Gaze Detection by Estimating the Depths and 3D Motion of Facial Features in Monocular Images

Kang Ryoung PARK; Si Wook NAM; Min Suk LEE; Jaihie KIM

Gaze Detection by Estimating the Depths and 3D Motion of Facial Features in Monocular Images

Kang Ryoung PARK, Si Wook NAM, Min Suk LEE, Jaihie KIM

Full Text Views

0

Cite this

Summary :

This paper describes a new method for detecting the gaze position of a user on a monitor from monocular images. In order to detect the gaze position, we extract facial features (both eyes, nostrils and lip corners) automatically in 2D camera images and estimate the 3D depth information and the initial 3D positions of those features by recursive estimation algorithm in starting images. Then, when a user moves his/her head in order to gaze at one position on a monitor, the moved 3D positions of those features can be estimated from 3D motion estimation by Extended Kalman Filter (EKF) and affine transform. Finally, the gaze position on a monitor is calculated from the normal vector of the plane determined by those moved 3D positions of features. Especially, in order to obtain the exact 3D depth and positions of initial feature points, we unify three coordinate systems (face, monitor and camera coordinate system) based on perspective transformation. As experimental results, the 3D depth and the position estimation error of initial feature points, which is the RMS error between the estimated initial 3D feature positions and the real positions (measured by 3D position tracker sensor) is about 1.28 cm (0.75 cm in X axis, 0.85 cm in Y axis, 0.6 cm in Z axis) and the 3D motion estimation errors of feature points by Extended Kalman Filter (EKF) are about 3.6 degrees and 1.4 cm in rotation and translation, respectively. From that, we can obtain the gaze position on a monitor (17 inches) and the gaze position accuracy between the calculated positions and the real ones is about 2.1 inches of RMS error.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E82-A No.10 pp.2274-2284

Publication Date: 1999/10/25

Publicized

Online ISSN

DOI

Type of Manuscript: PAPER

Category: Human Communications and Ergonomics

Cite this

Copy

Kang Ryoung PARK, Si Wook NAM, Min Suk LEE, Jaihie KIM, "Gaze Detection by Estimating the Depths and 3D Motion of Facial Features in Monocular Images" in IEICE TRANSACTIONS on Fundamentals, vol. E82-A, no. 10, pp. 2274-2284, October 1999, doi: .
Abstract: This paper describes a new method for detecting the gaze position of a user on a monitor from monocular images. In order to detect the gaze position, we extract facial features (both eyes, nostrils and lip corners) automatically in 2D camera images and estimate the 3D depth information and the initial 3D positions of those features by recursive estimation algorithm in starting images. Then, when a user moves his/her head in order to gaze at one position on a monitor, the moved 3D positions of those features can be estimated from 3D motion estimation by Extended Kalman Filter (EKF) and affine transform. Finally, the gaze position on a monitor is calculated from the normal vector of the plane determined by those moved 3D positions of features. Especially, in order to obtain the exact 3D depth and positions of initial feature points, we unify three coordinate systems (face, monitor and camera coordinate system) based on perspective transformation. As experimental results, the 3D depth and the position estimation error of initial feature points, which is the RMS error between the estimated initial 3D feature positions and the real positions (measured by 3D position tracker sensor) is about 1.28 cm (0.75 cm in X axis, 0.85 cm in Y axis, 0.6 cm in Z axis) and the 3D motion estimation errors of feature points by Extended Kalman Filter (EKF) are about 3.6 degrees and 1.4 cm in rotation and translation, respectively. From that, we can obtain the gaze position on a monitor (17 inches) and the gaze position accuracy between the calculated positions and the real ones is about 2.1 inches of RMS error.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e82-a_10_2274/_p

Copy

@ARTICLE{e82-a_10_2274,
author={Kang Ryoung PARK, Si Wook NAM, Min Suk LEE, Jaihie KIM, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Gaze Detection by Estimating the Depths and 3D Motion of Facial Features in Monocular Images},
year={1999},
volume={E82-A},
number={10},
pages={2274-2284},
abstract={This paper describes a new method for detecting the gaze position of a user on a monitor from monocular images. In order to detect the gaze position, we extract facial features (both eyes, nostrils and lip corners) automatically in 2D camera images and estimate the 3D depth information and the initial 3D positions of those features by recursive estimation algorithm in starting images. Then, when a user moves his/her head in order to gaze at one position on a monitor, the moved 3D positions of those features can be estimated from 3D motion estimation by Extended Kalman Filter (EKF) and affine transform. Finally, the gaze position on a monitor is calculated from the normal vector of the plane determined by those moved 3D positions of features. Especially, in order to obtain the exact 3D depth and positions of initial feature points, we unify three coordinate systems (face, monitor and camera coordinate system) based on perspective transformation. As experimental results, the 3D depth and the position estimation error of initial feature points, which is the RMS error between the estimated initial 3D feature positions and the real positions (measured by 3D position tracker sensor) is about 1.28 cm (0.75 cm in X axis, 0.85 cm in Y axis, 0.6 cm in Z axis) and the 3D motion estimation errors of feature points by Extended Kalman Filter (EKF) are about 3.6 degrees and 1.4 cm in rotation and translation, respectively. From that, we can obtain the gaze position on a monitor (17 inches) and the gaze position accuracy between the calculated positions and the real ones is about 2.1 inches of RMS error.},
keywords={},
doi={},
ISSN={},
month={October},}

Copy

TY - JOUR
TI - Gaze Detection by Estimating the Depths and 3D Motion of Facial Features in Monocular Images
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2274
EP - 2284
AU - Kang Ryoung PARK
AU - Si Wook NAM
AU - Min Suk LEE
AU - Jaihie KIM
PY - 1999
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E82-A
IS - 10
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - October 1999
AB - This paper describes a new method for detecting the gaze position of a user on a monitor from monocular images. In order to detect the gaze position, we extract facial features (both eyes, nostrils and lip corners) automatically in 2D camera images and estimate the 3D depth information and the initial 3D positions of those features by recursive estimation algorithm in starting images. Then, when a user moves his/her head in order to gaze at one position on a monitor, the moved 3D positions of those features can be estimated from 3D motion estimation by Extended Kalman Filter (EKF) and affine transform. Finally, the gaze position on a monitor is calculated from the normal vector of the plane determined by those moved 3D positions of features. Especially, in order to obtain the exact 3D depth and positions of initial feature points, we unify three coordinate systems (face, monitor and camera coordinate system) based on perspective transformation. As experimental results, the 3D depth and the position estimation error of initial feature points, which is the RMS error between the estimated initial 3D feature positions and the real positions (measured by 3D position tracker sensor) is about 1.28 cm (0.75 cm in X axis, 0.85 cm in Y axis, 0.6 cm in Z axis) and the 3D motion estimation errors of feature points by Extended Kalman Filter (EKF) are about 3.6 degrees and 1.4 cm in rotation and translation, respectively. From that, we can obtain the gaze position on a monitor (17 inches) and the gaze position accuracy between the calculated positions and the real ones is about 2.1 inches of RMS error.
ER -