Capturing Articulated Human Hand Motion: A Divide-and-Conquer Approach

The use of human hand as a natural interface device serves as a motivating force for research in the modeling, analyzing and capturing of the motion of articulated hand. Model-based hand motion capturing can be formulated as a large nonlinear programming problem, but this approach is plagued by local minima. An alternative way is to use analysis-bysynthesis by searching a huge space, but the results are rough and the computation expensive. In this paper, articulated hand motion is decoupled, a new twostep iterative model-based algorithm is proposed to capture articulated human hand motion, and a proof of convergence of this iterative algorithm is also given. In our proposed work, the decoupled global hand motion and local nger motion are parameterized by 3D hand pose and the state of the hand respectively. Hand pose determination is formulated as a least median of squares LMS problem rather than the non-robust least squares LS problem, so that 3D hand pose can be reliably calculated e...

• Type: Conference
• Year: 1999
• Where: ICCV
• Authors: Ying Wu, Thomas S. Huang
• Keywords: Computer Vision, Global Hand Motion, Hand Pose Determination, Human Hand Motion, ICCV 1999, Local Nger Motion, Model-based Hand Motion