微信服务号

微信订阅号

2025年7月11日 21:35 星期五
首页 > 过刊浏览>2015年第26卷第11期 >2884-2896. DOI:10.13328/j.cnki.jos.004893
PDF HTML阅读 XML下载 导出引用 引用提醒
基于多尺度时间递归神经网络的人群异常检测
作者:
基金项目:

国家自然科学基金(61202269, 61472089); 广东省自然科学基金(2014A030306004, 2014A030308008); 广东省科技计划(2013B051000076); 广东省高校学科专业建设与质量工程专项(PT2011JSJ); 广州市科技计划(201200000031, 2013Y2-00034, 2014Y2-00027); 计算机软件新技术国家重点实验室开发课题(KFKT2014B03, KFKT2014B23)


Abnormal Crowd Detection Based on Multi-Scale Recurrent Neural Network
Author:
  • 摘要
    • | |
  • 访问统计
    • |
  • 参考文献 [35]
    • |
  • 相似文献 [20]
    • | | |
  • 文章评论
    摘要:

    如何在人群密度大、变化快、存在大量遮挡的密集场景中实现可靠的人群事件检测,是领域研究的难点和热点.在密集场景时空建模的基础上提出了一种基于多尺度时间递归神经网络的人群异常事件检测和定位方法.首先对人群场景进行网格化划分,并利用多尺度光流直方图对每个网格的人群动态进行刻画;然后,连接各个局部的人群动态获得整体的人群动态,实现整体人群动态的时间序列建模;最后,利用多尺度时间递归神经网络实现异常事件的检测和定位.其中,多尺度隐含层实现了密集场景中不同规模相邻网格之间的空间联系,节点间的反馈关系则为时间维度上的关系表达提供了有效方案.与多种代表性算法的对比实验,验证了本方法的有效性.

    Abstract:

    Because of the great variations of crowd density and crowd dynamics, as well as the existence of many shelters in scenes, the abnormal crowd event detection and localization are still challenging problems and hot topics of the crowd scene analysis. Based on the spatial-temporal modeling of the crowd scene, this paper proposes an abnormal crowd event detection and localization approach based on multi-scale recurrent neural network. Firstly, the crowd scenes are split into grids and presented using multi-scale histogram of optical flow (MHOF). Then, different grids are connected to obtain a global time series model of the crowd scene. Finally, a multi-scale recurrent neural network is devised to detect and locate the abnormal event on the time series model of the crowd scene. In the multi-scale recurrent neural network, the multi-scale hidden layers are used to model the spatial relation among different scale neighbors, and the feedback loops are used to catch the temporal relation. Extensive experiments demonstrate the effectiveness of the presented approach.

    参考文献
    [1] Zhan B, Monekosso DN, Remagnino P, Velastin SA, Xu LQ. Crowd analysis:A survey. Machine Vision and Applications, 2008, 19(5-6):345-357.[doi:10.1007/s00138-008-0132-4]
    [2] Junior JCSJ, Musse SR, Jung CR. Crowd analysis using computer vision techniques. IEEE Signal Processing Magazine, 2010,27(5):66-77.[doi:10.1109/MSP.2010.937394]
    [3] Thida M, Yong YL, Climent-Pérez P, Eng HL, Remagnino P. A literature review on video analytics of crowded scenes. In:Proc. of the Intelligent Multimedia Surveillance. Berlin, Heidelberg:Springer-Verlag, 2013. 17-36.[doi:10.1007/978-3-642-41512-8_2]
    [4] Li T, Chang H, Wang M, Ni BB, Hong RC, Yan SC. Crowded scene analysis:A survey. IEEE Trans. on Circuits and Systems for Video Technology, 2014,25(3):367-386.[doi:10.1109/TCSVT.2014.2358029]
    [5] Kong D, Gray D, Tao H. A viewpoint invariant approach for crowd counting. In:Proc. of the 18th Int'l Conf. on Pattern Recognition. 2006. 1187-1190.[doi:10.1109/TCSVT.2014.2358029]
    [6] Kratz L, Nishino K. Tracking with local spatio-temporal motion patterns in extremely crowded scenes. In:Proc. of the Computer Vision and Pattern Recognition (CVPR). 2010. 693-700.[doi:10.1109/CVPR.2010.5540149]
    [7] Benabbas Y, Ihaddadene N, Djeraba C. Motion pattern extraction and event detection for automatic visual surveillance. Journal on Image and Video Processing, 2011,2011(1):413-447.[doi:10.1155/2011/163682]
    [8] Solmaz B, Moore BE, Shah M. Identifying behaviors in crowd scenes using stability analysis for dynamical systems. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2012,34(10):2064-2070.[doi:10.1109/TPAMI.2012.123]
    [9] Cong Y, Yuan J, Tang Y. Video anomaly search in crowded scenes via spatio-temporal motion context. IEEE Trans. on Information Forensics and Security, 2013,8(10):1590-1599.[doi:10.1109/TIFS.2013.2272243]
    [10] Reddy V, Sanderson C, Lovell BC. Improved anomaly detection in crowded scenes via cell-based analysis of foreground speed, size and texture. In:Proc. of the Computer Vision and Pattern Recognition Workshops (CVPRW). 2011. 55-61.[doi:10.1109/CVPRW.2011.5981799]
    [11] Cong Y, Yuan J, Liu J. Sparse reconstruction cost for abnormal event detection. In:Proc. of the Computer Vision and Pattern Recognition (CVPR). 2011. 3449-3456.[doi:10.1109/CVPR.2011.5995434]
    [12] Cheng KW, Chen YT, Fang WH. Abnormal crowd behavior detection and localization using maximum sub-sequence search. In:Proc. of the 4th ACM/IEEE Int'l Workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Stream. ACM Press, 2013. 49-58.[doi:10.1145/2510650.2510655]
    [13] Mehran R, Oyama A, Shah M. Abnormal crowd behavior detection using social force model. In:Proc. of the Computer Vision and Pattern Recognition (CVPR). 2009. 935-942.[doi:10.1109/CVPR.2009.5206641]
    [14] Chen DY, Huang PC. Visual-Based human crowds behavior analysis based on graph modeling and matching. Sensors Journal, IEEE, 2013,13(6):2129-2138.[doi:10.1109/JSEN.2013.2245889]
    [15] Antic B, Ommer B. Video parsing for abnormality detection. In:Proc. of the Computer Vision (ICCV). 2011. 2415-2422.[doi:10. 1109/ICCV.2011.6126525]
    [16] Wu S, Moore BE, Shah M. Chaotic invariants of lagrangian particle trajectories for anomaly detection in crowded scene. In:Proc. of the Computer Vision and Pattern Recognition (CVPR). 2010. 2054-2060.[doi:10.1109/CVPR.2010.5539882]
    [17] Zhang D, Gatica-Perez D, Bengio S, Mccowan L. Semi-Supervised adapted hmms for unusual event detection. In:Proc. of the Computer Vision and Pattern Recognition (CVPR). 2005. 611-618.[doi:10.1109/CVPR.2005.316]
    [18] Mahadevan V, Li W, Bhalodia V, Vasconcelos N. Anomaly detection in crowded scenes. In:Proc. of the Computer Vision and Pattern Recognition (CVPR). 2010. 1975-1981.[doi:10.1109/CVPR.2010.5539872]
    [19] Kim J, Grauman K. Observe locally, infer globally:A space-time MRF for detecting abnormal activities with incremental updates. In:Proc. of the Computer Vision and Pattern Recognition (CVPR). 2009. 2921-2928.[doi:10.1109/CVPR.2009.5206569]
    [20] Kratz L, Nishino K. Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models. In:Proc. of the Computer Vision and Pattern Recognition (CVPR). 2009. 1446-1453.[doi:10.1109/CVPR.2009.5206771]
    [21] Li W, Mahadevan V, Vasconcelos N. Anomaly detection and localization in crowded scene. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2014,36(1):18-32.[doi:10.1109/TPAMI.2013.111]
    [22] Cong Y, Yuan J, Liu J. Abnormal event detection in crowded scenes using sparse representation. Pattern Recognition, 2013,46(7):1851-1864.[doi:10.1016/j.patcog.2012.11.021]
    [23] Thida M, Eng HL, Dorothy M, Remagnino P. Learning video manifold for segmenting crowd events and abnormality detection. In:Proc. of the Computer Vision (ACCV 2010). Berlin, Heidelberg:Springer-Verlag, 2011. 439-449.[doi:10.1007/978-3-642-19315-6_34]
    [24] Andrade EL, Blunsden S, Fisher RB. Modelling crowd scenes for event detection. In:Proc. of the 18th Int'l Conf. on Pattern Recognition. 2006. 175-178.[doi:10.1109/ICPR.2006.806]
    [25] Benabbas Y, Ihaddadene N, Djeraba C. Motion pattern extraction and event detection for automatic visual surveillance. Journal on Image and Video Processing, 2011,2011:Article ID 163682.[doi:10.1155/2011/163682]
    [26] Wu S, Wong HS, Yu Z. A Bayesian model for crowd escape behavior detection. IEEE Trans. on Circuits and Systems for Video Technology, 2014,24(1):85-98.[doi:10.1109/TCSVT.2013.2276151]
    [27] Adam A, Rivlin E, Shimshoni I, Reinitz D. Robust real-time unusual event detection using multiple fixed-location monitors. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2008,30(3):555-560.[doi:10.1109/TPAMI.2007.70825]
    [28] Roshtkhari MJ, Levine MD. An on-line, real-time learning method for detecting anomalies in videos using spatio-temporal compositions. Computer Vision and Image Understanding, 2013,117(10):1436-1452.[doi:10.1016/j.cviu.2013.06.007]
    [29] Thida M, Eng HL, Remagnino P. Laplacian eigenmap with temporal constraints for local abnormality detection in crowded scenes. IEEE Trans. on Cybernetics, 2013,43(6):2147-2156.[doi:10.1109/TCYB.2013.2242059]
    [30] Loy CC, Xiang T, Gong S. Salient motion detection in crowded scenes. In:Proc. of the 5th IEEE Int'l Symp. on Communications Control and Signal Processing (ISCCSP). 2012. 1-4.[doi:10.1109/ISCCSP.2012.6217836]
    [31] Xiong G, Wu X, Chen Y, Ou Y. Abnormal crowd behavior detection based on the energy model. In:Proc. of the IEEE Int'l Conf. on Information and Automation (ICIA). 2011. 495-500.[doi:10.1109/ICINFA.2011.5949043]
    [32] Sodemann AA, Ross MP, Borghetti BJ. A review of anomaly detection in automated surveillance. IEEE Trans. on Systems, Man, and Cybernetics, Part C:Applications and Reviews, 2012,42(6):1257-1272.[doi:10.1109/TSMCC.2012.2215319]
    [33] Rumelhart DE, Hinton GE, Williams RJ. Learning representations by back-propagating errors. Nature, 1986,323(6088):533-536.
    [34] http://www.svcl.ucsd.edu/projects/anomaly
    [35] Fawcett T. ROC graphs:Notes and practical considerations for researchers. Technical Report, HPL-2003-4, Palo Alto:HP Laboratories, 2003.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

蔡瑞初,谢伟浩,郝志峰,王丽娟,温雯.基于多尺度时间递归神经网络的人群异常检测.软件学报,2015,26(11):2884-2896

复制
分享
文章指标
  • 点击次数:5292
  • 下载次数: 8839
  • HTML阅读次数: 2763
  • 引用次数: 0
历史
  • 收稿日期:2015-05-01
  • 最后修改日期:2015-08-26
  • 在线发布日期: 2015-11-04
文章二维码
友情链接:中国科学院软件研究所中国计算机学会中国科学院国家自然科学基金委员会CCF数字图书馆Int'l J of Softw Info计算机系统应用
您是第20214004位访问者
版权所有：中国科学院软件研究所 京ICP备05046678号-3
地址：北京市海淀区中关村南四街4号,邮政编码：100190
电话：010-62562563 传真：010-62562533 Email：jos@iscas.ac.cn
技术支持：北京勤云科技发展有限公司

京公网安备 11040202500063号