Modeling, Detection and Recognition of Spatio-Temporal Events from Vide

Vide 时空事件的建模、检测和识别

• 批准号: 0200511
• 负责人: Stefano Soatto
• 金额: $ 10.07万
• 依托单位: University of California-Los Angeles
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2002
• 资助国家: 美国
• 起止时间: 2002-07-01 至 2006-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0200511&HistoricalAwards=false
• 关键词: Modeling; Detection; Recognition; Spatio; Temporal

This project addresses the design and analysis of algorithms for theidentification of dynamical models of image sequences for the purpose ofdetection, classification and recognition of spatio-temporal events fromvideo. In particular, we concentrate on (segments of) image sequences thatsatisfy certain statistical regularity conditions, such as second-orderstationarity, or certain physical constraints, such as Lambertianreflection. While this does not cover the most general video sequences,generality will follow from compositionality, by segmenting each sequenceinto portions that do satisfy the assumptions. The purpose of our models isto enable the detection, classification and recognition of dynamic events,such as the presence of smoke, moving foliage, fire, walking humans etc. inlive video.

本项目致力于从视频中检测、分类和识别时空事件的图像序列动态模型识别算法的设计和分析。特别是，我们专注于（段）图像序列，满足一定的统计规律性条件，如二阶平稳性，或某些物理约束，如朗伯反射。虽然这并不涵盖最一般的视频序列，但一般性将遵循组合性，通过将每个序列分割成满足假设的部分。我们的模型的目的是使检测，分类和识别的动态事件，如烟雾的存在，移动的树叶，火灾，步行的人等。