Accurate head pose tracking in low resolution video

Juin Tu, Thomas S Huang, Hai Tao

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

Abstract

Estimating 3D head poses accurately in low resolution video is a challenging vision task because it is difficult to find continuous one-to-one mapping from person-independent low resolution visual representation to head pose parameters. We propose to track head poses by modeling the shape-free facial textures acquired from the video with subspace learning techniques. In particular, we propose to model the facial appearance variations online by incremental weighted PCA subspace with forgetting mechanism, and we do the tracking in an annealed particle filtering framework. Experiments show that, the tracking accuracy of our approach outperforms past visual face tracking algorithms especially in low resolution videos.

Original languageEnglish (US)
Title of host publicationFGR 2006
Subtitle of host publicationProceedings of the 7th International Conference on Automatic Face and Gesture Recognition
Pages573-578
Number of pages6
DOIs
StatePublished - Nov 14 2006
EventFGR 2006: 7th International Conference on Automatic Face and Gesture Recognition - Southampton, United Kingdom
Duration: Apr 10 2006Apr 12 2006

Publication series

NameFGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition
Volume2006

Other

OtherFGR 2006: 7th International Conference on Automatic Face and Gesture Recognition
CountryUnited Kingdom
CitySouthampton
Period4/10/064/12/06

Fingerprint

Textures
Experiments

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Tu, J., Huang, T. S., & Tao, H. (2006). Accurate head pose tracking in low resolution video. In FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition (pp. 573-578). [1613080] (FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition; Vol. 2006). https://doi.org/10.1109/FGR.2006.19

Accurate head pose tracking in low resolution video. / Tu, Juin; Huang, Thomas S; Tao, Hai.

FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition. 2006. p. 573-578 1613080 (FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition; Vol. 2006).

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

Tu, J, Huang, TS & Tao, H 2006, Accurate head pose tracking in low resolution video. in FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition., 1613080, FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition, vol. 2006, pp. 573-578, FGR 2006: 7th International Conference on Automatic Face and Gesture Recognition, Southampton, United Kingdom, 4/10/06. https://doi.org/10.1109/FGR.2006.19
Tu J, Huang TS, Tao H. Accurate head pose tracking in low resolution video. In FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition. 2006. p. 573-578. 1613080. (FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition). https://doi.org/10.1109/FGR.2006.19
Tu, Juin ; Huang, Thomas S ; Tao, Hai. / Accurate head pose tracking in low resolution video. FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition. 2006. pp. 573-578 (FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition).
@inproceedings{3f3d5bb2403b47ab8c972566b6996bec,
title = "Accurate head pose tracking in low resolution video",
abstract = "Estimating 3D head poses accurately in low resolution video is a challenging vision task because it is difficult to find continuous one-to-one mapping from person-independent low resolution visual representation to head pose parameters. We propose to track head poses by modeling the shape-free facial textures acquired from the video with subspace learning techniques. In particular, we propose to model the facial appearance variations online by incremental weighted PCA subspace with forgetting mechanism, and we do the tracking in an annealed particle filtering framework. Experiments show that, the tracking accuracy of our approach outperforms past visual face tracking algorithms especially in low resolution videos.",
author = "Juin Tu and Huang, {Thomas S} and Hai Tao",
year = "2006",
month = "11",
day = "14",
doi = "10.1109/FGR.2006.19",
language = "English (US)",
isbn = "0769525032",
series = "FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition",
pages = "573--578",
booktitle = "FGR 2006",

}

TY - GEN

T1 - Accurate head pose tracking in low resolution video

AU - Tu, Juin

AU - Huang, Thomas S

AU - Tao, Hai

PY - 2006/11/14

Y1 - 2006/11/14

N2 - Estimating 3D head poses accurately in low resolution video is a challenging vision task because it is difficult to find continuous one-to-one mapping from person-independent low resolution visual representation to head pose parameters. We propose to track head poses by modeling the shape-free facial textures acquired from the video with subspace learning techniques. In particular, we propose to model the facial appearance variations online by incremental weighted PCA subspace with forgetting mechanism, and we do the tracking in an annealed particle filtering framework. Experiments show that, the tracking accuracy of our approach outperforms past visual face tracking algorithms especially in low resolution videos.

AB - Estimating 3D head poses accurately in low resolution video is a challenging vision task because it is difficult to find continuous one-to-one mapping from person-independent low resolution visual representation to head pose parameters. We propose to track head poses by modeling the shape-free facial textures acquired from the video with subspace learning techniques. In particular, we propose to model the facial appearance variations online by incremental weighted PCA subspace with forgetting mechanism, and we do the tracking in an annealed particle filtering framework. Experiments show that, the tracking accuracy of our approach outperforms past visual face tracking algorithms especially in low resolution videos.

UR - http://www.scopus.com/inward/record.url?scp=33750827751&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750827751&partnerID=8YFLogxK

U2 - 10.1109/FGR.2006.19

DO - 10.1109/FGR.2006.19

M3 - Conference contribution

AN - SCOPUS:33750827751

SN - 0769525032

SN - 9780769525037

T3 - FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition

SP - 573

EP - 578

BT - FGR 2006

ER -