Model-based articulated hand motion tracking for gesture recognition

Conventional model-based hand gesture analysis systems require high computation cost to solve the finger inverse kinematics that makes them very difficult for real-time implementation. In this paper, we propose a fast hand model fitting method for the tracking of hand motion. The model fitting method consists of (1) finding the closed-form inverse kinematics solution for the finger fitting process, and (2) defining the alignment measure for the wrist fitting process. In the experiments, we illustrate that our hand model fitting method is effective and real-time implementable.

[1]  Takeo Kanade,et al.  DigitEyes: vision-based hand tracking for human-computer interaction , 1994, Proceedings of 1994 IEEE Workshop on Motion of Non-rigid and Articulated Objects.

[2]  Alan K. Mackworth,et al.  A model-based vision system for manipulator position sensing , 1989, [1989] Proceedings. Workshop on Interpretation of 3D Scenes.

[3]  Berthold K. P. Horn.  Robot vision , 1986, MIT electrical engineering and computer science series.

[4]  Michael Girard,et al.  Computer animation of knowledge-based human grasping , 1991, SIGGRAPH.

[5]  Norman I. Badler,et al.  Articulated Figure Positioning by Multiple Constraints , 1987, IEEE Computer Graphics and Applications.

[6]  Tosiyasu L. Kunii,et al.  Model-based analysis of hand posture , 1995, IEEE Computer Graphics and Applications.

[7]  Thomas S. Huang,et al.  Vision based hand modeling and tracking for virtual teleconferencing and telecollaboration , 1995, Proceedings of IEEE International Conference on Computer Vision.

[8]  Rangachar Kasturi,et al.  Machine vision , 1995 .

[9]  Pierre David Wellner,et al.  Interacting with paper on the DigitalDesk , 1993, CACM.

[10]  P. Lancaster.  Curve and surface fitting , 1986 .

[11]  Mubarak Shah,et al.  Visual gesture recognition , 1994 .