Head pose and gaze direction tracking for detecting a drowsy driver

Author

In-Ho Choi ; Yong-Guk Kim

Author_Institution

Dept. of Comput. Eng., Sejong Univ., Seoul, South Korea

fYear

2014

fDate

15-17 Jan. 2014

Firstpage

241

Lastpage

244

Abstract

This paper proposes a system that uses gaze direction tracking and head pose estimation to detect drowsiness of a driver. Head pose is estimated by calculating optic flow of the facial features, which are acquired with a corner detection algorithm. Analysis of the driver´s head behavior leads to three moving components: nodding, shaking, and tilting. To track the gaze direction of the driver, we trace the center point of the pupil using CDF analysis and estimate the frequency of eye-movement.

Keywords

driver information systems; feature extraction; gaze tracking; human factors; image sequences; object tracking; pose estimation; CDF analysis; corner detection algorithm; driver head behavior analysis; drowsiness detection; drowsy driver detection; eye-movement frequency estimation; facial features; gaze direction tracking; head pose estimation; head pose tracking; nodding component; optic flow; shaking component; tilting component; Accuracy; Estimation; Feature extraction; Head; Three-dimensional displays; Vectors; Vehicles; Driver Drowsiness Detection; Eye Blinking; Gaze Direction; Head Pose Estimation;

fLanguage

English

Publisher

ieee

Conference_Titel

Big Data and Smart Computing (BIGCOMP), 2014 International Conference on

Conference_Location

Bangkok

Type

conf

DOI

10.1109/BIGCOMP.2014.6741444

Filename

6741444