Temporal Texture and Action Identification: A Recognition Approach to Motion

时间纹理和动作识别：运动的识别方法

• 批准号: 9010692
• 负责人: Randal Nelson
• 金额: $ 4.83万
• 依托单位: University of Rochester
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 1990
• 资助国家: 美国
• 起止时间: 1990-07-01 至 1992-12-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9010692&HistoricalAwards=false
• 关键词: Temporal; Texture; Action; Identification; Recognition

This Research Initiation Award is for investigation of object recognition by means of motion patterns. Objects that typically move are easier to identify when in motion. Dr. Nelson will study both complex, non-rigid motion fields such as windblown trees, ripples on water, and chaotic fluid flow, and action identification for compact objects such as machinery and moving people. His recognition approach will apply methods of statistical texture identification to features extracted from optical motion fields. Monitoring and surveillance are among the possible applications.

这个研究启动奖是为了研究对象 通过运动模式进行识别。 对象通常 在运动中更容易识别。 纳尔逊医生会 研究复杂的非刚性运动场，如风吹 树木，水面上的涟漪，混乱的流体流动，以及动作 用于紧凑物体的识别，如机器和移动 人 他的识别方法将采用 统计纹理识别 光学运动场 监测和监视是其中之一 可能的应用。