Simulation of Evacuating Crowd Based on Deep Learning and Social Force Model

It is always difficult to evacuate crowds in public places like subway stations. The traditional crowd behavior simulation models often ignore two important issues in crowd evacuation: pedestrian tracking and individual differences. To solve the problem, this paper combines social force model (SFM) with deep learning into a novel pedestrian detection method. Firstly, several deep learning algorithms for pedestrian detection were compared, and the best ones for sparse and dense crowds were determined. Next, the pedestrian positions in a real video were acquired by the selected algorithms, and converted into actual coordinates in the scene. Then, the evacuation process was simulated with our method and the SFM based on these coordinates. The results show that our model output closer-to-reality results than the SFM. The research findings shed important new light on evacuation in crowded areas.

[1]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Chong Wang,et al.  Trend prediction of the 3D thermocline’s lateral boundary based on the SVR method , 2018, EURASIP J. Wirel. Commun. Netw..

[3]  Dirk Helbing,et al.  Simulating dynamical features of escape panic , 2000, Nature.

[4]  Harri Ehtamo,et al.  Pedestrian behavior and exit selection in evacuation of a corridor – An experimental study , 2012 .

[5]  Le Zhang,et al.  Improved Multi-Agent Reinforcement Learning for Path Planning-Based Crowd Simulation , 2019, IEEE Access.

[6]  Jin Wang,et al.  A parallel FP-growth algorithm on World Ocean Atlas data with multi-core CPU , 2018, The Journal of Supercomputing.

[7]  Chenfanfu Jiang,et al.  Position-based multi-agent dynamics for real-time crowd simulation , 2017, MIG.

[8]  Anders Peterson,et al.  Waiting pedestrians in the social force model , 2015 .

[9]  Rong Li,et al.  Simulation and analysis of congestion risk during escalator transfers using a modified social force model , 2015 .

[10]  Majid Sarvi,et al.  Stated and revealed exit choices of pedestrian crowd evacuees , 2017 .

[11]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Jian Sun,et al.  Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Yan-Qun Jiang,et al.  A higher-order macroscopic model for bi-direction pedestrian flow , 2015 .

[14]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Roger L. Hughes,et al.  A continuum theory for the flow of pedestrians , 2002 .

[16]  Helbing,et al.  Social force model for pedestrian dynamics. , 1995, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[17]  Ruggiero Lovreglio,et al.  A study of herding behaviour in exit choice during emergencies based on random utility theory. , 2016 .

[18]  Hong Liu,et al.  A social force evacuation model driven by video data , 2018, Simul. Model. Pract. Theory.

[19]  Daniel Nilsson,et al.  Social influence during the initial phase of a fire evacuation—Analysis of evacuation experiments in a cinema theatre , 2009 .

[20]  Xiang Zhang,et al.  OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks , 2013, ICLR.

[21]  Eliahu Stern,et al.  Wayfinding: Choice and Search , 1990 .

[22]  Yunyun Niu,et al.  Running Cells with Decision-Making Mechanism: Intelligence Decision P System for Evacuation Simulation , 2018, Int. J. Comput. Commun. Control.

[23]  Yanchao Sun,et al.  Distributed finite-time fault-tolerant containment control for multiple ocean Bottom Flying node systems with error constraints , 2019, Ocean Engineering.

[24]  Marie-Therese Wolfram,et al.  An improved version of the Hughes model for pedestrian flow , 2016 .

[25]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[26]  Tobias Kretz,et al.  Pedestrian traffic: on the quickest path , 2009, ArXiv.

[27]  Hongde Qin,et al.  Distributed finite-time fault-tolerant containment control for multiple ocean bottom flying nodes , 2020, J. Frankl. Inst..

[28]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[29]  M. Zsifkovits,et al.  Modelling and Parameterizing Pedestrian Behaviour in Public Places: A Review , 2016 .

[30]  Dirk Hartmann,et al.  Adaptive pedestrian dynamics based on geodesics , 2010 .

[31]  Hei Law,et al.  CornerNet: Detecting Objects as Paired Keypoints , 2018, International Journal of Computer Vision.

[32]  Ramesh Neelapu,et al.  Deep learning based conventional neural network architecture for medical image classification , 2018, Traitement du Signal.

[33]  Pietro Perona,et al.  Pedestrian Detection: An Evaluation of the State of the Art , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[34]  Haibo He,et al.  Robot-Assisted Pedestrian Regulation Based on Deep Reinforcement Learning , 2020, IEEE Transactions on Cybernetics.

[35]  Zhe Li,et al.  Design of moving target detection and tracking system based on cortex-A7 and openCV , 2018, Traitement du Signal.

[36]  Hai-Jun Huang,et al.  Route choice in pedestrian evacuation: formulated using a potential field , 2011 .

[37]  Dumitru Erhan,et al.  Deep Neural Networks for Object Detection , 2013, NIPS.

[38]  Yu Jiang,et al.  High-resolution temperature and salinity model analysis using support vector regression , 2018, Journal of Ambient Intelligence and Humanized Computing.