3D Gaze estimation based on facial feature tracking

Yi Man, Xinbo Zhao, Ke Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

A 3D gaze estimation and tracking algorithm based on facial feature tracking is presented in this paper. Firstly, we used the Active Shape Model (ASM) to extract facial feature points with a stereo camera. Then, the full 3D pose of head is estimated by comparing the feature points of current pose with initial head pose. After that, the center of eyeball is obtained based on a 3D eye model which is related to head pose and the middle point of eye corners. Thereby, optical axis was computed as 3D vectors through the center of eyeball to the center of pupil. Finally, visual axis was gotten by adding an angle to optical axis. Here, in our system, a one-time personal calibration is used to determine this angle. The experimental results show the accuracy of our gaze tracking system achieves less than 3 degree.

Original languageEnglish
Title of host publicationInternational Conference on Graphic and Image Processing, ICGIP 2012
DOIs
StatePublished - 2013
Event4th International Conference on Graphic and Image Processing, ICGIP 2012 - Singapore, Singapore
Duration: 6 Oct 20127 Oct 2012

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume8768
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference4th International Conference on Graphic and Image Processing, ICGIP 2012
Country/TerritorySingapore
CitySingapore
Period6/10/127/10/12

Keywords

  • Facial feature tracking
  • Gaze estimation
  • Gaze tracking
  • Head pose
  • Stereo cameras

Fingerprint

Dive into the research topics of '3D Gaze estimation based on facial feature tracking'. Together they form a unique fingerprint.

Cite this