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. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1145/2424321.2424367 | SIGSPATIAL/GIS |
Keywords | Field | DocType |
road network,previous eye,geographic vector feature,cartographic map,map matching,varying realism,underlying vector data,geometric algorithm,road network map,hidden markov model,mapping eye,eye tracking | Computer vision,Data set,Visual inspection,Gaze,Computer science,Eye tracking,Artificial intelligence,Hidden Markov model,Machine learning,Map matching | Conference |
Citations | PageRank | References |
6 | 0.57 | 18 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Peter Kiefer | 1 | 223 | 24.99 |
Ioannis Giannopoulos | 2 | 115 | 14.55 |