|本期目录/Table of Contents|

[1]陈冲,白硕,黄丽达,等.基于视频分析的人群密集场所客流监控预警研究[J].中国安全生产科学技术,2020,16(4):143-148.[doi:10.11731/j.issn.1673-193x.2020.04.023]
 CHEN Chong,BAI Shuo,HUANG Lida,et al.Research on monitoring and earlywarning of passenger flow in crowded places based on video analysis[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2020,16(4):143-148.[doi:10.11731/j.issn.1673-193x.2020.04.023]
点击复制

基于视频分析的人群密集场所客流监控预警研究
分享到:

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
16
期数:
2020年4期
页码:
143-148
栏目:
职业安全卫生管理与技术
出版日期:
2020-04-30

文章信息/Info

Title:
Research on monitoring and earlywarning of passenger flow in crowded places based on video analysis
文章编号:
1673-193X(2020)-04-0143-06
作者:
陈冲白硕黄丽达王晓萌刘春慧
(1.清华大学 工程物理系,北京 100084;
2.北京辰安科技股份有限公司,北京 100085)
Author(s):
CHEN Chong BAI Shuo HUANG Lida WANG Xiaomeng LIU Chunhui
(1.Department of Engineering Physics,Tsinghua University,Beijing 100084,China;
2.Beijing Global Safety Technology Inc.,Beijing 100085,China)
关键词:
人群密集场所人群计数人群密度异常行为监控预警
Keywords:
crowded places crowd counting crowd density abnormal behavior monitoring and earlywarning
分类号:
X913
DOI:
10.11731/j.issn.1673-193x.2020.04.023
文献标志码:
A
摘要:
为实现人群密集场所客流安全隐患早发现,辅助管理人员早决策,人群聚集风险区早疏散,提升对灾难的预见性和主动性。在国内外人群异常聚集监测预警现状分析基础上,对比分析得出监控视频分析技术是解决人群密集场所精准预警难题较为理想的解决方案;构建以视频智能分析的人群计数、密度估计、行人追踪、活动烈度识别为核心技术的人群密集场所风险预警技术框架;将该技术框架应用到某大型商圈的商业街区,获得监控区域内的人群总数、密度分布、行人轨迹和异常活动等特征。结果表明:提出的基于视频分析的人群密集场所风险预警技术框架可为城市大型商圈、交通枢纽、大型活动场所等城市公共场所的安全管理提供参考和借鉴。
Abstract:
In order to realize the detection on the potential safety hazard of passenger flow in the crowded places early,assist the managers to make decision early,evacuate the crowd in the gathering risk area early,and improve the foresight and initiative on the disasters,based on the analysis on the current situation of monitoring and earlywarning on the abnormal gathering of crowd at home and abroad,it was concluded that the analysis technology of monitoring video was the more ideal solution to solve the problem of accurate earlywarning in the crowded places through the comparative analysis.A technical framework of risk earlywarning for the crowded places was constructed,which took the crowd counting,density estimation,pedestrian tracking and activity intensity recognition as the core technologies,and it was applied in the commercial block of a large business district,then the characteristics of the total number of people,density distribution,pedestrian trajectory and abnormal activities in the monitored area were obtained.The results showed that the technical framework of risk earlywarning for the crowded places based on the video analysis can provide reference for the safety management of urban public places such as large commercial districts,transportation hubs and large event venues.

参考文献/References:

[1]王振.城市公共场所人群聚集风险理论及应用研究[D].天津:南开大学,2007.
[2]张青松,刘金兰,赵国敏.大型公共场所人群拥挤踩踏事故机理初探[J].自然灾害学报,2009,18(6):81-86. ZHANG Qingsong,LIU Jinlan,ZHAO Guomin.Discussion on cause mechanism of crowd crushing and trampling accident in large-scale public places [J].Journal of Natural Disasters,2009,18(6):81-86.
[3]王起全,李鹏昇.基于大数据的大型活动拥挤踩踏事故预警分析研究[J].中国安全生产科学技术,2017,13(12):58-66. WANG Qiquan,LI Pengsheng.Research on early warning analysis of crowded stampede accident in large-scale activity based on big data[J].Journal of Safety Science and Technology,2017,13(12):58-66.
[4]卢文刚,黄小珍.城市地铁踩踏事件应急管理研究——基于2008—2017年典型案例的分析[J].中国应急救援,2017(4):4-9. LU Wengang,HUANG Xiaozhen.Study on emergency management of urban subway stampede:based on the analysis of typical cases in 2008—2017[J].China Emergency Rescue,2017(4):4-9.
[5]尹晓庆,叶厚元.大型活动拥挤踩踏事件的事故树分析及其防控措施[J].安全与环境工程,2017,24(2):126-131. YIN Xiaoqing,YE Houyuan.Fault tree analysis of stampede accidents in large-scale activities and the prevention and control measures[J].Safety and Environmental Engineering,2017,24(2):126-131.
[6]王瑜,代宝乾.人员密集公共场所大客流预测预警[J].现代职业安全,2016(3):112-113. WANG Yu,DAI Baoqian.Prediction and early warning of large passenger flow in densely populated public places[J].Modern Occupational Safety,2016(3):112-113.
[7]HELBING D,FARKAS I,VICSEK T.Simulating dynamical features of escape panic[J].Nature,2000,407(6803):487-490.
[8]曾茂桃.人群密度分析对踩踏事件的预警作用[J].现代交际,2018(20):63-64. ZENG Maotao.Early warning effect of crowd density analysis on stampede[J].Modern Communication,2018(20):63-64.
[9]HUANG L,CHEN T,WANG Y,et al.Congestion detection of pedestrians using the velocity entropy:a case study of Love Parade 2010 disaster[J].Physica A:Statistical Mechanics and its Applications,2015,440:200-209.
[10]周京京,刘栋栋.人员密集风险监测及预警机制研究—以2016年北京地坛庙会为例[C]//第九届全国防震减灾工程学术研讨会.合肥:中国土木工程学会,2016:160-168.
[11]姚远,孙杨世佳.基于手机大数据的大型场馆不同功能区客流特征及预警研究[J].科技视界,2017(30):27-28.
[12]姚远.基于手机数据的客流分析展示系统研究[J].科技视界,2017(30):34-50.
[13]张昕,胡金星,尹凌,等.基于实时数据的交通枢纽客流态势研究[C]//第七届中国智能交通年会.北京:中国智能交通协会,2012:253-260.
[14]陈冬萍.人员密集公共场所大客流预测预警浅议[J].电脑知识与技术,2018,14(7):190-191. CHEN Dongping.On the prediction and early warning of large passenger flow in densely populated public places[J].Computer Knowledge and Technology,2018,14(7):190-191.
[15]倪慧荟,姚晓晖.人群聚集风险预警系统构建研究——以西单商业区为例[J].科技促进发展,2014(4):110-115. NI Huihui,YAO Xiaohui.Building an overcrowding forecast system:a case study of xidan district[J].Science & Technology for Development,2014(4):110-115.
[16]宁利君.人员密集场所人群聚集风险监测与预警系统研究[J].安全,2013,34(11):59-60. NING Lijun.Study on the risk monitoring and early warning system of crowd gathering in densely populated places[J].Safety,2013,34(11):59-60.
[17]史聪灵,钟茂华.人员密集场所客流监控预警系统[J].劳动保护,2015(2):112-113. SHI Congling,ZHONG Maohua.Passenger flow monitoring and early warning system in densely populated places[J].Labor Protection,2015(2):112-113.
[18]蔡牧夫.开放型公共场所踩踏事件人群密度分析与风险预警研究及应用[D].广州:暨南大学,2017.
[19]魏永超,庄夏,傅强.人群异常识别技术研究进展[J].计算机系统应用,2016,25(9):10-16. WEI Yongchao,ZHUANG Xia,FU Qiang.Research progress on the crowd abnormal recognition technology[J].Computer Systems & Applications,2016,25(9):10-16.
[20]ZHANG C,KANG K,LI H,et al.Data-driven crowd understanding:a baseline for a largescale crowd dataset[J].IEEE Transactions on Multimedia,2016,18(6):1048-1061.
[21]WANG Q,WAN J,YUAN Y.Deep metric learning for crowdedness regression[J].IEEE Transactions on Circuits and Systems for Video Technology,2018,28(10):2633-2643.
[22]WANG Q,GAO J,LIN W,et al.Learning from synthetic data for crowd counting in the wild[C]//2019 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).California:IEEE,2019:18-20.
[23]HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C] //2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Nevada:IEEE,2016:27-30.
[24]WOJKE N,BEWLEY A,PAULUS D,et al.Simple online and real-time tracking with a deep association metric[C] //2017 International Conference on Image Processing.Beijing:IEEE,2017:17-20.
[25]MEHRAN R,OYAMA A,SHAH M,et al.Abnormal crowd behavior detection using social force model[C] //2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).florida:IEEE,2009:20-25.
[26]HELBING D,MOLNAR P.Social force model for pedestrian dynamics[J].Physical Review E Statistical Physics Plasmas Fluids and Related Interdisciplinary Topics,1998,51(5):4282.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期: 2019-10-25
* 基金项目: 北京市科委项目(Z181100009018010);中国博士后科学基金项目( 2019M660661 )
作者简介: 陈冲,博士,助理研究员,主要研究方向为灾害监测预警。
更新日期/Last Update: 2020-05-11