Analyzing and Capturing Articulated Hand Motion in Image Sequences
IEEE Transactions on Pattern Analysis and Machine Intelligence
Vision-based hand pose estimation: A review
Computer Vision and Image Understanding
A real-time hand tracker using variable-length Markov models of behaviour
Computer Vision and Image Understanding
Real time trajectory based hand gesture recognition
WSEAS Transactions on Information Science and Applications
HandPuppet3D: Motion capture and analysis for character animation
Artificial Intelligence Review
3D model-based hand tracking using stochastic direct search method
FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
Trajectory based hand gesture recognition
CIMMACS'07 Proceedings of the 6th WSEAS international conference on Computational intelligence, man-machine systems and cybernetics
3D articulated hand tracking based on behavioral model
Transactions on Edutainment VIII
| Hi-index | 0.00 |
Visually capturing human hand motion requires estimatingthe 3D hand global pose as well as its local finger articulations.This is a challenging task that requires a searchin a high dimensional space due to the high degrees of freedomthat fingers exhibit and the self occlusions caused byglobal hand motion. In this paper we propose a divide andconquer approach to estimate both global and local handmotion. By looking into the palm and extra feature pointsprovided by fingers, the hand pose is determined from thepalm using Iterative Closed Point (ICP) algorithm and factorizationmethod. The hand global pose serves as the baseframe for the finger motion capturing. Noticing the naturalhand motion constraints, we propose an efficient trackingalgorithm based on sequential Monte Carlo technique fortracking finger motion. To enhance the accuracy, pose estimationsand finger articulation tracking are performed inan iterative manner. Our experiments show that our approachis accurate and robust for natural hand movements.