"Until now, if you were to hang an advertising poster in the pedestrian zone, and wanted to know how many people actually looked at it, you would not have had a chance," said Andreas Bulling, head of the Perceptual User Interfaces group at Saarland University and the Max Planck Institute for Informatics.
At the moment, this information is captured with special eye tracking equipment which needed minutes-long calibration, and everyone has to wear such a tracker. Real-world studies, such as in a pedestrian zone, or even just with multiple people, are very complicated and in the worst case, impossible.
Together with his PhD student Xucong Zhang, and his former PostDoc Yusuke Sugano, now a Professor at Osaka University, Bulling has developed a new generation of algorithms for estimating gaze direction.
These use a neural network where a clustering of the estimated gaze directions is carried out. In a second step, the most likely clusters are identified, and the gaze direction estimates are used for the training of a target-object-specific eye contact detector. This means the tracking can be carried out with no involvement from the user, and the method can also improve further, the longer the camera remains next to the target object and records data. "In this way, our method turns normal cameras into eye contact detectors, without the size or position of the target object having to be known or specified in advance," said Bulling.