Target detection in three-dimensional optic flow

三维光流中的目标检测

• 批准号: DP170100008
• 负责人: Prof Karin Nordstrom
• 金额: $ 18.23万
• 依托单位: Flinders University
• 依托单位国家: 澳大利亚
• 项目类别: Discovery Projects
• 财政年份: 2017
• 资助国家: 澳大利亚
• 起止时间: 2017-02-28 至 2019-06-02
• 项目状态: 已结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/DP170100008
• 关键词: Target; detection; three; dimensional; optic

This project aims to understand the behavioural, neural, and computational mechanisms underlying the visualisation of moving targets. Insects have poorer eyesight and smaller brains than humans, but can chase small targets at high speed. This project will use intracellular electrophysiology, information content analysis and model development to decipher the underlying neural tuning mechanisms of hoverflies, which could suggest advanced computational optimisation and miniaturisation. The project may generate algorithms for rapid and reliable information extraction from large, noisy inputs, useful for developing unmanned vehicles and in Big Data analysis. The results could be useful in developing anti-collision control systems in vehicles using less computational power.

该项目旨在了解移动目标可视化的行为，神经和计算机制。昆虫的视力和大脑都比人类差，但它们可以高速追逐小目标。该项目将使用细胞内电生理学，信息内容分析和模型开发来破译hoverflies的潜在神经调谐机制，这可能表明先进的计算优化和简化。该项目可能会生成算法，用于从大量嘈杂的输入中快速可靠地提取信息，这对开发无人驾驶车辆和大数据分析非常有用。研究结果可用于开发使用较少计算能力的车辆防撞控制系统。