Related Experiment Video
Updated: May 16, 2026
07:09
Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior
Published on: November 14, 2018
A free geometry model-independent neural eye-gaze tracking system
Massimo Gneo1, Maurizio Schmid, Silvia Conforto
1Engineering Department, Roma Tre University, Via della Vasca Navale, 84, Rome I-00146, Italy. massimo.gneo@tiscali.it
Journal of Neuroengineering and Rehabilitation
|November 20, 2012
Summary
This study introduces a new eye gaze tracking system (EGTS) using the pupil center corneal reflection (PCCR) method. The model-independent system achieves high accuracy for assistive technology and diagnostics.
Area of Science:
- Biomedical Engineering
- Human-Computer Interaction
- Computer Vision
Background:
- Eye Gaze Tracking Systems (EGTSs) estimate the Point Of Gaze (POG) for diagnostics and human-computer interfaces (HCI).
- The pupil center corneal reflection (PCCR) method uses the vector between the pupil and corneal reflection (glint) to determine POG.
- Existing systems often rely on specific physiological models or rigid setups.
Purpose of the Study:
- To propose a novel, model-independent EGTS based on the PCCR method.
- To develop an EGTS that avoids assumptions about eye physiology and allows flexible system/user positioning.
- To demonstrate the robustness and accuracy of the proposed EGTS.
Main Methods:
- Developed a model-independent EGTS utilizing the PCCR method.
- Employed artificial neural networks for the mapping function, eliminating the need for specific eye models.
- Validated the system's accuracy with diverse users, varied geometric configurations, and different testing protocols.
Main Results:
- Achieved high accuracy in POG estimation.
- Reported horizontal error of approximately 0.49°, vertical error of 0.41°, and radial error of 0.62°.
- Demonstrated superior performance compared to existing HCI-focused EGTSs.
Conclusions:
- The proposed model-independent EGTS based on PCCR is effective and accurate.
- The system outperforms existing EGTSs designed for HCI applications.
- This approach offers a robust and flexible solution for eye gaze tracking.
