Estimation of User's Attention Based on Saliency Map Using Distribution of Visual Acuity in First Person View

Abstract

As one of the component techniques of the human-symbiotic systems, the method for estimating a user's attention by combining the view estimation and the saliency map has been proposed. However, in this method, the saliency is calculated based on images captured from the external cameras instead of the user's first person view. Furthermore, the calculation does not take the human's visual characteristics into account. In this study, we propose a system for estimating a user's attention more accurately by calculating the saliency using the distribution of visual acuity in the user's estimated first person view.