A real-time robust eye tracking system for autostereoscopic displays using stereo cameras

Chan Hung Su; Yong-Sheng Chen; Yi Ping Hung; Chu Song Chen; Jiun Hung Chen

doi:10.1109/ROBOT.2003.1241835

A real-time robust eye tracking system for autostereoscopic displays using stereo cameras

Chan Hung Su, Yong-Sheng Chen^*, Yi Ping Hung, Chu Song Chen, Jiun Hung Chen

^*Corresponding author for this work

Department of Computer Science

Research output: Contribution to journal › Conference article › peer-review

7 Scopus citations

Abstract

Autostereoscopic display systems can provide users a natural 3-D visualization environment by projecting stereo video onto the user's eyes. Eye position localization is a central module in this kind of display system when users are allowed to move freely. This paper presents robust 3-D eye tracking techniques that can provide accurate eye positions in real time. Technical batteries comprise: (1) robust face detection based on eigenspace method; (2) real-time face tracking; and (3) eye detection in the obtained face region. According to our implementation on a PC with a Pentium IV 1.2 GHz CPU, the frame rate of the eye tracking process can achieve 25 Hz.

Original language	English
Pages (from-to)	1677-1681
Number of pages	5
Journal	Proceedings - IEEE International Conference on Robotics and Automation
Volume	2
DOIs	https://doi.org/10.1109/ROBOT.2003.1241835
State	Published - 9 Dec 2003
Event	2003 IEEE International Conference on Robotics and Automation - Taipei, Taiwan Duration: 14 Sep 2003 → 19 Sep 2003

Access to Document

10.1109/ROBOT.2003.1241835

Cite this

@article{7cc24a75315448b8a0ce08ba654ff3fd,

title = "A real-time robust eye tracking system for autostereoscopic displays using stereo cameras",

abstract = "Autostereoscopic display systems can provide users a natural 3-D visualization environment by projecting stereo video onto the user's eyes. Eye position localization is a central module in this kind of display system when users are allowed to move freely. This paper presents robust 3-D eye tracking techniques that can provide accurate eye positions in real time. Technical batteries comprise: (1) robust face detection based on eigenspace method; (2) real-time face tracking; and (3) eye detection in the obtained face region. According to our implementation on a PC with a Pentium IV 1.2 GHz CPU, the frame rate of the eye tracking process can achieve 25 Hz.",

author = "Su, {Chan Hung} and Yong-Sheng Chen and Hung, {Yi Ping} and Chen, {Chu Song} and Chen, {Jiun Hung}",

year = "2003",

month = dec,

day = "9",

doi = "10.1109/ROBOT.2003.1241835",

language = "English",

volume = "2",

pages = "1677--1681",

journal = "Proceedings - IEEE International Conference on Robotics and Automation",

issn = "1050-4729",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "null ; Conference date: 14-09-2003 Through 19-09-2003",

}

TY - JOUR

T1 - A real-time robust eye tracking system for autostereoscopic displays using stereo cameras

AU - Su, Chan Hung

AU - Chen, Yong-Sheng

AU - Hung, Yi Ping

AU - Chen, Chu Song

AU - Chen, Jiun Hung

PY - 2003/12/9

Y1 - 2003/12/9

N2 - Autostereoscopic display systems can provide users a natural 3-D visualization environment by projecting stereo video onto the user's eyes. Eye position localization is a central module in this kind of display system when users are allowed to move freely. This paper presents robust 3-D eye tracking techniques that can provide accurate eye positions in real time. Technical batteries comprise: (1) robust face detection based on eigenspace method; (2) real-time face tracking; and (3) eye detection in the obtained face region. According to our implementation on a PC with a Pentium IV 1.2 GHz CPU, the frame rate of the eye tracking process can achieve 25 Hz.

AB - Autostereoscopic display systems can provide users a natural 3-D visualization environment by projecting stereo video onto the user's eyes. Eye position localization is a central module in this kind of display system when users are allowed to move freely. This paper presents robust 3-D eye tracking techniques that can provide accurate eye positions in real time. Technical batteries comprise: (1) robust face detection based on eigenspace method; (2) real-time face tracking; and (3) eye detection in the obtained face region. According to our implementation on a PC with a Pentium IV 1.2 GHz CPU, the frame rate of the eye tracking process can achieve 25 Hz.

UR - http://www.scopus.com/inward/record.url?scp=0344445536&partnerID=8YFLogxK

U2 - 10.1109/ROBOT.2003.1241835

DO - 10.1109/ROBOT.2003.1241835

M3 - Conference article

AN - SCOPUS:0344445536

VL - 2

SP - 1677

EP - 1681

JO - Proceedings - IEEE International Conference on Robotics and Automation

JF - Proceedings - IEEE International Conference on Robotics and Automation

SN - 1050-4729

Y2 - 14 September 2003 through 19 September 2003

ER -

A real-time robust eye tracking system for autostereoscopic displays using stereo cameras

Abstract

Access to Document

Other files and links

Fingerprint

Cite this