Automating areas of interest analysis in mobile eye tracking experiments based on machine learning

  • Julian Wolf ETH Zurich
  • Stephan Hess ETH Zurich
  • David Bachmann ETH Zurich
  • Quentin Lohmeyer ETH Zurich
  • Mirko Meboldt ETH Zurich
Keywords: mobile eye tracking, areas of interest, gaze mapping, machine learning, mask R-CNN, object detection, tangible objects, cGOM, usability


For an in-depth, AOI-based analysis of mobile eye tracking data, a preceding gaze assignment step is inevitable. Current solutions such as manual gaze mapping or marker-based approaches are tedious and not suitable for applications manipulating tangible objects. This makes mobile eye tracking studies with several hours of recording difficult to analyse quantitatively. We introduce a new machine learning-based algorithm, the computational Gaze-Object Mapping (cGOM), that automatically maps gaze data onto respective AOIs. cGOM extends state-of-the-art object detection and segmentation by mask R-CNN with a gaze mapping feature. The new algorithm’s performance is validated against a manual fixation-by-fixation mapping, which is considered as ground truth, in terms of true positive rate (TPR), true negative rate (TNR) and efficiency. Using only 72 training images with 264 labelled object representations, cGOM is able to reach a TPR of approx. 80% and a TNR of 85% compared to the manual mapping. The break-even point is reached at 2 hours of eye tracking recording for the total procedure, respectively 1 hour considering human working time only. Together with a real-time capability of the mapping process after completed training, even hours of eye tracking recording can be evaluated efficiently.

(Code and video examples have been made available at:
How to Cite
Wolf, J., Hess, S., Bachmann, D., Lohmeyer, Q., & Meboldt, M. (2018). Automating areas of interest analysis in mobile eye tracking experiments based on machine learning. Journal of Eye Movement Research, 11(6).