Abstract
The concept and functionalities of a software tool developed for in depth performance evaluation of eye gaze estimation systems is presented. The software, GazeVisual has capabilities for quantitative, statistical, and visual analysis of eye gaze data as well as generation of static and dynamic visual stimuli for sample gaze data collection. This is a first of its kind cross-platform tool for gaze data analysis and evaluation. This software is made freely available to the eye gaze research and development community to provide a common framework for estimating the quality and reliability of data from eye tracking systems, especially those implemented in consumer electronics (CE) applications. The feasibility of using this software is tested through case studies which show that the software can handle eye gaze datasets obtained from several different consumer grade eye trackers. GazeVisual operates consistently, irrespective of the platform, algorithm or hardware of the eye trackers. In addition, the GazeVisual software capabilities are also made accessible via a Web-based application enabling performance evaluation of eye tracker data over a cloud-based platform.
| Original language | English |
|---|---|
| Article number | 8695131 |
| Pages (from-to) | 293-302 |
| Number of pages | 10 |
| Journal | IEEE Transactions on Consumer Electronics |
| Volume | 65 |
| Issue number | 3 |
| DOIs | |
| Publication status | Published - Aug 2019 |
Keywords
- Eye tracking
- Web-application
- data quality
- eye gaze
- performance evaluation
- visualizations