Digital video analysis based on contexts

基于上下文的数字视频分析

• 批准号: 36726-2010
• 负责人: Li, ZeNian
• 金额: $ 2.26万
• 依托单位: Simon Fraser University
• 依托单位国家: 加拿大
• 项目类别: Discovery Grants Program - Individual
• 财政年份: 2012
• 资助国家: 加拿大
• 起止时间: 2012-01-01 至 2013-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=508301
• 关键词: Digital; video; analysis; based; contexts

Digital video carries rich multimedia information and it involves insurmountable amount of data. In recent years, researchers have advocated that contextual information in the video is vital for understanding its content so its processing and retrieval can be more reliable. Because of its additional time dimension, digital video indeed facilitates contextual analysis. However, context itself is an elusive subject. Although simple visual features (color, texture, shape, etc.) and their geometric and temporal relationships can provide some contextual information, they are often limited and unreliable.

数字视频承载着丰富的多媒体信息，涉及的数据量是不可逾越的。近年来，研究人员主张，视频中的上下文信息对于理解视频内容至关重要，因此视频的处理和检索可以更加可靠。由于其额外的时间维度，数字视频确实有利于上下文分析。然而，语境本身是一个难以捉摸的主题。虽然简单的视觉特征（颜色、纹理、形状等）及其几何和时间关系可以提供一些上下文信息，但它们往往是有限和不可靠的。