Presentation 2009-12-17
Pupils Tracking Robust to the Changes of Face Pose with considering the Positions of Eyeballs
Yusuke OHTANI, Kazuhiro FUKUI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we will propose a method of detecting and tracking pupils by using the particle filter with a 3D head model. We used the weighted sum of the shape similarity from elliptical separability filter and the pattern similarity from discriminant analysis as the likelihood of each particle. The 3D head model has nine parameters, the six parameters of which represent the 3D position and the direction of a head and the rest represent the displacement angles of pupils. The evaluation experiments show that the proposed method can realize a robust pupil tracking against blinks or complicated motions of pupils.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Pupil Trackinig / Particle Filter / Separability Filter
Paper # PRMU2009-136
Date of Issue

Conference Information
Committee PRMU
Conference Date 2009/12/10(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) Pupils Tracking Robust to the Changes of Face Pose with considering the Positions of Eyeballs
Sub Title (in English)
Keyword(1) Pupil Trackinig
Keyword(2) Particle Filter
Keyword(3) Separability Filter
1st Author's Name Yusuke OHTANI
1st Author's Affiliation Graduate School of System and Information Engineering, University of Tsukuba()
2nd Author's Name Kazuhiro FUKUI
2nd Author's Affiliation Graduate School of System and Information Engineering, University of Tsukuba
Date 2009-12-17
Paper # PRMU2009-136
Volume (vol) vol.109
Number (no) 344
Page pp.pp.-
#Pages 6
Date of Issue