Presentation 2012-03-29
Model-based Gaze Estimation Method with Low-Resolution RGB Images of Eyes
Takashi FUKUDA, Hayato YAMANA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recording eye-gaze data from many people in natural situations are valuable in Human Factors, Market Strategy and any other studies. The gaze tracking system equipped with webcams is suitable to record eye-gaze data. The resolutions of eye-images captured by webcams are low. Low-resolution eye-images tend to be distorted and cause errors in gaze estimations. We have developed the gaze tracking system with low-resoltion eye-images. In our past study, we extract contours of pupils, remove distorted areas in these contours, approximate pupil contours into an ellipse, and calculate gaze direction from the ellipse. However, there was a problem that the threshold to binalize eye-images in our past system is hand-operated. In this paper, we propose the gaze tracking method using low-resolution eye-images with automatic-operated threshold. In our experiment, we have attained the accuracy that the horizontal error is 7.0[deg] and the vertical error is 4.3[deg].
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Gaze estimation method / Webcam / Model-Based gaze estimation method
Paper # PRMU2011-245,HIP2011-73
Date of Issue

Conference Information
Committee PRMU
Conference Date 2012/3/22(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) Model-based Gaze Estimation Method with Low-Resolution RGB Images of Eyes
Sub Title (in English)
Keyword(1) Gaze estimation method
Keyword(2) Webcam
Keyword(3) Model-Based gaze estimation method
1st Author's Name Takashi FUKUDA
1st Author's Affiliation Graduate School of Fundamental Science and Engineering, Waseda University()
2nd Author's Name Hayato YAMANA
2nd Author's Affiliation Science and Engineering, Waseda University:National Institute of Infromatics
Date 2012-03-29
Paper # PRMU2011-245,HIP2011-73
Volume (vol) vol.111
Number (no) 499
Page pp.pp.-
#Pages 6
Date of Issue