Please wait a minute...
浙江大学学报(工学版)
浙江大学学报(工学版)  2018, Vol. 52 Issue (4): 649-656    DOI: 10.3785/j.issn.1008-973X.2018.04.006
自动化技术     
结合背景差分与光流法的人群状态突变检测
高鹏辉, 赵武峰, 沈继忠
浙江大学 信息与电子工程学院, 浙江 杭州 310027
Detection of crowd state mutation based onbackground difference algorithm and optical flow algorithm
GAO Peng-hui, ZHAO Wu-feng, SHEN Ji-zhong
College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China
 全文: PDF(4875 KB)   HTML
摘要：

针对群体性异常事件中人群状态突变场景发生时的运动特征，提出结合背景差分和光流法的检测算法.对图像背景差分提取前景寻找特征点，利用光流法预测特征点位置，将特征点以光流运动方向为依据划分后处理数据，得到累积加速度进行判断.该算法弥补了单独使用背景差分算法检测准确率低和单独使用光流法检测效率低的缺陷，通过将特征点以光流运动方向划分处理数据，大幅度提高了检测的准确性和稳定性.经过实验测试，结果表明，该算法在人群状态突变异常事件检测中有较高的准确性，能够满足实时性要求，较同类检测算法在综合性能上有显著提高.
Abstract:

A detection algorithm based on background difference algorithm and optical flow algorithm was proposed in terms of the motion characteristics of crowd state mutation events. The background difference algorithm was used to extract the foreground and find the feature points. Then the optical flow algorithm was employed to predict the positions of the feature points. The feature points were divided into several parts based on the direction of the light flow, and the cumulative acceleration was calculated to determine whether group abnormal events have occurred or not. The proposed method makes up for the deficiencies of low detection accuracy using background difference algorithm and low detection efficiency using optical flow algorithm separately. The accuracy and stability of the detection was enhanced to a great extent by dividing the feature points by the light flow direction. The experimental results show that the algorithm has high accuracy in the detection of crowd state mutation events and can meet the requirements of real-time. The algorithm has a great improvement in comprehensive performance compared with other similar detection algorithms.
收稿日期: 2017-01-17
CLC:  TP391  
基金资助:

国家自然科学基金资助项目（61471314）.
通讯作者: 沈继忠,男,教授.orcid.org/0000-0002-9031-2379.     E-mail: jzshen@zju.edu.cn
作者简介: 高鹏辉(1991-),男,硕士生,从事视频检测与信息管理系统研究.orcid.org/0000-0001-8292-0502.E-mail:21431030@zju.edu.cn
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章　　

引用本文:

高鹏辉, 赵武峰, 沈继忠. 结合背景差分与光流法的人群状态突变检测[J]. 浙江大学学报(工学版), 2018, 52(4): 649-656.

GAO Peng-hui, ZHAO Wu-feng, SHEN Ji-zhong. Detection of crowd state mutation based onbackground difference algorithm and optical flow algorithm. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2018, 52(4): 649-656.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2018.04.006    或    http://www.zjujournals.com/eng/CN/Y2018/V52/I4/649

[1] 丁荣.网络视频监控系统的构建[D].上海:上海交通大学,2007. DING Rong. Construction of internet video monitoring system[D]. Shanghai:Shanghai Jiao Tong University, 2007.
[2] 饶彦.幼儿园智能视频监控系统探究[J].计算机光盘软件与应用,2013(13):217-218. RAO Yan. Research on intelligent video surveillance system in kindergarten[J]. Computer CD Software and Applications, 2013(13):217-218.
[3] 孙静.校园网视频监控安全系统[D].天津:天津大学, 2012. SUN Jing. Campus network video surveillance security system[D]. Tianjin:Tianjin University, 2012.
[4] CUI W, CHEN Y, SUN C, et al. Design and imple-mentation of embedded video monitoring system based on Tiny210[C]//IEEE 11th World Congress on Intelligent Control and Automation. Shenyang:IEEE, 2014:4651-4656.
[5] BABAGUCHI N, CAVALLARO A, CHELLAPPA R, et al. Guest editorial:special issue on intelligent video surveillance for public security and personal privacy[J]. IEEE Transactions on Information Forensics and Security, 2013, 8(10):1559-1561.
[6] WANG Z, OUYANG N, HAN C. Unusual event detection without tracking[C]//2009 International Conference on Computational Intelligence and Software Engineering, Wuhan:IEEE, 2009:1-3.
[7] WU X. Design of person flow counting and monitoring system based on feature point extraction of optical flow[C]//IEEE 5th International Conference on Intelligent Systems Design and Engineering Applications. Hunan:IEEE, 2014:376-380.
[8] 何传阳,王平,张晓华,等.基于智能监控的中小人群异常行为检测[J].计算机应用,2016,36(6):1724-1729. HE Chuan-yang, WANG Ping, ZHANG Xiao-hua, et al. Abnormal behavior detection of small and medium crowd based on intelligent video surveillance[J]. Journal of Computer Applications, 2016, 36(6):1724-1729.
[9] 曹艺华.面向视频监控的大尺度人群行为分析[D].上海:上海交通大学,2013. CAO Yi-hua. The large-scale crowd analysis in video surveillance[D]. Shanghai:Shanghai Jiao Tong Uni-versity, 2013.
[10] 林沁.视频中的大规模人群密度与异常行为分析[D].厦门:厦门大学,2014. LIN Qin. Crowd density and abnormal behavior analy-sis of video[D]. Xiamen:Xiamen University, 2014.
[11] 王乔.运动人体的异常行为检测研究[D].成都:电子科技大学,2012. WANG Qiao. Study on abnormal behavior detection of moving people[D]. Chengdu:University of Electronic Science and Technology of China, 2012.
[12] WANG J, XU Z. Spatio-temporal texture modelling for real-time crowd anomaly detection[J]. Computer Vision and Image Understanding, 2016, 144(C):177-187.
[13] KALTSA V, BRIASSOULI A, KOMPATSIARIS I, et al. Swarm intelligence for detecting interesting events in crowded environments[J]. IEEE Transactions on Image Processing, 2015, 24(7):2153-2166.
[14] 彭怀亮.视频监控场景中人群异常行为识别研究[D].杭州:中国计量学院,2014. PENG Huai-liang. Research on crowd abnormal behaviors recognition in video surveillance scene[D]. Hangzhou:China Jiliang University, 2014.
[15] 柴斌.突发人群聚集事件智能视频监控[D].成都:电子科技大学,2010. CHAI Bin. Intelligent video surveillance of Burst crowd gathering event[D]. Chengdu:University of Electronic Science and Technology of China, 2010.
[16] MARSDEN M, MCGUINNESS K, LITTLE S, et al. Holistic features for real-time crowd behaviour anomaly detection[C]//IEEE International Conference on Image Processing. Phoenix:IEEE, 2016:918-922.
[17] 杨世淼.基于Web Server和Android平台的智能幼儿园管理系统[D].杭州:浙江大学,2016. YANG Shi-miao. Intelligent management system for kindergarten based on the web server and android[D]. Hangzhou:Zhejiang University, 2016.
[18] ROJAS O E, TOZZI C L. Abnormal crowd behavior detection based on Gaussian mixture model[C]//Computer Vision-ECCV 2016 Workshops. Amsterdam:[s.n.], 2016:668-675.
[19] 杜晶晶.智能视频监控中运动目标检测与跟踪算法研究[D].成都:西南交通大学,2009. DU Jing-jing. Research on detection and tracking of moving object in intelligent video surveillance system[D]. Chengdu:Southwest Jiaotong University,2009.
[20] LAGANIERE R.OpenCV 2计算机视觉编程手册[M].张静,译. 北京:科学出版社,2013:46-71.
[21] BRAGA-NETO U, GOUTSIAS J. Object-based image analysis using multiscale connectivity[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(6):892-907.
[22] HERRERO E, ORRITE C, SENAR J. Detected motion classifycation with a double background and a neighborhood based difference[J]. Pattern Recognition Letters, 2003, 24(12):2079-2092.
[23] CUCCHIARA R, PICCARDI M, PRATI A. Detecting moving objects, ghosts, and shadows in video streams[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(10):1337-1342.
[24] 王永忠,梁彦,潘泉,等.基于自适应混合高斯模型的时空背景建模[J].自动化学报, 2009, 35(4):371-378. WANG Yong-zhong, LIANG Yan, PAN Quan, et al. Spatio temporal background modeling based on adaptive mixture of Gaussians[J]. Acta Automatica Sinica, 2009, 35(4):371-378.
[25] COLLINS R T, LIPTON A J, KANADE T, et al. A system for video surveillance and monitoring[C]//International Conference on Automated Deduction. Pittsburgh:[s. n.], 2000:497-501.
[26] SONKA M, HLAVAC V, BOYLE R.图象处理分析与机器视觉[M]. 艾海舟,武勃,等,译. 2版.北京:人民邮电出版社,2003:469-491.
[27] BEAUCHEMIN S S, BARRON J L. The computation of optical flow[J]. ACM Computing Surveys (CSUR), 1995, 27(3):433-466.
[28] VIDAL R, RAVICHANDRAN A. Optical flow estimation and segmentation of multiple moving dynamic textures[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition.San Diego:IEEE, 2005:516-521.
[29] MOCHIZUKI Y, KAMEDA Y, IMIYA A, et al. Variational method for super-resolution optical flow[J]. Signal Processing, 2011, 91(7):1535-1567.
[30] SáNCHEZ A, RUIZ J V, MORENO A S, et al. Differential optical flow applied to automatic facial expression recognition[J]. Neurocomputing, 2011, 74(8):1272-1282.
[31] 裴巧娜.基于光流法的运动目标检测与跟踪技术[D]. 北京:北方工业大学,2009. PEI Qiao-na. Moving objects detection and tracking techniques based optical flow[D]. Beijing:North China University of Technology, 2009.
[32] HORN B, SCHUNCH B. Determining optical flow[J]. Artificial Intelligence, 1981, 17(1-3):185-203.
[33] LUCAS B, KANADE T. An iterative image registration technique with an application to stereo vision[C]//Image Understanding Proceedings of a Workshop. Washington:[s. n.], 1981:121-130.
[34] CAVIAR test case scenarios[DB/OL].[2017-01-13].http://homepages.inf.ed.ac.uk/rbf/CAVIARDATA1/.
[35] Unusual crowd activity dataset[DB/OL].[2017-01-13]. http://mha.cs.umn.edu/proj_events.shtml.
[36] 视频监控格式[EB/OL].[2017-01-13]. https://zhidao.baidu.com/ques-tion/558546721.html. The format of video surveillance[EB/OL].[2017-01-13].https://zhi-dao.baidu.com/question/558546721.html.
[37] HANLEY J A, MCNEIL B J. The meaning and use of the area under a receiver operating characteristic (ROC) curve[J]. Radiology, 1982, 143(1):29-36.
[38] FAWCETT T. An introduction to ROC analysis[J]. Pattern Recognition Letters, 2006, 27(8):861-874.
[1] 韩勇, 宁连举, 郑小林, 林炜华, 孙中原. 基于社交信息和物品曝光度的矩阵分解推荐[J]. 浙江大学学报(工学版), 2019, 53(1): 89-98.
[2] 郑洲, 张学昌, 郑四鸣, 施岳定. 基于区域增长与统一化水平集的CT肝脏图像分割[J]. 浙江大学学报(工学版), 2018, 52(12): 2382-2396.
[3] 赵丽科, 郑顺义, 王晓南, 黄霞. 单目序列的刚体目标位姿测量[J]. 浙江大学学报(工学版), 2018, 52(12): 2372-2381.
[4] 何杰光, 彭志平, 崔得龙, 李启锐. 局部维度改进的教与学优化算法[J]. 浙江大学学报(工学版), 2018, 52(11): 2159-2170.
[5] 李志, 单洪, 马涛, 黄郡. 基于反向标签传播的移动终端用户群体发现[J]. 浙江大学学报(工学版), 2018, 52(11): 2171-2179.
[6] 王硕朋, 杨鹏, 孙昊. 听觉定位数据库构建过程优化[J]. 浙江大学学报(工学版), 2018, 52(10): 1973-1979.
[7] 魏小峰, 程承旗, 陈波, 王海岩. 基于独立边数的链码方法[J]. 浙江大学学报(工学版), 2018, 52(9): 1686-1693.
[8] 陈荣华, 王鹰汉, 卜佳俊, 于智, 高斐. 基于KNN算法与局部回归的网站无障碍采样评估[J]. 浙江大学学报(工学版), 2018, 52(9): 1702-1708.
[9] 张承志, 冯华君, 徐之海, 李奇, 陈跃庭. 图像噪声方差分段估计法[J]. 浙江大学学报(工学版), 2018, 52(9): 1804-1810.
[10] 刘洲洲, 李士宁, 李彬, 王皓, 张倩昀, 郑然. 基于弹性碰撞优化算法的传感云资源调度[J]. 浙江大学学报(工学版), 2018, 52(8): 1431-1443.
[11] 王勇超, 祝凯林, 吴奇轩, 鲁东明. 基于局部渲染的高精度模型自适应展示技术[J]. 浙江大学学报(工学版), 2018, 52(8): 1461-1466.
[12] 孙念, 李玉强, 刘爱华, 刘春, 黎威威. 基于松散条件下协同学习的中文微博情感分析[J]. 浙江大学学报(工学版), 2018, 52(8): 1452-1460.
[13] 郑守国, 崔雁民, 王青, 杨飞, 程亮. 飞机装配现场数据采集平台设计[J]. 浙江大学学报(工学版), 2018, 52(8): 1526-1534.
[14] 毕晓君, 王朝. 基于超平面投影的高维多目标进化算法[J]. 浙江大学学报(工学版), 2018, 52(7): 1284-1293.
[15] 张廷蓉, 滕奇志, 李征骥, 卿粼波, 何小海. 岩心三维CT图像超分辨率重建[J]. 浙江大学学报(工学版), 2018, 52(7): 1294-1301.