Paper Info
Title
Model-Based 3D Hand Pose Estimation from Monocular Video
Abstract
A novel model-based approach to 3D hand tracking from monocular video is presented. The 3D hand pose, the hand texture, and the illuminant are dynamically estimated through minimization of an objective function. Derived from an inverse problem formulation, the objective function enables explicit use of temporal texture continuity and shading information while handling important self-occlusions and time-varying illumination. The minimization is done efficiently using a quasi-Newton method, for which we provide a rigorous derivation of the objective function gradient. Particular attention is given to terms related to the change of visibility near self-occlusion boundaries that are neglected in existing formulations. To this end, we introduce new occlusion forces and show that using all gradient terms greatly improves the performance of the method. Qualitative and quantitative experimental results demonstrate the potential of the approach.
Year
DOI
Venue
2011
10.1109/TPAMI.2011.33
IEEE transactions on pattern analysis and machine intelligence
Keywords
Field
DocType
novel model-based approach,objective function gradient,quasi-newton method,hand tracking,explicit use,monocular video,important self-occlusions,objective function,hand pose estimation,gradient term,temporal texture continuity,hand texture,quasi newton method,three dimensional,minimisation,solid modeling,inverse problem,computer graphics,inverse problems,newton method,object tracking,pose estimation,edge detection,surface texture,gradient descent,shape from shading
Computer vision,Gradient descent,Visibility,Computer science,Pose,Video tracking,Minification,Minimisation (psychology),Artificial intelligence,Inverse problem,Newton's method
Journal
Volume
Issue
ISSN
33
9
1939-3539
Citations 
PageRank 
References 
103
3.56
22
Authors
3
Search Limit
100103
Name
Order
Citations
PageRank
Martin de La Gorce121812.78
David J. Fleet25236550.74
Nikos Paragios36055387.68