全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

视频监控中的行为序列分割与识别

DOI: 10.11834/jig.20091138

Keywords: 行为序列分割,行为识别,本征维数,奇异值分解,隐马尔可夫模型

Full-Text   Cite this paper   Add to My Lib

Abstract:

智能监控系统中的行为分析与识别是当前计算机视觉领域的研究热点,而行为序列分割则是行为分析与识别的基础。提出了一种无监督的行为序列分割算法,并对分割结果进行识别。首先,采用鲁棒的形状编码方案得到人体轮廓的紧凑表示,提取轮廓点集特征描述运动人体;然后,基于奇异值分解(SVD)估计行为序列数据的本征维数,确定数据对应的低维流形,并通过检测特征数据在该流形上的投影误差的突变实现行为序列分割;最后,采用隐马尔可夫模型(HMM)对分割结果进行识别。在公共数据库上的实验结果表明了此分割和识别算法的有效性。

References

[1]  Gong Shao-gang,Xiang Tan,Recognition of group activities using dynamic probabilistic networks,Nice,France,2003.
[2]  Zelnik-manor L,lrani M,Event-based analysis of video,Waikoloa,Hawaii,USA,2001.
[3]  Xiang Tan,Gong Shao-gang,Video behaviour profiling and abnormality detectionwithoutmanuallabeling,北京,2005.
[4]  Barbic J,Safonova A,Pan J Y,Segmenting motion capture data into distinct behaviors,Ontario,Canada,2004.
[5]  Chen Duan-yu,Liao Hongyuanmark,Shih Sheng-wen,Continuous human action segmentation and recognition using a spatio-tempnral probabilistic framework,San Diego,California,USA,2006.
[6]  查看详情 2009
[7]  Babick A F,Davis J W,The recognition of human movement using temporal templates,IEEE Transactions on Pattern Analysis and Machine Intelligence,2001(03).
[8]  Oliver N M,Rosario B,Pentland A P,A bayesian computer vision system for modeling human interactions,IEEE Transactions on Pattern Analysis and Machine Intelligence,2000(08).
[9]  Zhong Hua,Shi Jian-bo,Visontai M,Detecting unusual activity in video,Washington,DC:USA,2004.
[10]  Yong Rui,Anandan P,Segmenting visual actions based on spatiotemporal motion patterns,Hilton Head,SC,USA,2000.
[11]  吴晓婕,胡占义,吴毅红,基于Segmental-DTW的无监督行为序列分割,软件学报,2008(09).
[12]  All A,Aggarwal J K,Segmentation and recognition of continuous human activity,Vancouver,BC,Canda,2001.
[13]  Bauchhage C,Tsotsos J K,Bunn F E,Automatic detection of abnormal gait,Image and Vision Computing,2009(1-2).
[14]  查看详情 2009
[15]  查看详情 2005

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133