期刊文献+

基于集群运动局部有序性测度的异常行为检测 被引量:1

下载PDF
导出
摘要 在异常行为检测中,运动人群中个体间的运动一致有序性程度是判断异常与否的一个重要指标。针对该情况,本文提出了基于速度场分布的粒子间作用力模型,将其应用到全局集群性描述子(Collectiveness)中来判断集群运动的一致有序性程度,即集群运动一致有序性测度。该方法采用混合高斯模型动态建模提取出视频图像的背景,在提取到的背景图像上使用KLT(Kanade-Lucas-Tomasi)算法追踪前景获得人群中个体运动的速度和位置信息。然后基于运动粒子的速度和位置信息计算邻域范围内粒子间的相互作用力,把基于速度场分布的粒子间作用力应用到全局集群性描述子中并结合邻域特性来表达集群的局部有序性测度。接着将集群中个体的局部有序性测度的分布投影到直方图,并通过计算直方图的熵值来描述行为。最后,根据计算的熵值与阈值进行比较来检测异常行为。基于不同场景下的视频序列所进行的实验测试结果验证了所提方法的有效性。
出处 《数据通信》 2016年第1期39-44,共6页
基金 国家自然科学基金(61175026) 宁波市自然科学基金(2014A610031 2014A610032) 宁波大学胡岚博士基金(ZX2013000319) 宁波大学人才工程项目(20111537) "信息与通信工程"浙江省重中之重学科开放基金(xkxl1521)
  • 相关文献

参考文献13

  • 1Kratz L, Nishino K. Anomaly detection in extremely crowded scenes using spalio-temporal motion pattern models [C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR).2009:1446-1453.
  • 2Helbing D,Molnar P. Social force model for pedestrian dynamics [J]. Physical review E, 1995,5 l (5):4282.
  • 3D.H. Anders Johansson and P.K.Shukla. Specification of the social force pedestrian model by evolutionary, adjustment to video tracking data. Advances in Complex Systems, 10 (2): 271-288, December 2007.
  • 4B. Zhou, X. Wang, and X. Tang. Understanding collective crowd behaviors: Learning a mixture model of dynamic pedestrian-agents. In Proe. CVPR, 2012.
  • 5Stauffer C, Grimson W E L. Adaptive background mixture models for real-time tracking [C]//Computer Vision and Pattern Recognition, 1999.
  • 6Tomasi C, Kanade.T Detection and tracking of point features[R]. Tech.Rep.CMU-CS-91-132,Carnegie Mellon University,1991.
  • 7Zhou B, Tang X, Wang X. Measuring Crowd Collectiveness[C] //IEEE Confence on Computer Vision and Pattern Recognition(CVPR).2013.
  • 8Freeman W T, Roth M. Orientation histograms for hand gesture recognition [C]//International Workshop on Automatic Face anti Gesture Recognition. 1995, 12:296-301.
  • 9Wikipedia., "Entropy (information theory) -- Wikipedia, the free encyclopedia," 2009. [Online]. Available: http://en. wikipedia.org/w/index.php?title=Entropy_(information_theoD,).
  • 10Unusual crowd activity dataset of University of Minnesota, available from http://mha.cs.umn.edu/movies/crowdactivity-all.

二级参考文献19

  • 1POPPE R. Vision-based human motion analysis: an overview [J]. Computer Vision and Image Understanding, 2007, 104(2): 4 -18.
  • 2MITRA S, ACHARYA T. Gesture recognition: a survey [J]. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, 2007, 37(3): 311- 324.
  • 3MECOCCI A, PANNOZZO M. A completely autonomous system that learns anomalous movements in advanced videosurveillance applications [C] /// 1EEE International Conference on Image Processing. London: IEEE, 2005:II-586 - 589.
  • 4CALDERARA S, CUCCHIARA R, PRATI A. Detection of abnormal behaviors using a mixture of Von Mises distributions [C]//IEEE Conference on Advanced Video and Signal Based Surveillanee. London: IEEE, 2007: 141- 146.
  • 5BOUTTEFROY P I. M, BOUZERDOUM A, PHUNG S L, et al. Abnormal behavior detection using a multi-modal stochastic learning approach [C]// International Conference on Intelligent Sensors, Sensor Networks and Information Processing. Sydney: IEEE, 2008: 121- 126.
  • 6TEHRANI M A, KLEIHORST R, MEIJER P, et al. Abnormal motion detection in a real time smart camera systern [C]//3rd ACM/IEEE International Conference on Distributed Smart Cameras. Como: IEEE, 2009: 1- 7.
  • 7DATTA A, SHAH M, I.()B() N D V. Person on-per son violence detection in video data [C] // Proceedings of the 16th International Conference on Pattern Recognition. Quebec City: IEEE, 2002:433-438.
  • 8CHEN Yu-feng, LIANG Guo yuan, LEE Ka-keung, el al. Abnormal behavior detection by muhi-SVM-based Baycsian network [C]// International Conference on Information Acquisition. Seogwipo-si: IEEE, 2007 : 298 - 303.
  • 9XIANG Tao, GONG Shao gang. Incremental and adaptive abnormal behavior detection [J]. Computer Vision and Image Understanding, 2008, 111(1): 59- 73.
  • 10FATHI A, MORI G. Action recognition by learning mid-level motion features [C] // IEEE Conference on Computer Vision and Pattern Recognition. Anchorage: IEEE, 2008:1-8.

共引文献19

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