Paper published in the IEEE Conference on Advanced Video and Signal Based Surveillance (AVSS 2005)
Location: Como, Italy
Date: Sep. 2005
Publisher: IEEE Computer Society
DOI Bookmark: 10.1109/AVSS.2005.1577252
Dan Witzner Hansen, IT University of Copenhagen
Riad Hammoud, Delphi Electronics and Safety
In this paper we propose a log likelihood-ratio function of foreground and background models used in a particle filter to track the eye region in dark-bright pupil image sequences. This model fuses information from both dark and bright pupil images and their difference image into one model. The tracker overcomes the issues of prior selection of static thresholds during the detection of feature observations in the bright-dark difference images. The auto-initialization process is performed using cascaded classifier trained using adaboost and adapted to IR eye images. Experiments show good performance in challenging sequences with test subjects showing large head movements and under significant light changes.