TY - JOUR
T1 - Driver’s eye-based gaze tracking system by one-point calibration
AU - Yoon, Hyo Sik
AU - Hong, Hyung Gil
AU - Lee, Dong Eun
AU - Park, Kang Ryoung
N1 - Publisher Copyright:
© 2018, Springer Science+Business Media, LLC, part of Springer Nature.
PY - 2019/3/1
Y1 - 2019/3/1
N2 - The accuracies of driver’s gaze detection by previous researches are affected by the various sitting positions and heights of drivers in case that initial calibration of driver is not performed. By using dual cameras, the driver’s calibration can be omitted, but processing time with complexity is increased. In addition, the problem of disappearing corneal specular reflection (SR) in the eye image as the driver severely turns his/her head has not been dealt in previous researches. To consider these issues, we propose a gaze tracking method based on driver’s one-point calibration using both corneal SR and medial canthus (MC) based on maximum entropy criterion. An experiment with collected data from 26 subjects (wearing nothing, glasses, sunglasses, hat, or taking various hand pose) in a vehicle, showed that the accuracy of the proposed method is higher than that of other gaze tracking methods. In addition, we showed the effectiveness of our method in the real driving environment.
AB - The accuracies of driver’s gaze detection by previous researches are affected by the various sitting positions and heights of drivers in case that initial calibration of driver is not performed. By using dual cameras, the driver’s calibration can be omitted, but processing time with complexity is increased. In addition, the problem of disappearing corneal specular reflection (SR) in the eye image as the driver severely turns his/her head has not been dealt in previous researches. To consider these issues, we propose a gaze tracking method based on driver’s one-point calibration using both corneal SR and medial canthus (MC) based on maximum entropy criterion. An experiment with collected data from 26 subjects (wearing nothing, glasses, sunglasses, hat, or taking various hand pose) in a vehicle, showed that the accuracy of the proposed method is higher than that of other gaze tracking methods. In addition, we showed the effectiveness of our method in the real driving environment.
KW - Driver’s gaze detection
KW - Initial calibration of driver
KW - Maximum entropy criterion
KW - NIR camera and NIR illuminator
KW - Pupil, corneal specular reflection and medial canthus
UR - http://www.scopus.com/inward/record.url?scp=85051692942&partnerID=8YFLogxK
U2 - 10.1007/s11042-018-6490-7
DO - 10.1007/s11042-018-6490-7
M3 - Article
AN - SCOPUS:85051692942
SN - 1380-7501
VL - 78
SP - 7155
EP - 7179
JO - Multimedia Tools and Applications
JF - Multimedia Tools and Applications
IS - 6
ER -