Gaze map matching: mapping eye tracking data to geographic vector features

  • Authors:
  • Peter Kiefer;Ioannis Giannopoulos

  • Affiliations:
  • Institute of Cartography and Geoinformation, ETH Zurich, Zurich, Switzerland;Institute of Cartography and Geoinformation, ETH Zurich, Zurich, Switzerland

  • Venue:
  • Proceedings of the 20th International Conference on Advances in Geographic Information Systems
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper introduces gaze map matching as the problem of algorithmically interpreting eye tracking data with respect to geographic vector features, such as a road network shown on a map. This differs from previous eye tracking studies which have not taken into account the underlying vector data of the cartographic map. The paper explores the challenges of gaze map matching and relates it to the (vehicle) map matching problem. We propose a gaze map matching algorithm based on a Hidden Markov Model, and compare its performance with two purely geometric algorithms. Two eye tracking data sets recorded during the visual inspection of 14 road network maps of varying realism and complexity are used for this evaluation.