期刊文献+

基于阶层多观测模型的多人行为识别

Hierarchical multi-observation model for multi-person activity recognition
原文传递
导出
摘要 为解决多人行为识别中高维特征空间、角色分配不准确和复杂的时间结构等问题,该文分析了多人行为的特点,提出了一种递归的多层随机网络模型。该模型通过多层网络表达行为的多尺度特性,并由高层体现行为的长时间依赖性。通过对观测的分解大大降低了特征空间的维数,从而降低了问题的复杂度,并在一定程度上消除了目标角色分配不准确带来的影响。实验结果表明:该文提出的模型比其他常用模型具有更好的识别效果,即使对复杂行为依然具有91.3%以上的识别率。 A reeursive multi-level stochastic model is presented for multi-person activity recognition, such as in a high-dimension feature space, role assignments and with complex temporal structures. The model represents the multi-scale characteristics of activities by the multi-level network and captures the long-term dependency using high-level chains. The model decomposing observations considerably reduce the dimensionality of the feature space. The assumption that sub-observations have uniform distributions partly eliminates the effects of role assignment errors. Test results demonstrate that the model outperforms other popular models, with 91.3% recognition rate even for complex activities.
出处 《清华大学学报(自然科学版)》 EI CAS CSCD 北大核心 2009年第7期1058-1061,共4页 Journal of Tsinghua University(Science and Technology)
基金 国家自然科学基金资助项目(60772050)
关键词 行为识别 隐MARKOV模型 多通道序列处理 阶层建模 activity recognition hidden Markov model (HMM) multi-channel sequence modeling hierarchy modeling
  • 相关文献

参考文献8

  • 1HU Weiming, TAN Tieniu, WANG Liang, et al. A survey on visual surveillance of object motion and behaviors [J]. IEEE Tran on System, Man, and Cyberbetics, 2004, 34 (3):334 - 352.
  • 2Oliver N, Rosario B, Pentland A. A Bayesian computer vision system for modeling human interactions[J]. IEEE Tran on PAMI, 2000, 22:831 - 843.
  • 3Hakeem A, Shah M. Learning, detection and representation of multi-agent events in videos[J]. Artificial Intelligence, 2007, 171: 586-605.
  • 4ZHANG Weidong, CHEN Feng, XU Wenli, et al, Decomposition in hidden Markov models for activity recognition [C]//MCAM. WH: LNCS, 2007:232 - 241.
  • 5LIU Xiaohui, Chua C S, Multi-agent activity recognition using observation decomposed hidden Markov models [J]. Image and Vision Computing. 2006, 24:166 - 175.
  • 6Murphy K P. Dynamic Bayesian networks: Representation, inference and learning[D]. Berkeley, US: University of California at Berkeley, 2002.
  • 7ZHANG Weidong, CHEN Feng, XU Wenli, et al, Real-time video intelligent surveillance system [C]// ICME. Canada: IEEE, 2006:1021 - 1024.
  • 8Fine S, Singer Y, Tishby N. The hierarchical hidden Markov model: Analysis and applications[J]. Machine Learning, 1998, 32(1): 41-62.

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