Eye tracker project
In this work an on-line method is proposed for statistical evaluation of dynamic web advertisements via measuring their visit frequencies. To minimize the required user-interaction, the eye movements are tracked by a special eye camera, and the hits on advertisements are automatically recognized. The detection step is mapped to a 2D template matching problem, and novel algorithms are developed to significantly decrease the processing time, via excluding quickly most of the false hit-candidates. We show that due to the improvements the method runs in real time in the context of the selected application. The solution has been validated on real test data and quantitative results have been provided to show the gain in recognition rate and processing time versus previous approaches.
The template matching method has been published at VISAPP 2008 Conference.
Collaborators in this project: Dániel Szolgay, Csaba Benedek, Viktor Gál, Tamás Szirányi, Zoltán Vidnyánszky (PPKE ITK), and the C3 Foundation Hungary.
1) "Video" window contains the periodically captured screen shots, with visualizing some processing steps:
Red dot in "Video" window is the current eye position measured by iView X eye camera
Identified template hits are marked by blue cast and red bounding rectangle in the input screen shot sequence.
2) In the "Eyetracker and hit alarm" windows one can find the enlarged neighborhood of the current eye position and the matched templates.
3) In the "Template browser", the user can check the template database (each dynamic advertisement is stored as a sequence of still images, i.e. "frames")
4) "Statistics" window summarizes the template hit history.
References
[1] D. Szolgay, Cs. Benedek and T. Szirányi: ”Fast template matching for measuring visit frequencies of dynamic web advertisements,” International Conference on Computer Vision Theory and Applications (VISAPP), pp. 228-233, Funchal, Madeira, Portugal, January 22-25, 2008,
