In the Eye of the Beholder: A Survey of Models for Eyes and Gaze

doi:10.1109/TPAMI.2009.30

Paper

In the Eye of the Beholder: A Survey of Models for Eyes and Gaze

Published Mar 1, 2010 · D. Hansen, Q. Ji

IEEE Transactions on Pattern Analysis and Machine Intelligence

Q1 SJR score

1,452

Citations

105

Influential Citations

Full text Semantic Scholar

Abstract

Despite active research and significant progress in the last 30 years, eye detection and tracking remains challenging due to the individuality of eyes, occlusion, variability in scale, location, and light conditions. Data on eye location and details of eye movements have numerous applications and are essential in face detection, biometric identification, and particular human-computer interaction tasks. This paper reviews current progress and state of the art in video-based eye detection and tracking in order to identify promising techniques as well as issues to be further addressed. We present a detailed review of recent eye models and techniques for eye detection and tracking. We also survey methods for gaze estimation and compare them based on their geometric properties and reported accuracies. This review shows that, despite their apparent simplicity, the development of a general eye detection technique involves addressing many challenges, requires further theoretical developments, and is consequently of interest to many other domains problems in computer vision and beyond.

Highly Cited

Study Snapshot

Key takeawayEye detection and tracking remain challenging due to individuality, occlusion, and light conditions, but progress has been made and is crucial for face detection, biometric identification, and human-computer interaction tasks.

PopulationOlder adults (50-71 years)

Sample size24

MethodsObservational

OutcomesBody Mass Index projections

ResultsSocial networks mitigate obesity in older groups.

Sign up to use Study Snapshot

Consensus is limited without an account. Create an account or sign in to get more searches and use the Study Snapshot.

Create an account

Paper

In the Eye of the Beholder: A Survey of Models for Eyes and Gaze

Sign up to use Study Snapshot

References

Accurate eye center location and tracking using isophote curvature

Our method accurately locates and tracks eyes using a webcam, improving accuracy over state-of-the-art techniques while maintaining low computational costs.

3D point-of-gaze estimation on a volumetric display

This system, using eye vergence, can accurately estimate the point-of-gaze on a volumetric display, improving the accuracy of eye-gaze tracking devices.

Remote gaze estimation with a single camera based on facial-feature tracking without special calibration actions

Our gaze estimation method, using facial-feature tracking, accurately estimates gaze directions in daily-life situations without special user actions.

Noise tolerant selection by gaze-controlled pan and zoom in 3D

StarGazer is an intuitive 3D interface for gaze navigation, allowing more selectable objects on the screen than the accuracy of gaze trackers would otherwise permit.

Investigation of the Cross-Ratios Method for Point-of-Gaze Estimation

The cross-ratios method for point-of-gaze estimation has subject-dependent bias due to angular deviation of visual axis from optic axis and pupil center not coplanar with light source virtual images.

Citations

Appearance-Based Gaze Estimation as a Benchmark for Eye Image Data Generation Methods

Our hybrid method combining 3D rendering and neural style transfer improves appearance-based gaze estimation accuracy for 39 out of 40 subjects.

Cross-Dataset Gaze Estimation by Evidential Inter-intra Fusion

Our EIF framework effectively combines diverse gaze datasets, improving gaze estimation in both seen and unseen domains.

Can Stylized Products Generated by AI Better Attract User Attention? Using Eye-Tracking Technology for Research

AI-generated stylized products, particularly those created for females, have a longer fixation duration compared to those generated for males.

Accurate Gaze Estimation: An Innovative Eye Movement Prediction Architecture

This paper presents an innovative eye movement prediction architecture that addresses challenges in accuracy, personalization, and real-time processing while minimizing resource usage and increasing accessibility, transforming human interaction with technology and understanding human cognition.

Multi-Eyes: A Framework for Multi-User Eye-Tracking using Webcameras

Multi-Eyes is a webcam-based solution that enables scalable, cost-efficient multi-user eye tracking, achieving the lowest gaze error of 4.33 and demonstrating feasibility for multi-user interactions and joint attention.