Key Techniques of Eye Gaze Tracking Based on Pupil Corneal Reflection
Authors:
- Chi Jian-NanCJChi Jian-Nan
- Zhang Peng-YiZPZhang Peng-Yi
- Zheng Si-YiZSZheng Si-Yi
- Zhang ChuangZCZhang Chuang
- Huang YingHYHuang Ying
- 1 January 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2 (21556083) , 133-138
Abstract
Eye Gaze Tracking (EGT) is a kind of techniques that can estimate gaze direction of a person via various methods such as optics, electronics, mechanics etc. Pupil corneal reflection is one of those methods that using the vector from Purkinje image center location to pupil center location to estimate the gaze direction. A review on key techniques of EGT based on pupil corneal reflection is given in three aspects of eye feature detection, mapping model from gaze parameters to gaze direction and face pose estimation. The characteristics of two kind mapping models are analyzed and the detection method of gaze direction based on stereovision is discussed. According to a large number of recent references, we propose some major problems and their possible solutions in EGT techniques as well as its research orientation in future.Keywords
This publication has 18 references indexed in Scilit:
- Eye tracking: Pupil orientation geometrical modelingImage and Vision Computing, 2006
- Eye gaze tracking techniques for interactive applicationsComputer Vision and Image Understanding, 2005
- A non-contact device for tracking gaze in a human computer interfaceComputer Vision and Image Understanding, 2005
- A novel non-intrusive eye gaze estimation using cross-ratio under large head motionComputer Vision and Image Understanding, 2005
- Automated eye tracking system calibration using artificial neural networksComputer Methods and Programs in Biomedicine, 2004
- Model-based head pose tracking with stereovision2003
- Eye Tracking Methodology: Theory and Practice2003
- 3D head pose computation from 2D images: templates versus features2002
- Facial feature detection and face recognition from 2D and 3D imagesPattern Recognition Letters, 2002
- Real-time face pose estimationReal-Time Imaging, 1998