Related Experiment Video
Updated: Mar 14, 2026
07:24
Using Eye-tracking to Assess the Relative Importance of Visual and Vestibular Input to Subcortical Motion Processing in the Roll Plane
Published on: August 22, 2025
607
Head movement compensation and multi-modal event detection in eye-tracking data for unconstrained head movements
Linnéa Larsson1, Andrea Schwaller1, Marcus Nyström2
1Department of Biomedical Engineering, Lund University, Lund, Box 118, 221 00 Lund, Sweden.
Journal of Neuroscience Methods
|October 4, 2016
Summary
This study introduces a new method for analyzing mobile eye-tracking data by compensating for head movements and using object detection. This approach improves the accuracy of detecting eye-tracking events, even with significant head motion.
Area of Science:
- Human-Computer Interaction
- Biomedical Engineering
- Computer Vision
Background:
- Mobile eye-tracking data analysis is complex due to head and body movements influencing signals.
- Head and body motion artifacts in mobile eye-tracking complicate event detection.
Purpose of the Study:
- To develop a robust method for event detection in mobile eye-tracking signals.
- To improve the accuracy of classifying eye movements during natural head motion.
Main Methods:
- Compensation of head movements using inertial measurement unit (IMU) data.
- Multi-modal event detection algorithm integrating head-compensated eye-tracking data and scene camera object information.
Main Results:
- Head movement compensation reduced fixation signal standard deviation from 8° to 3.3°.
- The proposed algorithm achieved a balanced accuracy of 0.90, outperforming existing methods (0.85 and 0.75).
Conclusions:
- Combining head movement compensation and object detection enhances mobile eye-tracking event classification.
- The developed method offers improved accuracy for analyzing eye movements in mobile eye-tracking applications.
