Presentation 2022-03-11
Gaze Estimation for a Driving Simulator Using Machine Learning
Takayuki Furukawa, Yuji Matsuki,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Several studies have been conducted on gaze estimation in driving simulators due to the widespread attention it has attracted. However, peculiar issues with accuracy and measurable range still abound. Herein, we propose a new method that combines machine learning with the face images of the driver captured using three cameras. The proposed method used dataset collection, preprocessing, and machine learning using a neural network. Additionally, we evaluated the accuracy of the proposed method via an experiment. The measurable range was approximately 160° and the mean Euclidean error over the evaluation data, which was collected on a driving simulator, was approximately 3.83°.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Gaze estimation / Machine learning / Convolutional neural network / Driving simulator
Paper # ITS2021-70
Date of Issue 2022-03-04 (ITS)

Conference Information
Committee ITS / IEE-ITS
Conference Date 2022/3/11(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Information Processing for ITS, etc.
Chair Masahiro Fujii(Utsunomiya Univ.) / Hiroyuki Hosono(Nihon Univ.)
Vice Chair Kohei Ohno(Meiji Univ.) / Naohisa Hashimoto(AIST)
Secretary Kohei Ohno(Akita Prefectural Univ.) / Naohisa Hashimoto(NIT, Tsuruoka College) / (Nagoya Electric Works)
Assistant Msataka Imao(Mitsubishi Electric) / Kenshi Saho(Toyama Prefectural Univ.) / Keiji Jimi(Gunma Univ.) / Tou Lin(Nihon Univ.)

Paper Information
Registration To Technical Committee on Intelligent Transport Systems Technology / Technical Meeting on Intelligent Transport Systems
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Gaze Estimation for a Driving Simulator Using Machine Learning
Sub Title (in English)
Keyword(1) Gaze estimation
Keyword(2) Machine learning
Keyword(3) Convolutional neural network
Keyword(4) Driving simulator
1st Author's Name Takayuki Furukawa
1st Author's Affiliation Fukuoka Institute of Technology(FIT)
2nd Author's Name Yuji Matsuki
2nd Author's Affiliation Fukuoka Institute of Technology(FIT)
Date 2022-03-11
Paper # ITS2021-70
Volume (vol) vol.121
Number (no) ITS-436
Page pp.pp.38-43(ITS),
#Pages 6
Date of Issue 2022-03-04 (ITS)