Master's Defense: Zachary Kozak
Monday, April 20
3 PM
SHOR 211
Zoom: https://unl.zoom.us/j/98015427367
"A Webcam Eye Tracking Infrastructure for Software Engineering Tasks"
Performing eye tracking utilizing commodity webcams has been explored for over a decade, but limited camera quality and sensitivity to head movements have hindered its adoption in research settings. Recent work in this area, advances in consumer-grade webcams, and better machine learning methods present an opportunity to improve the accuracy of webcam eye tracking and extend the feasibility of studies beyond controlled laboratory environments.
Current methods restrict webcam eye tracking implementations to a browser and rely on continuous user interactions for predictions, which limits the kinds of studies that can be done. This thesis presents a feature-based (ML) gaze prediction system for the webcam, with additional focus on handling natural head movements and blinks. Furthermore, the webcam eye tracker is integrated into iTrace, an eye tracking infrastructure for software engineering tasks, to evaluate it against other eye tracking solutions and determine its feasibility for various types of software engineering studies.
Committee:
Dr. Bonita Sharif, Chair
Dr. Robert Dyer
Dr. Michael Dodd