Computational Vision

计算视觉

• 批准号: CRC-2017-00328
• 负责人: Tsotsos, John
• 金额: $ 14.57万
• 依托单位: York University
• 依托单位国家: 加拿大
• 项目类别: Canada Research Chairs
• 财政年份: 2019
• 资助国家: 加拿大
• 起止时间: 2019-01-01 至 2020-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=694300
• 关键词: Computational; Vision

Research focuses on two main goals: to further understanding of how vision can be the primary sense that guides human behavior, and to use this understanding to build active agents that purposely behave in real environments. We employ human experimental studies and the full spectrum of computational methods. Our model of visual attention will be extended to support visual reasoning and task execution in dynamic environments. These require interactions with memory, control, sensor sub-systems, and joint attention for interactions with other agents. Relevance will be demonstrated with applications to autonomous driving and companion robots for the elderly and in manufacturing.

研究集中在两个主要目标：进一步理解视觉如何成为指导人类行为的主要感觉，并利用这种理解来构建主动代理，有目的地在真实的环境中表现。我们采用人体实验研究和全谱计算方法。我们的视觉注意力模型将被扩展以支持动态环境中的视觉推理和任务执行。这些需要与记忆，控制，传感器子系统的交互，以及与其他代理交互的联合注意力。相关性将通过应用于老年人和制造业的自动驾驶和伴侣机器人来证明。