期刊文献+

基于Latent SVM的多视角行为识别方法 被引量:1

Multiple-Viewpoint Human Action Recognition Based on Latent SVM
下载PDF
导出
摘要 为了在静态图像中获取有效信息,构建行为模型,提出了行为覆盖区ACA(Action Coverage Area)和行为核心AC(Action Core)的概念,基于Latent SVM(Support Vector Machine)目标识别方法,设计了一种多视角行为模型MVAM(Multiple Viewpoint Action Model)。建立了独立的用于行为模型训练和测试的行为数据库。实验表明,该表示法对静态图像中的人体行为能有效地进行分类和检测。 We study the concepts of ACA( Action Coverage Area) and AC( Action Core),and design a multiple-viewpoint action model based on the advanced object recogniton method Latent SVM( Support Vector Machine). Multi-viewpoint ACA can succinctly describe the non-rigid change and appearance variation due to different viewpoints and multi-viewpoint AC,because the auxiliary of ACA can help to improve the efficiency and robustness of action recognition. We created an independent dataset of human action for model training and testing. Experiments showed that our model had high performance in classifying and detecting human action in still images.
出处 《吉林大学学报(信息科学版)》 CAS 2016年第6期747-752,共6页 Journal of Jilin University(Information Science Edition)
基金 国家自然科学基金资助项目(61101155) 吉林省发展和改革委员会省级产业创新专项基金资助项目(2016C035)
关键词 行为识别 隐变量支持向量机 行为覆盖区 行为核心 多视角行为模型 action recognition latent support vector machine(SVM) action coverage area(ACA) action core(AC) multiple viewpoint action model(MVAM)
  • 相关文献

参考文献2

二级参考文献56

  • 1刘相滨,向坚持,王胜春.人行为识别与理解研究探讨[J].计算机与现代化,2004(12):1-5. 被引量:12
  • 2魏志强,纪筱鹏,冯业伟.基于自适应背景图像更新的运动目标检测方法[J].电子学报,2005,33(12):2261-2264. 被引量:54
  • 3Oliver N,Horvitz E.A comparison of HMMs and dynamic Bayesian networks for recognizing office activities[J].Lecture Notes in Artificial Intelligence,2005,3538:199-209. 被引量:1
  • 4Kolonias I,Christmas W,Kittler J.Use of context in automatic annotation of sports videos[J].Lecture Notes in Computer Science,2004,3287:1-12. 被引量:1
  • 5Park S,Aggarwal J K.A hierarchical Bayesian network for event recognition of human actions and interactions[J].Multimedia Systems,2004,10(2):164-179. 被引量:1
  • 6Lafferty J,Mccallum A,Pereira F.Conditional random fields:probabilistic models for segmenting and labeling sequence data[A].In Proc ICML[C].Massachusetts:IEEE press,2001,282-289. 被引量:1
  • 7Sminchisescu C,Kanaujia A,Li Z,Metaxas D.Conditional models for contextual human motion recognition[A].In Proc ICCV[C].Beijing:IEEE Computer Society Press,2005.2:1808-1815. 被引量:1
  • 8Luhr S,Bui H H,Venkatesh S,West G A W.Recognition of Human Activity through Hierarchical Stochastic Learning[A].In Proc.PerCom[C].Texas:IEEE Computer Society Press,2003.416-422. 被引量:1
  • 9Duong T V,Bui H H,Phung D Q,Venkatesh S.Activity recognition and abnormality detection with the switching hidden semi-Markov model[A].In Proc CVPR[C].San Diego:IEEE Computer Society Press,2005.838-845. 被引量:1
  • 10Nguyen N T,Venkatesh S,West G A W.Learning people movement model from multiple cameras for behaviour recognition[J].Lecture Notes in Computer Science,2004,3138:315-324. 被引量:1

共引文献78

同被引文献4

引证文献1

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