Presentation 2013-03-14
A Study on Gaze Estimation from Person Images Using Head Pose Information
Nobuhiro FUNATSU, Tomokazu TAKAHASHI, Daisuke DEGUCHI, Ichiro IDE, Hiroshi MURASE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Gaze estimation techniques using a camera have widely been studied in recent years. Most existing methods require a high-quality image of the eye area. However, an eye image obtained under real environments is often in low resolution, affected by illumination changes, and occluded by sunglasses or head rotation. Thus, we propose a method that estimates a gaze direction accurately using pose information including the head direction, the body direction, and the head motion. The proposed method estimates the pose information from an input person image sequence. Then, it calculates a likelihood function of gaze directions using the estimated pose information. Finally, it outputs the gaze direction that maximizes the likelihood value as a gaze estimation result. Experimental results showed that the proposed method could estimate gaze directions more accurately than an existing method. This indicates the effectiveness of the proposed method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) gaze estimation / face direction estimation
Paper # PRMU2012-197
Date of Issue

Conference Information
Committee PRMU
Conference Date 2013/3/7(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Study on Gaze Estimation from Person Images Using Head Pose Information
Sub Title (in English)
Keyword(1) gaze estimation
Keyword(2) face direction estimation
1st Author's Name Nobuhiro FUNATSU
1st Author's Affiliation Graduate School of Information Science, Nagoya University()
2nd Author's Name Tomokazu TAKAHASHI
2nd Author's Affiliation Faculty of Economics and Information, Gifu Shotoku Gakuen University
3rd Author's Name Daisuke DEGUCHI
3rd Author's Affiliation Information and Communications Headquarters, Nagoya University
4th Author's Name Ichiro IDE
4th Author's Affiliation Graduate School of Information Science, Nagoya University
5th Author's Name Hiroshi MURASE
5th Author's Affiliation Graduate School of Information Science, Nagoya University
Date 2013-03-14
Paper # PRMU2012-197
Volume (vol) vol.112
Number (no) 495
Page pp.pp.-
#Pages 6
Date of Issue