Bio-inspired computer vision: Towards a synergistic approach of artificial and biological vision
作者：
Highlights：
• We present an overview of computational approaches to biological vision.
• We develop a task centered presentation of biological vision studies.
• We revisit three tasks: image sensing, scene segmentation and optical flow.
• We show how new computer vision methods could be developed from biological insights.
• We identify key task specific biological vision models which could be scaled up.
摘要
•We present an overview of computational approaches to biological vision.•We develop a task centered presentation of biological vision studies.•We revisit three tasks: image sensing, scene segmentation and optical flow.•We show how new computer vision methods could be developed from biological insights.•We identify key task specific biological vision models which could be scaled up.
论文关键词：Canonical computations,Event based processing,Dynamic sensors,Multiplexed representation,Population coding,Soft selectivity,Feedback,Lateral interactions,Form-motion interactions
论文评审过程：Received 25 March 2015, Revised 8 April 2016, Accepted 17 April 2016, Available online 29 April 2016, Version of Record 30 June 2016.
论文官网地址：https://doi.org/10.1016/j.cviu.2016.04.009
