A Review Of Attention Models In Image Protrusion And Object Detection

摘要

Modelling in visual attention especially the stimulus-driven one, i.e. saliency-based attention, has been a very active research field during the recent 25 years. There are many attention models which, apart from being in other aspects, have been offered in successful functions of computer vision, moving robots, and cognitive systems. The present article surveys the primary concepts of visual attention, implemented in cognitive, Bayesian network, decision theories, and information theory in a computational perspective. It will demonstrate a categorization that provides a critical comparison of the approaches as well as their abilities and results. Specifically, the article formulates the criteria, derived from computational behaviors and studies in order to compare the quality of visual attention models.