Driver Fatigue Detection based on Eye State Analysis

DOI

10.2991/jcis.2008.23How to use a DOI?

Keywords

driver fatigue detection, face segment, eye location, eye states analysis

Abstract

Driver fatigue is one of the important fac-tors in a large number of traffic accidents. Eye states (full open, half open or closed) analysis is an efficient measure to evalu-ate driver’s alertness. In this paper, we present an effective vision-based driver fatigue detection method. Firstly, the in-terframe difference approach binding color information is used to decide whether there exists a face. If exists, the face area is segmented from the image based on a mixed skin tone model. After that, we simulated the process of crystal-lization to obtain the location of eyes within the face area. Later, eye area, av-erage height of the pupil and width to height ratio were used to analyze the eye’s states. Finally, the driver fatigue is confirmed by analyzing the changes of eye’s states. The experimental results show validity of our proposed method for driver fatigue detection under realistic conditions.

Copyright

© 2008, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yong Du
AU  - Peijun Ma
AU  - Xiaohong Su
AU  - Yingjun Zhang
PY  - 2008/12
DA  - 2008/12
TI  - Driver Fatigue Detection based on Eye State Analysis
BT  - Proceedings of the 11th Joint Conference on Information Sciences (JCIS 2008)
PB  - Atlantis Press
SP  - 132
EP  - 137
SN  - 1951-6851
UR  - https://doi.org/10.2991/jcis.2008.23
DO  - 10.2991/jcis.2008.23
ID  - Du2008/12
ER  -