Presentation 2012-03-16
A Method for Estimation of Three-Dimensional Eye Rotations with the Feature Points on the Eyeball
Takashi KIHARA, Shinichi HIKITA, Yasuhide KOBAYASHI, Takahiko ONO, Mitsuyuki SAITO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a new method for estimation of three-dimensional eye rotations using feature points on the eyeball such as edges of the iris or blood vessels. The relationship between the feature points and the gaze vector are obtained by three-points calibration. We evaluated the accuracy of the gaze position with the glass sphere as an eye model. As a result, the mean error of the horizontal angle was 0.34deg in the range of ±30deg and that of vertical angle was 0.29deg in the range of ±15deg, while the mean error of the torsional angle was 0.08deg in the range of ±10deg.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) torsion / gaze estimation / calibration / video camera
Paper # MBE2011-144
Date of Issue

Conference Information
Committee MBE
Conference Date 2012/3/7(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 ME and Bio Cybernetics (MBE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Method for Estimation of Three-Dimensional Eye Rotations with the Feature Points on the Eyeball
Sub Title (in English)
Keyword(1) torsion
Keyword(2) gaze estimation
Keyword(3) calibration
Keyword(4) video camera
1st Author's Name Takashi KIHARA
1st Author's Affiliation Graduate School of Information Sciences, Hiroshima City University()
2nd Author's Name Shinichi HIKITA
2nd Author's Affiliation Graduate School of Information Sciences, Hiroshima City University
3rd Author's Name Yasuhide KOBAYASHI
3rd Author's Affiliation Graduate School of Information Sciences, Hiroshima City University
4th Author's Name Takahiko ONO
4th Author's Affiliation Graduate School of Information Sciences, Hiroshima City University
5th Author's Name Mitsuyuki SAITO
5th Author's Affiliation Graduate School of Information Sciences, Hiroshima City University
Date 2012-03-16
Paper # MBE2011-144
Volume (vol) vol.111
Number (no) 482
Page pp.pp.-
#Pages 4
Date of Issue