Hierarchical Visual Attention Model for Saliency Detection Inspired by Avian Visual Pathways

作     者：Xiaohua Wang Haibin Duan 

作者机构：the State Key Laboratory of Virtual Reality Technology and Systems School of Automation Science and Electrical Engineering Beihang University the State Key Laboratory of Virtual Reality Technology and Systems School of Automation Science and Electrical EngineeringBeihang University the Peng Cheng Laboratory 

出 版 物：《IEEE/CAA Journal of Automatica Sinica》 (自动化学报（英文版）)

年 卷 期：2019年第6卷第2期

页      面：540-552页

核心收录：

学科分类：0710[理学-生物学] 0810[工学-信息与通信工程] 1205[管理学-图书情报与档案管理] 07[理学] 08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 0811[工学-控制科学与工程] 071003[理学-生理学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by Natural Science Foundation of China(61425008 61333004 61273054) 

主　　题：Avian visual pathways bio-inspired saliency detection visual attention 

摘      要：Visual attention is a mechanism that enables the visual system to detect potentially important objects in complex environment. Most computational visual attention models are designed with inspirations from mammalian visual systems.However, electrophysiological and behavioral evidences indicate that avian species are animals with high visual capability that can process complex information accurately in real time. Therefore,the visual system of the avian species, especially the nuclei related to the visual attention mechanism, are investigated in this paper. Afterwards, a hierarchical visual attention model is proposed for saliency detection. The optic tectum neuron responses are computed and the self-information is used to compute primary saliency maps in the first hierarchy. The winner-takeall network in the tecto-isthmal projection is simulated and final saliency maps are estimated with the regularized random walks ranking in the second hierarchy. Comparison results verify that the proposed model, which can define the focus of attention accurately, outperforms several state-of-the-art models.This study provides insights into the relationship between the visual attention mechanism and the avian visual pathways. The computational visual attention model may reveal the underlying neural mechanism of the nuclei for biological visual attention.