期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

自然环境下日常动作的在线识别 被引量：4

On-Line Recognition of Actions in Daily Living
下载PDF
导出
摘要 自然环境下的日常动作识别有着广泛的应用前景和重要的研究价值.不同于以往在结构化和孤立条件下进行的动作识别,自然环境下的日常动作是连续的,视角多变并常发生遮挡.本文提出了分布式视觉系统下日常动作的在线识别方法.时间轴上的滑动窗口每个时刻取一段视频帧,采用基于"包容形状"的视角无关的体态表示方法提取体态特征向量,并用隐马尔科夫模型进行识别.动作类型的搜索空间由环境知识推理得到.遮挡检测和部分遮挡下的体态表示也在文中进行了讨论.实验表明本文提出的日常动作的在线识别方法能够克服日常场景给动作识别带来的困难,结果证实了方法的有效性. Recognition of actions in daily living is challenging because： （ 1 ） actions are continuous; （2） human location is changeful; （3） human body is partially occluded sometimes. This paper proposes a multi-view framework for on-line recognition of actions in daily living. Action representation based on ＂Envelope shape＂ enables view-invariant action recognition. A sliding window concatenates the feature vectors for action representation into a stream as the input to a bank of HMMs. A maximum likelihood based classifier detects action. The HMMs are chosen by an ontology based enviroument knowledge model. Besides, occlusion detection and action representation in occlusion are also discussed. Implementations demonstrate the efficacy of our approach.
作者 曹媛媛 黄飞跃 陶霖密 徐光祜
机构地区 普适计算教育部重点实验室 腾讯研究院
出处 《电子学报》 EI CAS CSCD 北大核心 2009年第B04期16-21,共6页 Acta Electronica Sinica
基金 国家自然科学基金(No.60673189)
关键词 动作识别 视角不变 遮挡检测 action recognition view invariant occlusion detection
分类号 TP391 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献10

  • 1L W Campbell, D A Becker, A Azarbayejani, A F Bobick, A Penfland. Invariant features for 3D gesture recognition[A]. Proceedings of International Conference on Automatic Face and Gesture Recognition [C]. Vermont, USA: IEEE, 1996. 157 -162.
  • 2N Jin, F Mokhtarian. Image-based shape model for view-invariant human motion recognition [ A ]. Proceedings of Conference on Advanced Video and Signal Based Surveillance [ C ]. London: IEEE, 2007. 336 - 341.
  • 3A S Ogale, A Karapurkar, Y Aloimonos. View-invariant modeling and recognition of human actions using grammars[A]. International Conference on Computer Vision, Workshop on Dynamical Vision[C]. Beijing, China: Springer Verlag, 2005.
  • 4C Rao, A Yilmaz, M Shah. View-invariant representation and recognition of actions[J]. International Joumal of Computer Vision, 2002,50(2) : 203 - 226.
  • 5V Parameswaran, R Chellappa. Using 2D projective invariance for human action recognition[J]. International Journal of Computer Vision, 2006,66(1) : 83 - 101.
  • 6P C Chung, C D Liu. A daily behavior enabled hidden Markov model for human behavior understanding [J]. Pattern Recognition,2008,41 (5) : 1572 - 1580.
  • 7Y Wang, K Huang, T N Tan. Abnormal activity recognition in office based on R transform[A]. Proceedings of IEEE Conference on Image Processing [C]. San Antonio, Texas: IEEE, 2007. 341 - 344.
  • 8N T Nguyen, D Q Phung, S Venkatesh, H Bui. Learning and detecting activities from movement trajectories using the hierarchical hidden Markov model[ A]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition [ C ]. San Diego, CA, USA: IEEE, 2005.955 - 960.
  • 9J Wu, A Osuntogun, T Choudhury. A scalable approach to activity recognition based on object use[A]. Proceedings of IEEE Conference on Computer Vision [C]. Rio de Janeiro, Brazil: Springer Verlag, 2007.1 - 8.
  • 10W M Hu, X Zhou. Principal axis-based correspondence between multiple cameras for people tracking [J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2006, 28 (4) : 663 - 671.

同被引文献60

  • 1陈薇.基于关联函数评价应注意的问题[J].哈尔滨工业大学学报,2006,38(7):1143-1145. 被引量：9
  • 2Yuping Shen, Foroosh H. View-Invariant. Action Recognition from Point Triplets[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(10): 1898-1905.
  • 3Liang Wang, David Suter. Learning and Matching of Dynamic Shape Manifolds for Human Action Recognition[J]. IEEE Transactions on Image Processing, 2006, 16(6):1646-q661.
  • 4Taylor Goodhart, Pingkun Yan, Mubamk Shah. Action Recogn ition Using Spatio-temporal Regularity Based Features[C]. ICASSP 2008. Las Vegas:[s.n.],2008,9:745-748.
  • 5Isabel Serrano Vicente. Danica Kragic and Jan-Olof Eklundh. Learning and Recognition of Object manipulation Actions Using Linear and Nonlinear Dimensionality Reduction[C]. 16th IEEE Intemational Conference on Robot & Human Interactive Communication. Korea:[s.n.], 2007:1010-1015.
  • 6Yang Wang, Greg Mori. Human Action Recognition by Semilatent Topic Models[J]. IEEE IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(10):1762-1774.
  • 7Masamichi Shimosaka, Yu Nejigane. Fast Online Action Recognition With Efficient Structured Boosting[C]. ICME 2009. Mexico:[s.n],2009:706-709.
  • 8Chuohao Yeo, Parvez Ahammad, Kannan Ramchandran, S. Shankar Sastry. High-Speed Action Recognition and Localization in Compressed Domain Videos[J]. IEEE Transactions on Circuits and Systems for Video Techdology, 2008,18(8): 1006-1015.
  • 9Dennis Herzog, Ales Ude, Volker KrUger. Motion Imitation and Recognition using Parametric Hidden Markov Models[C].IEEE-RAS International Conference on Humanoid Robots. Kerea:[s.n.], 2008:339-346.
  • 10蔡文.物元及其应用[M].北京:科学技术文献出版社,1994:267-275.

引证文献4

二级引证文献8

电子学报
2009年 第B04期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部