Dynamical optical flow of saliency maps for predicting visual attention
This work addresses the lack of general agreement on saliency maps for dynamic scenes, providing a solution for researchers in computer vision and psychology studying human visual attention.
The paper tackled the problem of computing saliency maps for dynamic scenes by proposing a method that integrates static saliency maps with optical flow to overcome the aperture problem, resulting in a highly accurate model that explains human fixation behavior in challenging scenarios like occlusions.
Saliency maps are used to understand human attention and visual fixation. However, while very well established for static images, there is no general agreement on how to compute a saliency map of dynamic scenes. In this paper we propose a mathematically rigorous approach to this prob- lem, including static saliency maps of each video frame for the calculation of the optical flow. Taking into account static saliency maps for calculating the optical flow allows for overcoming the aperture problem. Our ap- proach is able to explain human fixation behavior in situations which pose challenges to standard approaches, such as when a fixated object disappears behind an occlusion and reappears after several frames. In addition, we quantitatively compare our model against alternative solutions using a large eye tracking data set. Together, our results suggest that assessing optical flow information across a series of saliency maps gives a highly accurate and useful account of human overt attention in dynamic scenes.