3D Model-based hand tracking using stochastic direct search method

John Y. Lin, Ying Wu, Thomas S. Huang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Tracking the articulated hand motion in a video sequence is a challenging problem in which the main difficulty arises from the complexity of searching for an optimal motion estimate in a high dimensional configuration space induced by the articulated motion. Considering that the complexities of this problem may be reduced by learning the lower dimensional manifold of the articulation motion in the configuration space, we propose a new representation for the non-linear manifold of the articulated motion, with a stochastic simplex algorithm that facilitates very efficient search. Contrary to traditional methods of representing the manifolds through clustering and transition matrix construction, we maintain the set of all training samples. To perform the search of best matching configuration with respect to the input image, we combine sequential Monte Carlo technique with the Nelder-Mead simplex search which is efficient and effective when the gradient is not readily accessible. This new approach has been successfully applied to hand tracking and our experiments show the efficiency and robustness of our algorithm.

Original languageEnglish (US)
Title of host publicationProceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004
Pages693-698
Number of pages6
DOIs
StatePublished - Sep 24 2004
EventProceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004 - Seoul, Korea, Republic of
Duration: May 17 2004May 19 2004

Publication series

NameProceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition

Other

OtherProceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004
CountryKorea, Republic of
CitySeoul
Period5/17/045/19/04

Fingerprint

Experiments

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Lin, J. Y., Wu, Y., & Huang, T. S. (2004). 3D Model-based hand tracking using stochastic direct search method. In Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004 (pp. 693-698). (Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition). https://doi.org/10.1109/AFGR.2004.1301615

3D Model-based hand tracking using stochastic direct search method. / Lin, John Y.; Wu, Ying; Huang, Thomas S.

Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004. 2004. p. 693-698 (Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lin, JY, Wu, Y & Huang, TS 2004, 3D Model-based hand tracking using stochastic direct search method. in Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004. Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition, pp. 693-698, Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004, Seoul, Korea, Republic of, 5/17/04. https://doi.org/10.1109/AFGR.2004.1301615
Lin JY, Wu Y, Huang TS. 3D Model-based hand tracking using stochastic direct search method. In Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004. 2004. p. 693-698. (Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition). https://doi.org/10.1109/AFGR.2004.1301615
Lin, John Y. ; Wu, Ying ; Huang, Thomas S. / 3D Model-based hand tracking using stochastic direct search method. Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004. 2004. pp. 693-698 (Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition).
@inproceedings{262ca91d632f4723abaa270fcf83d3d1,
title = "3D Model-based hand tracking using stochastic direct search method",
abstract = "Tracking the articulated hand motion in a video sequence is a challenging problem in which the main difficulty arises from the complexity of searching for an optimal motion estimate in a high dimensional configuration space induced by the articulated motion. Considering that the complexities of this problem may be reduced by learning the lower dimensional manifold of the articulation motion in the configuration space, we propose a new representation for the non-linear manifold of the articulated motion, with a stochastic simplex algorithm that facilitates very efficient search. Contrary to traditional methods of representing the manifolds through clustering and transition matrix construction, we maintain the set of all training samples. To perform the search of best matching configuration with respect to the input image, we combine sequential Monte Carlo technique with the Nelder-Mead simplex search which is efficient and effective when the gradient is not readily accessible. This new approach has been successfully applied to hand tracking and our experiments show the efficiency and robustness of our algorithm.",
author = "Lin, {John Y.} and Ying Wu and Huang, {Thomas S.}",
year = "2004",
month = "9",
day = "24",
doi = "10.1109/AFGR.2004.1301615",
language = "English (US)",
isbn = "0769521223",
series = "Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition",
pages = "693--698",
booktitle = "Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004",

}

TY - GEN

T1 - 3D Model-based hand tracking using stochastic direct search method

AU - Lin, John Y.

AU - Wu, Ying

AU - Huang, Thomas S.

PY - 2004/9/24

Y1 - 2004/9/24

N2 - Tracking the articulated hand motion in a video sequence is a challenging problem in which the main difficulty arises from the complexity of searching for an optimal motion estimate in a high dimensional configuration space induced by the articulated motion. Considering that the complexities of this problem may be reduced by learning the lower dimensional manifold of the articulation motion in the configuration space, we propose a new representation for the non-linear manifold of the articulated motion, with a stochastic simplex algorithm that facilitates very efficient search. Contrary to traditional methods of representing the manifolds through clustering and transition matrix construction, we maintain the set of all training samples. To perform the search of best matching configuration with respect to the input image, we combine sequential Monte Carlo technique with the Nelder-Mead simplex search which is efficient and effective when the gradient is not readily accessible. This new approach has been successfully applied to hand tracking and our experiments show the efficiency and robustness of our algorithm.

AB - Tracking the articulated hand motion in a video sequence is a challenging problem in which the main difficulty arises from the complexity of searching for an optimal motion estimate in a high dimensional configuration space induced by the articulated motion. Considering that the complexities of this problem may be reduced by learning the lower dimensional manifold of the articulation motion in the configuration space, we propose a new representation for the non-linear manifold of the articulated motion, with a stochastic simplex algorithm that facilitates very efficient search. Contrary to traditional methods of representing the manifolds through clustering and transition matrix construction, we maintain the set of all training samples. To perform the search of best matching configuration with respect to the input image, we combine sequential Monte Carlo technique with the Nelder-Mead simplex search which is efficient and effective when the gradient is not readily accessible. This new approach has been successfully applied to hand tracking and our experiments show the efficiency and robustness of our algorithm.

UR - http://www.scopus.com/inward/record.url?scp=4544320575&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=4544320575&partnerID=8YFLogxK

U2 - 10.1109/AFGR.2004.1301615

DO - 10.1109/AFGR.2004.1301615

M3 - Conference contribution

AN - SCOPUS:4544320575

SN - 0769521223

SN - 9780769521220

T3 - Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition

SP - 693

EP - 698

BT - Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004

ER -