Gaze direction estimation with a single camera based on four reference points and three calibration images

Authors:
Shinjiro Kawato;Akira Utsumi;Shinji Abe
Affiliations:
ATR Intelligent Robotics and Communication Laboratories, Keihanna Science City, Kyoto, Japan;ATR Intelligent Robotics and Communication Laboratories, Keihanna Science City, Kyoto, Japan;ATR Intelligent Robotics and Communication Laboratories, Keihanna Science City, Kyoto, Japan
Venue:
ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part I
Year:
2006

Citing 8
Cited 1

Just blink your eyes: a head-free gaze tracking system

CHI '03 Extended Abstracts on Human Factors in Computing Systems
An Algorithm for Real-Time Stereo Vision Implementation of Head Pose and Gaze Direction Measurement

FG '00 Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition 2000
Non-Intrusive Gaze Tracking Using Artificial Neural Networks

Non-Intrusive Gaze Tracking Using Artificial Neural Networks
Subpixel Eye Gaze Tracking

FGR '02 Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition
Eye gaze tracking techniques for interactive applications

Computer Vision and Image Understanding - Special issue on eye detection and tracking
Estimating the eye gaze from one eye

Computer Vision and Image Understanding - Special issue on eye detection and tracking
A novel non-intrusive eye gaze estimation using cross-ratio under large head motion

Computer Vision and Image Understanding - Special issue on eye detection and tracking
Conic-based algorithm for visual line estimation from one image

FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition

Eye-gaze detection from monocular camera image using parametric template matching

ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a method to estimate gaze direction in real time with a single camera based on four reference points and three calibration images. First, the position at which the eyeball center is projected is calculated as a linear combination of those of the reference points. Then, the gaze direction is estimated as a vector connecting the calculated eyeball center and the detected iris center. The algorithm is head pose free. We implemented the algorithm on a PC with a Xeon 2.2-GHz CPU, which works at a rate of 30 fps.