorithm with new features for fast and accurate tracking by adapting the different step sizes between as well as within video frames and by introducing a robust cost function which incorporates both depths and surface orientations. The advantages of the resulting tracker over state-of-the-art methods are supported through 3D hand tracking experiments. A realistic deformable hand model reinforces the accuracy of our tracker. Key words: Stochastic Meta-Descent, hand tracking, deformable hand model.
Matthieu Bray, Esther Koller-Meier, Nicol N. Schra
Added 15 Dec 2010
Updated 15 Dec 2010
Type Journal
Year 2007
Where IVC
Authors Matthieu Bray, Esther Koller-Meier, Nicol N. Schraudolph, Luc J. Van Gool
Comments (0)
books