Individual predictions of eye-movements with dynamic scenes

Erhardt Barth , Jan Drewes, and Thomas Martinetz
Institute for Neuro- and Bioinformatics, University of Luebeck, Germany


We present a model that predicts saccadic eye-movements and can be tuned to a particular human observer who is viewing a dynamic sequence of images. Our work is motivated by applications that involve gaze-contingent interactive displays on which information is displayed as a function of gaze direction. The approach therefore differs from standard approaches in two ways: (i) we deal with dynamic scenes, and (ii) we provide means of adapting the model to a particular observer. As an indicator for the degree of saliency we evaluate the intrinsic dimension of the image sequence within a geometric approach implemented by using the structure tensor. Out of these candidate saliency-based locations, the currently attended location is selected according to a strategy found by supervised learning. The data are obtained with an eye-tracker and subjects who view video sequences. The selection algorithm receives candidate locations of current and past frames and a limited history of locations attended in the past. We use a linear mapping that is obtained by minimizing the quadratic difference between the predicted and the actually attended location by gradient descent. Being linear, the learned mapping can be quickly adapted to the individual observer.

Keywords: Eye-movements, saccades, saliency map, intrinsic dimension, machine learning, gaze-contingent display

Download paper in PDF format.

The videos and further results will be made available here soon.