计算机工程与应用Issue(9)：103-106,149,5.DOI:10.3778/j.issn.1002-8331.1312-0172
基于时序上下文的视频场景分类
Video classification based on time series contextual informa-tion
摘要
Abstract
On the basis of traditional bag of word model, according to the spatial and semantic similarity between the key frames of adjacent lens, this paper brings a new video scene classification model. It divides video clips into many shots and extracts their key frames and makes the key frames a gauge. The next thing is that the key frames as an image block produces an image on time sequence. SIFT features and HSV feature are extracted. This paper embeds the SIFT features and HSV feature data into Hilbert space. Through multi kernel learning, the algorithm selects the appropriate kernel func-tions to train each image, and gets the classification model. Experiments show that the proposed algorithm for video classi-fication can achieve better performance.关键词
时序上下文特征/尺度不变特征变换(SIFT)特征/HSV颜色特征/多核学习Key words
time series contextual character/Scale-Invariant Feature Transform(SIFT)character/HSV character/multi kernel learning分类
信息技术与安全科学引用本文复制引用
彭太乐,张文俊,丁友东,郭桂芳..基于时序上下文的视频场景分类[J].计算机工程与应用,2014,(9):103-106,149,5.基金项目
国家自然科学基金（No.61303093）；安徽省高校自然科学研究重点项目（No.KJ2010A304）。 （）
