Driver’s eye-based gaze tracking system by one-point calibration

Hyo Sik Yoon, Hyung Gil Hong, Dong Eun Lee, Kang Ryoung Park

Research output: Contribution to journalArticlepeer-review

8 Scopus citations

Abstract

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.

Original languageEnglish
Pages (from-to)7155-7179
Number of pages25
JournalMultimedia Tools and Applications
Volume78
Issue number6
DOIs
StatePublished - 1 Mar 2019

Keywords

  • Driver’s gaze detection
  • Initial calibration of driver
  • Maximum entropy criterion
  • NIR camera and NIR illuminator
  • Pupil, corneal specular reflection and medial canthus

Fingerprint

Dive into the research topics of 'Driver’s eye-based gaze tracking system by one-point calibration'. Together they form a unique fingerprint.

Cite this