Object recognition and person detection for mobile eye-tracking research: A case study with real-life customer journeys

In this paper, we present a novel method for the automatic analysis of mobile eye-tracking data in natural environments. Mobile eye-trackers generate large amounts of data, making manual analysis very time consuming. Available solutions such as marker-based analysis minimize the manual labour but require experimental control, making real-life experiments practically unfeasible. We present a novel method for processing data of mobile eye-trackers by applying object detection and recognition algorithms. This enables the analysis to be performed on the object level rather than the traditionally used coordinate level. We apply algorithms to detect specific objects, human bodies and faces. We propose our novel detection scheme and present profound evaluation results of our system concerning accuracy on a challenging real-life customer journey experiment.