Feature matching and ArUco markers application in mobile eye tracking studies

Abstract

This paper presents eye tracking glasses data analysis automation techniques, utilizing image processing. Two separate techniques will be described. One method is used to automate mapping of point-of-regard to a static reference image using a feature matching algorithm AKAZE. The second method utilizes ArUco markers for mapping of point-of-regard to a screencast from a mobile device. The described methods are used to aggregate experiment statistical data for future analysis and presentation in forms like heatmaps or gaze plots. Algorithms are implemented in Python 3.6 and OpenCV library.