A real-time stereo head pose tracking system

Jingying Chen; B. Tiddeman

doi:10.1109/ISSPIT.2005.1577105

A real-time stereo head pose tracking system

Jingying Chen, B. Tiddeman

School of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Head pose tracking is very important in many human machine interfaces. In this paper, a stereo head pose tracking system is proposed, which detects and tracks six facial features (pupils, nostrils and lip corners) automatically when a human face appears in front of two low-cost USB cameras. The epipolar constraint and a 3D facial feature model are used to improve the accuracy and robustness of the system. This system has the advantages of automatically detecting the facial features and recovering the features lost during the tracking process. Encouraging results have been obtained using the proposed system

Original language	Undefined/Unknown
Title of host publication	Proceedings of the Fifth IEEE International Symposium on Signal Processing and Information Technology, 2005.
Pages	258-263
Number of pages	6
DOIs	https://doi.org/10.1109/ISSPIT.2005.1577105
Publication status	Published - 1 Dec 2005

Keywords

computer vision
face recognition
object detection
stereo image processing
3D facial feature model
epipolar constraint
facial feature detection
human machine interfaces
real-time stereo head pose tracking system
Cameras
Computer science
Face detection
Facial features
Humans
Magnetic heads
Real time systems
Robustness
Skin
Universal Serial Bus

Access to Document

10.1109/ISSPIT.2005.1577105

PROTOTYPING TRANS FACIAL APPREARENCE DYN: Prototyping and transformaing facial appearance and dynamics using 3D performance models
Tiddeman, B. P. (PI)
EPSRC
6/01/05 → 5/04/08
Project: Standard

Cite this

@inproceedings{9d9ac546327e4003b4a4b6ea6acecb5e,

title = "A real-time stereo head pose tracking system",

abstract = "Head pose tracking is very important in many human machine interfaces. In this paper, a stereo head pose tracking system is proposed, which detects and tracks six facial features (pupils, nostrils and lip corners) automatically when a human face appears in front of two low-cost USB cameras. The epipolar constraint and a 3D facial feature model are used to improve the accuracy and robustness of the system. This system has the advantages of automatically detecting the facial features and recovering the features lost during the tracking process. Encouraging results have been obtained using the proposed system",

keywords = "computer vision, face recognition, object detection, stereo image processing, 3D facial feature model, epipolar constraint, facial feature detection, human machine interfaces, real-time stereo head pose tracking system, Cameras, Computer science, Face detection, Facial features, Humans, Magnetic heads, Real time systems, Robustness, Skin, Universal Serial Bus",

author = "Jingying Chen and B. Tiddeman",

year = "2005",

month = dec,

day = "1",

doi = "10.1109/ISSPIT.2005.1577105",

language = "Undefined/Unknown",

pages = "258--263",

booktitle = "Proceedings of the Fifth IEEE International Symposium on Signal Processing and Information Technology, 2005.",

}

TY - GEN

T1 - A real-time stereo head pose tracking system

AU - Chen, Jingying

AU - Tiddeman, B.

PY - 2005/12/1

Y1 - 2005/12/1

N2 - Head pose tracking is very important in many human machine interfaces. In this paper, a stereo head pose tracking system is proposed, which detects and tracks six facial features (pupils, nostrils and lip corners) automatically when a human face appears in front of two low-cost USB cameras. The epipolar constraint and a 3D facial feature model are used to improve the accuracy and robustness of the system. This system has the advantages of automatically detecting the facial features and recovering the features lost during the tracking process. Encouraging results have been obtained using the proposed system

AB - Head pose tracking is very important in many human machine interfaces. In this paper, a stereo head pose tracking system is proposed, which detects and tracks six facial features (pupils, nostrils and lip corners) automatically when a human face appears in front of two low-cost USB cameras. The epipolar constraint and a 3D facial feature model are used to improve the accuracy and robustness of the system. This system has the advantages of automatically detecting the facial features and recovering the features lost during the tracking process. Encouraging results have been obtained using the proposed system

KW - computer vision

KW - face recognition

KW - object detection

KW - stereo image processing

KW - 3D facial feature model

KW - epipolar constraint

KW - facial feature detection

KW - human machine interfaces

KW - real-time stereo head pose tracking system

KW - Cameras

KW - Computer science

KW - Face detection

KW - Facial features

KW - Humans

KW - Magnetic heads

KW - Real time systems

KW - Robustness

KW - Skin

KW - Universal Serial Bus

U2 - 10.1109/ISSPIT.2005.1577105

DO - 10.1109/ISSPIT.2005.1577105

M3 - Conference contribution

SP - 258

EP - 263

BT - Proceedings of the Fifth IEEE International Symposium on Signal Processing and Information Technology, 2005.

ER -

A real-time stereo head pose tracking system

Abstract

Keywords

Access to Document

Projects

PROTOTYPING TRANS FACIAL APPREARENCE DYN: Prototyping and transformaing facial appearance and dynamics using 3D performance models

Cite this