Eye-tracking technology for the analysis of dynamic data

In this paper, known eye-tracking algorithms, which in most cases require the use of infrared light, as well as the presence of some specialized physical device (eye-tracker) are considered. This greatly limits the range of tasks that can be solved with eye-tracking technology. The aim of the work is to increase the effectiveness of the appliance of eye-tracking technology through the development of an intelligent software module based on the proposed by authors “grid” method for tracking the eye pupil in the analysis of dynamic data. Efficiency and expediency of the proposed intelligent software module is proved when solving the task of analyzing streaming video with a high frame rate, in particular an advertising video clip. In addition, this approach will increase safety for dependable computing, in particular, for solving the problem of rapid (critical) reaction of a car in case of consciousness loss and/or falling asleep during driving.