基于视频数据的公共场所行人应急疏散建模与仿真优化

doi:10.16381/j.cnki.issn1003-207x.2024.0668

摘要/Abstract

摘要：

本文面向公共场所内的行人安全，提出一个基于视频数据的公共场所行人应急疏散建模与仿真优化框架。构建行人疏散的仿真模型，包括行人运动路线决策模型和行人微观运动模型；建立行人疏散仿真系统；提出面向行人快速疏散的仿真优化算法，以此确定此类场所中各类元素的最优设置方案。在案例分析中，通过收集和分析地震时华中农业大学图书馆内大量监控视频数据，运用所提出的框架建立该场景下的行人疏散模型及仿真系统，考虑不同疏散人数、是否使用电梯以及低能见度等多种情境，运用仿真优化算法分析得到了不同情境下楼梯、电梯、闸机如何开放以及阅览室出入口如何设置等结论。本文主要创新之处主要在于：将视频数据分析、行人运动建模和仿真优化相结合，提出一套具有普适性的、面向行人快速疏散的公共场所元素优化设置的完整解决方案。

关键词: 公共场所, 行人安全, 疏散, 视频数据, 仿真优化

Abstract:

On the background of the national improvement of public safety governance， a comprehensive framework is proposed for modeling and optimizing pedestrian emergency evacuation in public spaces based on video data. The framework utilizes real video data from specific public place and scenarios to construct pedestrian evacuation simulation models， comprising both route decision models and microscopic movement models. By establishing a pedestrian evacuation simulation system and developing optimization algorithms focused on rapid evacuation， the framework determines optimal configurations for various facility elements. In the case study， extensive surveillance video data from the Huazhong Agricultural University library during an earthquake is collected and analyzed. Using the proposed framework， pedestrian evacuation models and simulation systems is developed for this specific scenario. Considering multiple situations including different number of pedestrians， elevator availability， and power outage with low visibility conditions， the simulation optimization algorithms is used to analyze the simulation results， and the conclusions on how to open the stairs， elevators， gate machines and how to set the entrances and exits of the reading room in different situations are obtained. The main contribution of this paper lies in proposing a universally applicable and comprehensive solution for optimizing public place elements to facilitate rapid pedestrian evacuation. By integrating video data analysis， pedestrian movement modeling， and simulation optimization， this framework provides a scientific basis for decision-making in public safety management.

Key words: public place, pedestrian safety, evacuation, video data, simulation optimization

中图分类号:

C931

刘嘉,阮伟乔,张新缘, 等. 基于视频数据的公共场所行人应急疏散建模与仿真优化[J]. 中国管理科学, 2026, 34(7): 249-263.

Jia Liu,Weiqiao Ruan,Xinyuan Zhang, et al. Modeling and Simulation Optimization of Emergency Evacuation of Pedestrians in Public Places Based on Video Data[J]. Chinese Journal of Management Science, 2026, 34(7): 249-263.

图/表 11

图1

图2

图3

表1

从视频数据中提取的结构化数据"

行人	所选出口	出口1各因素值	…	出口m各因素值
行人1	$T 1$	$x 11 1, x 11 2, …, x 11 p$	$⋯$	$x m 1 1, x m 1 2, …, x m 1 p$
行人2	$T 2$	$x 12 1, x 12 2, …, x 12 p$	$⋯$	$x m 2 1, x m 2 2, …, x m 2 p$
…	…	…	…	…
行人n	$T n$	$x 1 n 1, x 1 n 2, …, x 1 n p$	$⋯$	$x m n 1, x m n 2, …, x m n p$

表1

图4

图5

表2

各因素回归分析"

变量	精准率	召回率	F1值
$x s i 1$	0.62	0.25	0.36
$x s i 2$	0.38	0.12	0.18
$x s i 4$	0.18	0.09	0.12
$x s i 3$	0.11	0.10	0.10

表2

表3

逐步逻辑回归过程"

模型考虑的因素		参数 $ω$ 取值	精准率	召回率	F1值	AUC
1	$x s i 1$	-4.5	0.62	0.25	0.36	0.58
2	$x s i 1$	-5	0.71	0.38	0.48	0.76
2	$x s i 2$	-2.3	0.71	0.38	0.48	0.76
3	$x s i 1$	-5	0.78	0.49	0.60	0.81
	$x s i 2$	-2.2
	$x s i 4$	0.15
4	$x s i 1$	-4.7	0.69	0.31	0.42	0.67
	$x s i 2$	-2.2
	$x s i 4$	0.15
	$x s i 3$	0.01

表3

表4

微观运动模型参数"

参数	取值	T统计量	Sig	P值	F值
$P 1$	15.74	15.21	0.048	0.046	20.36
$P 2$	1.85	4.11	0.044
$P 3$	$0.62 × 103$	1.52	0.022
$P 4$	0.06	7.48	0.051
$P 5$	$2.14 × 105$	6.83	0.077

表4

图6

图7

参考文献 62

[1]	Wright L G， Onodera T， Stein M M， et al. Deep physical neural networks trained with backpropagation［J］. Nature， 2022， 601（7894）： 549-555.
[2]	张江华，刘治平，朱道立. 多源点突发灾害事故应急疏散模型与算法［J］. 管理科学学报， 2009， 12（3）： 111-118.
	Zhang J H， Liu Z P， Zhu D L. Multi-source emergency evacuation model and algorithm［J］. Journal of Management Sciences in China， 2009， 12（3）： 111-118.
[3]	Xiao Y， Gao Z Y， Qu Y C， et al. A pedestrian flow model considering the impact of local density： Voronoi diagram based heuristics approach［J］. Transportation Research Part C： Emerging Technologies， 2016， 68： 566-580.
[4]	Tong Y H， Bode N W F. The value pedestrians attribute to environmental information diminishes in route choice sequences［J］. Transportation Research Part C： Emerging Technologies， 2021， 124： 102909.
[5]	Helbing D， Molnár P. Social force model for pedestrian dynamics［J］. Physical Review E， 1995， 51（5）： 4282-4286.
[6]	Helbing D， Farkas I， Vicsek T. Simulating dynamical features of escape panic［J］. Nature， 2000， 407（6803）： 487-490.
[7]	Burstedde C， Klauck K， Schadschneider A， et al. Simulation of pedestrian dynamics using a two-dimensional cellular automaton［J］. Physica A： Statistical Mechanics and Its Applications， 2001， 295（3-4）： 507-525.
[8]	Dutra T B， Marques R， Cavalcante-Neto J B， et al. Gradient-based steering for vision-based crowd simulation algorithms［J］. Computer Graphics Forum， 2017， 36（2）： 337-348.
[9]	Huo F Z， Song W G， Chen L， et al. Experimental study on characteristics of pedestrian evacuation on stairs in a high-rise building［J］. Safety Science， 2016， 86： 165-173.
[10]	Pelechano N， Malkawi A. Evacuation simulation models： Challenges in modeling high rise building evacuation with cellular automata approaches［J］. Automation in Construction， 2008， 17（4）： 377-385.
[11]	Zhang L M， Liu M J， Wu X G， et al. Simulation-based route planning for pedestrian evacuation in metro stations： A case study［J］. Automation in Construction， 2016， 71： 430-442.
[12]	Poulos A， Tocornal F， de la Llera J C， et al. Validation of an agent-based building evacuation model with a school drill［J］. Transportation Research Part C： Emerging Technologies， 2018， 97： 82-95.
[13]	Zhang H， Liu H， Qin X， et al. Modified two-layer social force model for emergency earthquake evacuation［J］. Physica A： Statistical Mechanics and Its Applications， 2018， 492： 1107-1119.
[14]	Shahhoseini Z， Sarvi M. Pedestrian crowd flows in shared spaces： Investigating the impact of geometry based on micro and macro scale measures［J］. Transportation Research Part B： Methodological， 2019， 122： 57-87.
[15]	Qu Y C， Gao Z Y， Xiao Y， et al. Modeling the pedestrian’s movement and simulating evacuation dynamics on stairs［J］. Safety Science， 2014， 70： 189-201.
[16]	Guo N， Hao Q Y， Jiang R， et al. Uni- and bi-directional pedestrian flow in the view-limited condition： Experiments and modeling［J］. Transportation Research Part C： Emerging Technologies， 2016， 71： 63-85.
[17]	Guo R Y， Huang H J， Wong S C. Route choice in pedestrian evacuation under conditions of good and zero visibility： Experimental and simulation results［J］. Transportation Research Part B： Methodological， 2012， 46（6）： 669-686.
[18]	Liu J， Chen Y， Chen Y. Emergency and disaster management-crowd evacuation research［J］. Journal of Industrial Information Integration， 2021， 21： 100191.
[19]	Li H L， Zhang J， Xia L， et al. Comparing the route-choice behavior of pedestrians around obstacles in a virtual experiment and a field study［J］. Transportation Research Part C： Emerging Technologies， 2019， 107： 120-136.
[20]	Yu B. Consideration of tactical decisions in microscopic pedestrian simulation： Algorithm and experiments［J］. Transportation Research Part C： Emerging Technologies， 2020， 119： 102742.
[21]	Feliciani C， Murakami H， Shimura K， et al. Efficiently informing crowds-Experiments and simulations on route choice and decision making in pedestrian crowds with wheelchair users［J］. Transportation Research Part C： Emerging Technologies， 2020， 114： 484-503.
[22]	Kurdi H， Almulifi A， Al-Megren S， et al. A balanced evacuation algorithm for facilities with multiple exits［J］. European Journal of Operational Research， 2021， 289（1）： 285-296.
[23]	Kurdi H A， Al-Megren S， Althunyan R， et al. Effect of exit placement on evacuation plans［J］. European Journal of Operational Research， 2018， 269（2）： 749-759.
[24]	Lopez-Carmona M A， Paricio Garcia A. Adaptive cell-based evacuation systems for leader-follower crowd evacuation［J］. Transportation Research Part C： Emerging Technologies， 2022， 140： 103699.
[25]	Li S Y， Zhuang J， Shen S F. A three-stage evacuation decision-making and behavior model for the onset of an attack［J］. Transportation Research Part C： Emerging Technologies， 2017， 79： 119-135.
[26]	吴丽君，霍非舟，张钦钦，等. 多出口场景下考虑危险信息传播的人员疏散模拟研究［J］. 系统工程理论与实践， 2023， 43（3）： 929-940.
	Wu L J， Huo F Z， Zhang Q Q， et al. Simulation study on evacuation considering hazard information transmission in multi-exit scenario［J］. Systems Engineering —Theory & Practice， 2023， 43（3）： 929-940.
[27]	马剑，王翔，肖修昆. 基于有限理性路径决策的人员疏散双层模型［J］. 系统工程理论与实践， 2020， 40（10）： 2698-2706.
	Ma J， Wang X， Xiao X K. Bi-level evacuation modeling considering boundedly rational route choice behavior［J］. Systems Engineering —Theory & Practice， 2020， 40（10）： 2698-2706.
[28]	Tan L， Hu M， Lin H. Agent-based simulation of building evacuation： Combining human behavior with predictable spatial accessibility in a fire emergency［J］. Information Sciences， 2015， 295： 53-66.
[29]	Wang W L， Lo S M， Liu S B， et al. Microscopic modeling of pedestrian movement behavior： Interacting with visual attractors in the environment［J］. Transportation Research Part C： Emerging Technologies， 2014， 44： 21-33.
[30]	陈国青，吴刚，顾远东，等. 管理决策情境下大数据驱动的研究和应用挑战——范式转变与研究方向［J］. 管理科学学报， 2018， 21（7）： 1-10.
	Chen G Q， Wu G， Gu Y D， et al. The challenges for big data driven research and applications in the context of managerial decision-making： Paradigm shift and research directions［J］. Journal of Management Sciences in China， 2018， 21（7）： 1-10.
[31]	Liu J， Chen X. Simulation of passenger motion in metro stations during rush hours based on video analysis［J］. Automation in Construction， 2019， 107： 102938.
[32]	Bernardini G， Quagliarini E， D’Orazio M. Towards creating a combined database for earthquake pedestrians’ evacuation models［J］. Safety Science， 2016， 82： 77-94.
[33]	Haghani M， Sarvi M， Shahhoseini Z， et al. Dynamics of social groups’ decision-making in evacuations［J］. Transportation Research Part C： Emerging Technologies， 2019， 104： 135-157.
[34]	Haghani M， Sarvi M. Simulating dynamics of adaptive exit-choice changing in crowd evacuations： Model implementation and behavioural interpretations［J］. Transportation Research Part C： Emerging Technologies， 2019， 103： 56-82.
[35]	Bera A， Kim S， Manocha D. Efficient trajectory extraction and parameter learning for data-driven crowd simulation［C］// Proceedings of the 41st Graphics Interface Conference， Halifax， Nova Scotia， Canada，June 3-5， Canadian Information Processing Society， 2015： 65-72.
[36]	Kleijnen J P C. Factor screening in simulation experiments： Review of sequential bifurcation［M］//Alexopoulos C， Goldsman D， Wilson J R， Advancing the Frontiers of Simulation： A Festschrift in Honor of George Samuel Fishman， Boston， MA： Springer US，2009： 153-167.
[37]	Campolongo F， Cariboni J， Saltelli A. An effective screening design for sensitivity analysis of large models［J］. Environmental Modelling & Software， 2007， 22（10）： 1509-1518.
[38]	Borgonovo E， Plischke E. Sensitivity analysis： A review of recent advances［J］. European Journal of Operational Research， 2016， 248（3）： 869-887.
[39]	Bettonvil B， Kleijnen J P C. Searching for important factors in simulation models with many factors： Sequential bifurcation［J］. European Journal of Operational Research， 1997， 96（1）： 180-194.
[40]	Morris M D. Factorial sampling plans for preliminary computational experiments［J］. Technometrics， 1991， 33（2）： 161-174.
[41]	Cheng R C H. Searching for important factors： Sequential bifurcation under uncertainty［C］//Proceedings of the 29th Conference on Winter Simulation，Atlanta Georgia，USA，Dec 7-10，ACM， 1997： 275-280.
[42]	Shen H， Wan H. Controlled sequential factorial design for simulation factor screening［J］. European Journal of Operational Research， 2009， 198（2）： 511-519.
[43]	Shi W， Shang J， Liu Z， et al. Optimal design of the auto parts supply chain for JIT operations： Sequential bifurcation factor screening and multi-response surface methodology［J］. European Journal of Operational Research， 2014， 236（2）： 664-676.
[44]	Lucay F A， Sales-Cruz M， Gálvez E D， et al. Modeling of the complex behavior through an improved response surface methodology［J］. Mineral Processing and Extractive Metallurgy Review， 2021， 42（5）： 285-311.
[45]	Chen X W， Jia Y P， Tong X Q， et al. Research on pedestrian detection and DeepSort tracking in front of intelligent vehicle based on deep learning［J］. Sustainability， 2022， 14（15）： 9281.
[46]	Gai Y， He W， Zhou Z. Pedestrian target tracking based on DeepSORT with YOLOv5［C］//2021 2nd International Conference on Computer Engineering and Intelligent Control （ICCEIC）. November 12-14， 2021， Chongqing， China. IEEE， 2021： 1-5.
[47]	Wojke N， Bewley A， Paulus D. Simple online and realtime tracking with a deep association metric［C］//Proceedings of 2017 IEEE International Conference on Image Processing （ICIP）， Beijing， China， September 17-20， IEEE， 2017： 3645-3649.
[48]	Abdel-Aziz Y I， Karara H M. Direct linear transformation from comparator coordinates into object space coordinates in close-range photogrammetry［J］. Photogrammetric Engineering & Remote Sensing， 2015， 81（2）： 103-107.
[49]	Haghani M， Sarvi M. Stated and revealed exit choices of pedestrian crowd evacuees［J］. Transportation Research Part B：Methodological， 2017， 95： 238-259.
[50]	Hensher D A， Rose J M， Greene W H. Applied Choice Analysis［M］. 2nd Ed. Cambridge， UK： Cambridge University Press， 2015.
[51]	Lovreglio R， Fonzone A， Dell’Olio L. A mixed logit model for predicting exit choice during building evacuations［J］. Transportation Research Part A： Policy and Practice， 2016， 92： 59-75.
[52]	van der Heijden H. Decision support for selecting optimal logistic regression models［J］. Expert Systems with Applications， 2012， 39（10）： 8573-8583.
[53]	Hoogendoorn S P， Bovy P H L. Pedestrian route-choice and activity scheduling theory and models［J］. Transportation Research Part B： Methodological， 2004， 38（2）： 169-190.
[54]	Zhao X D， Zhang J， Song W G. A Radar-Nearest-Neighbor based data-driven approach for crowd simulation［J］. Transportation Research Part C： Emerging Technologies， 2021， 129： 103260.
[55]	Liu J， Chen X. Simulation of passenger motion in metro stations during rush hours based on video analysis［J］. Automation in Construction， 2019， 107： 102938.
[56]	Simpson T W， Booker A J， Ghosh D， et al. Approximation methods in multidisciplinary analysis and optimization： A panel discussion［J］. Structural and Multidisciplinary Optimization， 2004， 27（5）： 302-313.
[57]	Filgueiras A V， Gago J， García I， et al. Plackett Burman design for microplastics quantification in marine sediments［J］. Marine Pollution Bulletin， 2021， 162： 111841.
[58]	Shi W， Liu Z， Shang J， et al. Multi-criteria robust design of a JIT-based cross-docking distribution center for an auto parts supply chain［J］. European Journal of Operational Research， 2013， 229（3）： 695-706.
[59]	Dellino G， Kleijnen J P C， Meloni C. Robust optimization in simulation： Taguchi and response surface methodology［J］. International Journal of Production Economics， 2010， 125（1）： 52-59.
[60]	Haghani M， Sarvi M. Crowd model calibration at strategic， tactical， and operational levels： Full-spectrum sensitivity analyses show bottleneck parameters are most critical， followed by exit-choice-changing parameters［J］. Transportation Letters， 2024， 16（4）： 354-381.
[61]	刘嘉，袁欣，阮伟乔，等. 呼吸道传染病疫情下地铁站行人感染风险控制［J］. 中国管理科学， 2025， 33（5）： 236-246.
	Liu J， Yuan X， Ruan W Q， et al. Infection risk control of pedestrians in subway stations under epidemic of respiratory infectious diseases［J］. Chinese Journal of Management Science， 2025， 33（5）： 236-246.
[62]	Haghani M， Sarvi M. Human exit choice in crowded built environments： Investigating underlying behavioural differences between normal egress and emergency evacuations［J］. Fire Safety Journal， 2016， 85： 1-9.