Landmark Detection for Mobile Eye Tracking

Mobile eye tracking studies in urban environments can provide important insights into several processes of human behavior, ranging from wayfinding to human-environment interaction. The analysis of this kind of eye tracking data are based on a semi-manual or even sometimes completely manual process, consuming immense post-processing time. In this thesis, we propose an approach based on computer vision methods that allows fully automatic analysis of eye tracking data, captured in an urban environment. We present our approach, as well as the results of three experiments that were conducted in order to evaluate the robustness of the system in open, as well as in narrow spaces. Furthermore, we give directions towards computation time optimization in order to achieve analysis on the fly of the captured eye tracking data, opening the way for human-environment interaction in real time