A scalable model-based hand posture analysis system

Abstract.Model-based hand posture analysis systems fall into two categories: hand without markers and hand with markers methods. The hand model fitting method proposed in this paper belongs to the second category. However, the main problems that make conventional marker-based hand posture analysis systems inapplicable are their inefficient calculation of the inverse kinematics, their inability to scale the size of the hand model, and their inability to analyze hand posture when some markers are occluded. In this paper, a scalable hand posture analysis system is proposed to overcome these problems. The proposed system consists of three new techniques: (1) the generation of scalable inverse kinematics solutions for the finger-positioning process, (2) a scale calibration process for the 3D hand model, and (3) a 3D marker position prediction method for occluded markers. The experimental results illustrate that the scalable hand posture analysis system outperforms conventional marker-based hand posture analysis systems.

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

[2]  Tosiyasu L. Kunii,et al.  Constraint-Based Hand Animation , 1993 .

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

[4]  David Zeltzer,et al.  A survey of glove-based input , 1994, IEEE Computer Graphics and Applications.

[5]  Yuntao Cui,et al.  Hand sign recognition from intensity image sequences with complex backgrounds , 1996, Proceedings of the Second International Conference on Automatic Face and Gesture Recognition.

[6]  Chung-Lin Huang,et al.  Hand gesture recognition using a real-time tracking method and hidden Markov models , 2003, Image Vis. Comput..

[7]  Zbigniew Michalewicz,et al.  Genetic Algorithms + Data Structures = Evolution Programs , 1996, Springer Berlin Heidelberg.

[8]  David C. Hogg,et al.  Towards 3D hand tracking using a deformable model , 1996, Proceedings of the Second International Conference on Automatic Face and Gesture Recognition.

[9]  Chung-Lin Huang,et al.  The model-based dynamic hand posture identification using genetic algorithm , 1998, Machine Vision and Applications.

[10]  Chung-Lin Huang,et al.  Dynamic scene analysis using path and shape coherence , 1992, Pattern Recognit..

[11]  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.

[12]  Stelios C. A. Thomopoulos,et al.  An iterative solution to the inverse kinematics of robotic manipulators , 1991 .

[13]  Wei-Song Lin,et al.  Calibration of an active binocular head , 1998, IEEE Trans. Syst. Man Cybern. Part A.

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

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

[16]  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.

[17]  Takeo Kanade,et al.  Visual Tracking of High DOF Articulated Structures: an Application to Human Hand Tracking , 1994, ECCV.

[18]  Chong-Wah Ngo,et al.  Gesture tracking and recognition for lecture video editing , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[19]  Yoshiaki Shirai,et al.  Hand gesture estimation and model refinement using monocular camera-ambiguity limitation by inequality constraints , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[20]  Yoshiaki Shirai,et al.  Model Adaptation and Posture Estimation of Moving Articulated Object Using Monocular Camera , 2000, AMDO.

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