期刊文献+

基于超图模型的复杂视频事件检测 被引量:2

Detection of complexity video event based on hypergraph model
下载PDF
导出
摘要 近年来,语义事件分析越来越受到重视,典型语义事件的检测与识别是一个具有挑战性的研究领域。提出了基于超图模型的复杂视频事件检测方法,通过分析对象的运动轨迹,检测出视频中的所有子事件并构建时序关系图及依赖关系图,从而生成子事件超图,并通过谱超图聚类分析来检测相应的复杂事件。采用图变换工具AGG进行模拟实验,其实验结果表明,该方法具有较高的准确率与召回率。 In recent years,semantic event analysis is more and more attention.To researchers,semantic event detection and recognition is a challenging area.This paper presented a method for detection of complex video event based on hypergraph model,which could analyze the trajectory of the object for detecting sub-events,built a timing diagram and dependency graph for generating a sub-events hypergraph,and used spectral hypergraph cluster for analyzing the complex event.It used the graph transformation tool AGG simulation to verify the new method.Experimental results show that this method has higher accuracy and recall rate.
出处 《计算机应用研究》 CSCD 北大核心 2012年第12期4770-4774,共5页 Application Research of Computers
基金 国家自然科学基金资助项目(61170126) 国家教育部人文社会科学研究青年基金资助项目(12YJCZH020) 江苏省2008年度普通高校研究生科研创新计划资助项目(CX08B_097Z)
关键词 视频语义 视频事件检测 时序关系 超图模型 谱超图聚类 video semantic video event detection temporal relationship hypergraph model spectral hypergraph clustering
  • 相关文献

参考文献14

  • 1HAKEEM A, SHAH M. Learning, detection and representation of multi-agent events in videos [ J]. Artificial Intelligence, 2007,371 (8-9) : 586-605. 被引量:1
  • 2BADLER N. Temporal scene analysis: conceptual description of object movements, University of Toronto Technical Report No. 80 [R].1975. 被引量:1
  • 3AYERS D, SHAH M. Monitoring human behavior from video taken in an office environment[J]. Image and Vision Computing,2001,3 9 (12) : 833-846. 被引量:1
  • 4徐杨,吴成东,陈东岳.基于视频图像的交通事件自动检测算法综述[J].计算机应用研究,2011,28(4):1206-1210. 被引量:17
  • 5XIN Lun, TAN Tie-niu. Semi-supervised learning on semantic manifold for event analysis in dynamic scenes[C]//Proc of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington DC : IEEE Computer Society,2007 : 18- 23. 被引量:1
  • 6刘卫宁,曾恒,孙棣华,赵敏.基于视频检测技术的交通拥挤判别模型[J].计算机应用研究,2010,27(8):3006-3008. 被引量:9
  • 7ZHANG Zhang, HUANG Kai-qi, TAN Tie-niu, et al. Trajectory series analysis based event rule induction for visual surveillance [ C ]// Proc of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington DC: IEEE Computer Society,2007: 1-8. 被引量:1
  • 8ZHONG Hua, SHI Jian-bo, VISONTAI M. Detecting unusual activity in video [ C ]//Proc of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2004 : 819-826. 被引量:1
  • 9RAO Cen, YILMAZ A, SHAH M. View-invariant representation and recognition of actions[J]. International Journal of Computer Vision ,2002,50 ( 2 ) :203-226. 被引量:1
  • 10JU Shi-guang, CHEN Xiao-jun, XU Guang-hua. An improved mixture Gaussian models to detect moving object under real-time complex background [ C ]//Proc of International Conference on Cyberworlds. 2008:730-734. 被引量:1

二级参考文献48

  • 1侯志强,韩崇昭.视觉跟踪技术综述[J].自动化学报,2006,32(4):603-617. 被引量:254
  • 2方晓莹,黄林伟,刘富强.ITS中基于视频的交通异常情况检测[J].计算机工程与应用,2006,42(36):212-215. 被引量:5
  • 3孙棣华,董均宇,廖孝勇.基于GPS探测车的道路交通状态估计技术[J].计算机应用研究,2007,24(2):243-245. 被引量:19
  • 4ELGAMMAL A,DURAISWAMI R,HARWOOD D,et al.Background and foreground modeling using nonparametric kernel density estimation for visual surveillance[J].Proceedings of the IEEE,2002,90(7):1151-1163. 被引量:1
  • 5Highway capacity manual[M].Washington DC:TRB,National Research Council,2000. 被引量:1
  • 6ELGAMMAL A,HARWOOD D,DAVIS L.Non-parametric model for background subtraction[C] //Proc of the 6th European Conference on Computer Vision.2000. 被引量:1
  • 7LI Li, SONG Jing-yan, WANG Fei-yue, et al. IVS 05 : new developments and research trends for intelligent vehicles [ J ]. IEEE intelligent Systems,2005,20 ( 4 ) : 10-14. 被引量:1
  • 8LI Li, WANG Fei-yue. Advanced motion control and sensing for intelligent vehicles[ M ].New York : Springer,2007. 被引量:1
  • 9AOK1 M. Imaging and analysis of traffic scene[ C]//Proe of International Conference on image Processing. 1999 : 1-5. 被引量:1
  • 10IKEDA H. Abnormal incident detection system employing image pro- cessing technology[ C]//Proe of IEEE International Conference on Intelligent Transportation Systems. 1999:748-752. 被引量:1

共引文献24

同被引文献4

引证文献2

二级引证文献3

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