Stochastic Meta-Descent for Tracking Articulated Structures

Recently, an optimization approach for fast visual tracking of articulated structures based on Stochastic Meta-Descent (SMD) 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 likelihood function which incorporates both depths and surface orientations. A realistic deformable hand model reinforces the accuracy of our tracker. The advantages of the resulting tracker over state-of-the-art methods are corroborated through experiments.

[1]  Kenneth Levenberg A METHOD FOR THE SOLUTION OF CERTAIN NON – LINEAR PROBLEMS IN LEAST SQUARES , 1944 .

[2]  Andrew Blake,et al.  Articulated body motion capture by annealed particle filtering , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[3]  D. Marquardt An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[4]  David J. Fleet,et al.  Stochastic Tracking of 3D Human Figures Using 2D Image Motion , 2000, ECCV.

[5]  Luc Van Gool,et al.  Real-time range scanning of deformable surfaces by adaptively coded structured light , 2003, Fourth International Conference on 3-D Digital Imaging and Modeling, 2003. 3DIM 2003. Proceedings..

[6]  Ying Wu,et al.  Capturing natural hand articulation , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[7]  William H. Press,et al.  Numerical recipes in C , 2002 .

[8]  John P. Lewis,et al.  Pose Space Deformation: A Unified Approach to Shape Interpolation and Skeleton-Driven Deformation , 2000, SIGGRAPH.

[9]  Takeo Kanade,et al.  Model-based tracking of self-occluding articulated objects , 1995, Proceedings of IEEE International Conference on Computer Vision.

[10]  Michael Isard,et al.  CONDENSATION—Conditional Density Propagation for Visual Tracking , 1998, International Journal of Computer Vision.

[11]  Nicol N. Schraudolph,et al.  3D hand tracking by rapid stochastic gradient descent using a skinning model , 2004 .

[12]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Cristian Sminchisescu,et al.  Covariance scaled sampling for monocular 3D body tracking , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[14]  Marc Levoy,et al.  Real-time 3D model acquisition , 2002, ACM Trans. Graph..