陈威华,张旭,曹黎俊,黄凯奇

• 1:中国科学院自动化研究所模式识别国家重点实验室&智能感知与计算研究中心

摘要(Abstract)：

基于视频分析的人群监控,涉及到获取人群行为和数量,这在智能监控领域具有重要的现实价值。本文建立基于运动特征的群体性行为模型,挖掘复杂人群场景中的群体行为,用于人群行为和数量的分析。群体性行为模型是一种主题模型(LDA),通过样本学习,可以获得描述不同群体行为的特征集,用于人群分析。实验中,将群体性行为模型应用于挖掘监控场景下的不同人群行为及其特征集,并使用人工神经网络完成人数统计,统计正确率达到92.35%。

关键词(KeyWords)： 群体性行为模型;LDA;人群分析;人数统计

Abstract:

Keywords:

基金项目(Foundation): 中国科学院战略性先导科技专项(XDA06030300)资助

作者(Author): 陈威华,张旭,曹黎俊,黄凯奇

参考文献(References)：

• [1]Ihaddadene N,Djeraba C.Real-time crowd motion analysis[C].Tampa,FL,United states,ICPR 2008.19th International Conference on.IEEE,2008:1-4
• [2]Saxena S,Brémond F,Thonnat M,et al.Crowd behavior recognition for video surveillance[C].Juan-les-Pins,France,Advanced Concepts for Intelligent Vision Systems.2008:970-981
• [3]Chan M T,Hoogs A,Schmiederer J,et al.Detecting rare events in video using semantic primitives with HMM[C].Cambridge,United kingdom,ICPR 2004.Proceedings of the 17th International Conference on.IEEE,2004,4:150-154
• [4]Dee H M,Hogg D.Detecting inexplicable behaviour[C].BMVC.2004:1-10
• [5]Hu W,Xiao X,Fu Z,et al.A system for learning statistical motion patterns[J].Pattern Analysis and Machine Intelligence,IEEE Transactions on,2006,28(9):1450-1464
• [6]Johnson N,Hogg D.Learning the distribution of object trajectories for event recognition[J].Image and Vision Computing,1996,14(8):609-615
• [7]Hassner T,Itcher Y,Kliper-Gross O.Violent flows:Real-time detection of violent crowd behavior[C],Providence,RI,United states,Computer Vision and Pattern Recognition Workshops(CVPRW),2012 IEEE Computer Society Conference on.IEEE,2012:1-6
• [8]Hu Y,Zhang Y,Davis L S.Unsupervised Abnormal Crowd Activity Detection Using Semiparametric Scan Statistic[C].Portland,Oregon,Computer Vision and Pattern Recognition Workshops(CVPRW),2013 IEEE Conference on.IEEE,2013:767-774
• [9]Liao H,Xiang J,Sun W,et al.An Abnormal Event Recognition in Crowd Scene[C].Hefei,Anhui,China,Image and Graphics(ICIG),2011 Sixth International Conference on.IEEE,2011:731-736
• [10]Cong Y,Yuan J,Liu J.Sparse reconstruction cost for abnormal event detection[C].Colorado Springs,CO,United states,Computer Vision and Pattern Recognition(CVPR),2011 IEEE Conference on.IEEE,2011:3449-3456
• [11]Kim J,Grauman K.Observe locally,infer globally:a space-time MRF for detecting abnormal activities with incremental updates[C].Miami,FL,United states,Computer Vision and Pattern Recognition,2009.CVPR 2009.IEEE Conference on.IEEE,2009:2921-2928
• [12]Zhao B,Fei-Fei L,Xing E P.Online detection of unusual events in videos via dynamic sparse coding[C].Colorado Springs,CO,United states,Computer Vision and Pattern Recognition(CVPR),2011 IEEE Conference on.IEEE,2011:3313-3320
• [13]Blei D M,Ng A Y,Jordan M I.Latent dirichlet allocation[J].the Journal of machine Learning research,2003,3:993-1022
• [14]Horn B K P,Schunck B G.Determining optical flow[J].Artificial intelligence,1981,17(1):185-203
• [15]Nguyen D,Huynh L,Dinh T B,et al.Video Monitoring System:Counting People by Tracking[C.Ho Chi Minh City,Viet nam,Computing and Communication Technologies,Research,Innovation,and Vision for the Future(RIVF),2012 IEEE RIVF International Conference on.IEEE,2012:1-4
• [16]Chen C C,Lin H H,Chen O T C.Tracking and counting people in visual surveillance systems[C].Prague,Czech republic,Acoustics,Speech and Signal Processing(ICASSP),2011 IEEE International Conference on.IEEE,2011:1425-1428
• [17]Liu X,Tu P H,Rittscher J,et al.Detecting and counting people in surveillance applications[C].Como,Italy,Advanced Video and Signal Based Surveillance,2005.AVSS 2005.IEEE Conference on.IEEE,2005:306-311
• [18]Zhao X,Delleandrea E,Chen L.A people counting system based on face detection and tracking in a video[C].Genova,Italy,Advanced Video and Signal Based Surveillance,2009.AVSS'09.Sixth IEEE International Conference on.IEEE,2009:67-72
• [19]Septian H,Tao J,Tan Y P.People counting by video segmentation and tracking[C].Singapore,Control,Automation,Robotics and Vision,2006.ICARCV'06.9th International Conference on.IEEE,2006:1-4
• [20]Antic B,Letic D,Culibrk D,et al.K-means based segmentation for real-time zenithal people counting[C].Cairo,Egypt,Image Processing(ICIP),2009 16th IEEE International Conference on.IEEE,2009:2565-2568
• [21]Lee K Z,Tsai L W,Hung P C.Fast People Counting Using Sampled Motion Statistics[C].Piraeus-Athens,Greece,Intelligent Information Hiding and Multimedia Signal Processing(IIH-MSP),2012 Eighth International Conference on.IEEE,2012:162-165
• [22]Chen T H,Chen T Y,Chen Z X.An intelligent people-flow counting method for passing through a gate[C].Bangkok,Thailand,Robotics,Automation and Mechatronics,2006 IEEE Conference on.IEEE,2006:1-6
• [23]Hou Y L,Pang G K H.People counting and human detection in a challenging situation[J].Systems,Man and Cybernetics,Part A:Systems and Humans,IEEE Transactions on,2011,41(1):24-33
• [24]Morerio P,Marcenaro L,Regazzoni C S.People Count Estimation In Small Crowds[C].Beijing,China,Advanced Video and Signal-Based Surveillance(AVSS),2012 IEEE Ninth International Conference on.IEEE,2012:476-480
• [25]Conte D,Foggia P,Percannella G,et al.A method for counting people in crowded scenes[C].Boston,MA,United states,Advanced Video and Signal Based Surveillance(AVSS),2010 Seventh IEEE International Conference on.IEEE,2010:225-232
• [26]Kong D,Gray D,Tao H.Counting Pedestrians in Crowds Using Viewpoint Invariant Training[C].BMVC.2005