Gaze position detection by computing the three dimensional facial positions and motions

Kang Ryoung Park, Jeong Jun Lee, Jaihie Kim

Research output: Contribution to journalArticle

21 Citations (Scopus)

Abstract

Gaze detection is to locate the position on a monitor screen where a user is looking. In our work, we implemented it by a computer vision system with a single camera above the monitor. We computed the initial three dimensional positions of facial features (both eyes, nostrils and lip comers) by a camera calibration and a parameter estimation algorithm, and also computed the moved 3D positions of those features by 3D rotation and translation estimations and affine transform. Finally, the gaze position on the monitor is computed from the normal vector of the plane determined by those moved 3D positions of features. Gaze detection error was 5.11 cm (RMS error) when the distance between the user and the monitor is 50-70 cm and a 19 in monitor is used.

Original languageEnglish
Pages (from-to)2559-2569
Number of pages11
JournalPattern Recognition
Volume35
Issue number11
DOIs
Publication statusPublished - 2002 Nov 1

Fingerprint

Cameras
Affine transforms
Error detection
Parameter estimation
Computer vision
Calibration

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Park, Kang Ryoung ; Lee, Jeong Jun ; Kim, Jaihie. / Gaze position detection by computing the three dimensional facial positions and motions. In: Pattern Recognition. 2002 ; Vol. 35, No. 11. pp. 2559-2569.
@article{a3b5e0b32ca04793bf103de6b78de8d2,
title = "Gaze position detection by computing the three dimensional facial positions and motions",
abstract = "Gaze detection is to locate the position on a monitor screen where a user is looking. In our work, we implemented it by a computer vision system with a single camera above the monitor. We computed the initial three dimensional positions of facial features (both eyes, nostrils and lip comers) by a camera calibration and a parameter estimation algorithm, and also computed the moved 3D positions of those features by 3D rotation and translation estimations and affine transform. Finally, the gaze position on the monitor is computed from the normal vector of the plane determined by those moved 3D positions of features. Gaze detection error was 5.11 cm (RMS error) when the distance between the user and the monitor is 50-70 cm and a 19 in monitor is used.",
author = "Park, {Kang Ryoung} and Lee, {Jeong Jun} and Jaihie Kim",
year = "2002",
month = "11",
day = "1",
doi = "10.1016/S0031-3203(01)00206-0",
language = "English",
volume = "35",
pages = "2559--2569",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "11",

}

Gaze position detection by computing the three dimensional facial positions and motions. / Park, Kang Ryoung; Lee, Jeong Jun; Kim, Jaihie.

In: Pattern Recognition, Vol. 35, No. 11, 01.11.2002, p. 2559-2569.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Gaze position detection by computing the three dimensional facial positions and motions

AU - Park, Kang Ryoung

AU - Lee, Jeong Jun

AU - Kim, Jaihie

PY - 2002/11/1

Y1 - 2002/11/1

N2 - Gaze detection is to locate the position on a monitor screen where a user is looking. In our work, we implemented it by a computer vision system with a single camera above the monitor. We computed the initial three dimensional positions of facial features (both eyes, nostrils and lip comers) by a camera calibration and a parameter estimation algorithm, and also computed the moved 3D positions of those features by 3D rotation and translation estimations and affine transform. Finally, the gaze position on the monitor is computed from the normal vector of the plane determined by those moved 3D positions of features. Gaze detection error was 5.11 cm (RMS error) when the distance between the user and the monitor is 50-70 cm and a 19 in monitor is used.

AB - Gaze detection is to locate the position on a monitor screen where a user is looking. In our work, we implemented it by a computer vision system with a single camera above the monitor. We computed the initial three dimensional positions of facial features (both eyes, nostrils and lip comers) by a camera calibration and a parameter estimation algorithm, and also computed the moved 3D positions of those features by 3D rotation and translation estimations and affine transform. Finally, the gaze position on the monitor is computed from the normal vector of the plane determined by those moved 3D positions of features. Gaze detection error was 5.11 cm (RMS error) when the distance between the user and the monitor is 50-70 cm and a 19 in monitor is used.

UR - http://www.scopus.com/inward/record.url?scp=0036833262&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036833262&partnerID=8YFLogxK

U2 - 10.1016/S0031-3203(01)00206-0

DO - 10.1016/S0031-3203(01)00206-0

M3 - Article

VL - 35

SP - 2559

EP - 2569

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 11

ER -