Paper Info
Title
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.
Year
DOI
Venue
2002
10.1007/s00138-004-0167-0
Machine Vision and Applications
Keywords
Field
DocType
conventional marker-based hand posture,hand model,scalable hand posture analysis,analysis system,Model-based hand posture analysis,hand model fitting method,hand posture,markers method,proposed system,scalable inverse kinematics solution,scalable model-based hand posture
Computer vision,Inverse kinematics,Pattern recognition,Computer science,Artificial intelligence,Calibration,Scalability
Conference
Volume
Issue
ISSN
16
3
0932-8092
Citations 
PageRank 
References 
1
0.36
0
Authors
1
Name
Order
Citations
PageRank
Cheng-Chang Lien112813.15