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

一种基于稀疏编码模型的视频异常发现方法 被引量：4

Research on Video Anomaly Discovery Based on Sparse Coding Model
下载PDF
导出
摘要 提出一种基于稀疏编码模型的视频异常发现方法,不仅可以检测"个体异常行为",同时也可以应用于"群体异常行为"检测.对个体异常和群体异常事件,分别提取HNF和多尺度运动直方图作为不同的特征,通过快速稀疏编码算法学习包含正常行为特征的字典,以特征关于字典稀疏表达的重构误差作为判断异常的标准,如重构误差大,则判断为异常.多尺度运动矢量直方图不仅减小了特征提取阶段的计算量,实验结果也证明了该特征在群体异常检测中的有效性,实现了帧级场景异常检测,与真实结果比较能更及时的报警异常出现的时刻.实验使用3种标准行为识别数据库,ROC曲线和AUC值证明了算法的实用性和有效性. An anomaly detection algorithm for video based on spare coding model is proposed, which can not only detect individual abnormal behavior, but also crowd abnormal behavior. The feature of HNF and multi-scale histogram of motion are extracted respec- tively as different features according to individual anomaly and crowd anomaly, and fast sparse coding algorithm is exploited to learn the dictionary including the feature information of normal behavior. Recontruction error is used as the criterion of discriminating a- nomaly. If the representation error is beyond a predefined threshold, it is discriminated as an anomaly. Multi-scale histogram of mo- tion not only reduce the computational complexity in the stage of feature extraction, also did the experiment result prove the efficiency of the feature in crowd anomaly detection, implementing frame-level detection in the scene. Compared with ground-truth result, our method can alarm the appearing moment of the anomaly more promptly. Three standard behavior recognition datasets are used in the work and the result of ROC curve and AUC value demonstrate the practical applicability and efficiency of the method.
作者 谢锦生 郭立 赵龙 桂树
机构地区 中国科学技术大学电子科学与技术系
出处 《小型微型计算机系统》 CSCD 北大核心 2014年第4期917-921,共5页 Journal of Chinese Computer Systems
基金 国家自然科学基金项目(61071173)资助
关键词 异常检测 稀疏编码 时空兴趣点 视频分析 anomaly detection sparse coding space-time interest point video analysis
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

  • 1Cong Y,Yuan J S,Liu J. Sparse reconstruction cost for abnormal e- vent detection [C]. 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) ,2011:3449- 3456.
  • 2Mehran R, Oyama A, Shah M. Abnormal crowd behavior detection u- sing social force model [ C]. Cvpr:2000 IEEE Conference on Com- puter Vision and Pattern Recognition ,2009,1-4:935-942.
  • 3Mahadevan V, Li Wei-xin, Bhalodia Viral. Anomaly detection in crowded scenes [ C~. 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) ,2010 : 1975-198 I.
  • 4Adam A,Rivlin E,Shimshoni I. Robust real-time unusual event detec- tion using multiple fixed-location monitors ~ J ]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(3 ):555-560.
  • 5Popoola O P,Wang K. Video-based abnormal human behavior recogni- tion--a review ~J]. Systems, Man, and Cybernetics, Part C: Applica- tions and Reviews,IEEE Transactions on,2012,42(6) :865-878.
  • 6Wright J, Yang A Y, Ganesh A. Robust face recognition via sparse representation [ J]. IEEE Transactions on Pattern Analysis and Ma- chine Intelligence,2009,31 ( 2 ) :210-227.
  • 7Laptev I. On space-time interest points~ J ]. International Journal of Computer Vision ,2005,64( 2-3 ) : 107-123.
  • 8Wang H, Ullah M M, Klaser Alexander. Evaluation of local spatio- temporal features for action recognition ~C]. In BMVC 2009- British Machine Vision Conference,2009:233-245.
  • 9Mairal J, Ponce Jean, Sapiro Guillermo. Online dictionary learning for sparse coding [ C 1- In Proceedings of the 26th Annual Interna- tional Conference on Machine Learning,2009:689-696.
  • 10Boiman O,Irani M. Detecting irregularities in images and in video [ C]. International Journal of Computer Vision,2007,74( 1 ) :17-31.

同被引文献32

  • 1ADAM A,RIVLIN E,SHIMSHONI I,et al.Robust real-time unusual event detection using multiple fixed-location monitors[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(3):555-560.
  • 2KIM J,GRAUMAN K.Observe locally,infer globally:A space-time MRF for detecting abnormal activities with incremental updates[C]//2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009). Miami,Florida,USA:IEEE,2009:2921-2928.
  • 3KRATZ L,NISHINO K.Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models[C]//2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009). Miami,Florida,USA: IEEE,2009:1446-1453.
  • 4MEHRAN R,OYAMA A,SHAH M.Abnormal crowd behavior detection using social force model[C]//2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009).Miami,Florida,USA: IEEE,2009:935-942.
  • 5LAPTEV I.On space-time interest points[J].International Journal of Computer Vision,2005,64(2/3):107-123.
  • 6DOLLáR P,RABAUD V,COTTRELL G,et al.Behavior recognition via sparse spatio-temporal features[C]//2nd Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance,2005.USA: IEEE,2005:65-72.
  • 7BLANK M,GORELICK L,SHECHTMAN E,et al.Actions as space-time shapes[C]//Tenth IEEE International Conference on Computer Vision2005,ICCV 2005.Beijing:IEEE,2005,2:1395-1402.
  • 8HELBING D,MOLNAR P.Social force model for pedestrian dynamics[J].Physical Review E,1995,51(5):4282.
  • 9KLASER A,MARSZA?EK M,SCHMID C.A spatio-temporal descriptor based on 3d-gradients[C]//BMVC 2008-19th British Machine Vision Conference.UK: British Machine Vision Association,2008,275:1-10.
  • 10WILLEMS G,TUYTELAARS T,VAN GOOL L.An efficient dense and scale-invariant spatio-temporal interest point detector[M]//10th European Conference on Computer Vision.Marseille.France:Springer Berlin Heidelberg,2008:650-663.

引证文献4

二级引证文献8

小型微型计算机系统
2014年 第4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