A Role-dependent Data-driven Approach for High Density Crowd Behavior Modeling

In this paper, we propose a role-dependent data-driven modeling approach to simulate pedestrians' motion in high density scenes. It is commonly observed that pedestrians behave quite differently when walking in dense crowd. Some people explore routes towards their destinations. Meanwhile, some people deliberately follow others, leading to lane formation. Based on these observations, two roles are included in the proposed model: leader and follower. The motion behaviors of leader and follower are modeled separately. Leaders' behaviors are learned from real crowd motion data using state-action pairs while followers' behaviors are calculated based on specific targets that are obtained dynamically during the simulation. The proposed role-dependent data-driven model is trained on crowd video data in one dataset and is then applied to two other different datasets to test its generality and effectiveness. The simulation results demonstrate that the proposed role-dependent data-driven model is capable of simulating crowd behaviors in crowded scenes realistically and reproducing collective crowd behaviors such as lane formation.

[1]  N. Badler,et al.  Crowd simulation incorporating agent psychological models, roles and communication , 2005 .

[2]  Cécile Appert-Rolland,et al.  Realistic following behaviors for crowd simulation , 2012, Comput. Graph. Forum.

[3]  William H. Warren,et al.  Behavioral Dynamics of Heading Alignment in Pedestrian Following , 2014 .

[4]  Marshall F. Tappen,et al.  Learning pedestrian dynamics from the real world , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[5]  Katsuhiro Nishinari,et al.  Simulation for pedestrian dynamics by real-coded cellular automata (RCA) , 2007 .

[6]  Dimitris N. Metaxas,et al.  Eurographics/ Acm Siggraph Symposium on Computer Animation (2007) Group Behavior from Video: a Data-driven Approach to Crowd Simulation , 2022 .

[7]  Dinesh Manocha,et al.  Least-effort trajectories lead to emergent crowd behaviors. , 2012, Physical review. E, Statistical, nonlinear, and soft matter physics.

[8]  Victor J. Blue,et al.  Cellular Automata Microsimulation of Bidirectional Pedestrian Flows , 1999 .

[9]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[10]  George J. Milne,et al.  Modelling Emergent Crowd Behaviour , 2003 .

[11]  Stephen John Turner,et al.  A Data-Driven Crowd Simulation Model Based on Clustering and Classification , 2013, 2013 IEEE/ACM 17th International Symposium on Distributed Simulation and Real Time Applications.

[12]  Christian Dogbé.  On the numerical solutions of second order macroscopic models of pedestrian flows , 2008, Comput. Math. Appl..

[13]  Dinesh Manocha,et al.  Reciprocal Velocity Obstacles for real-time multi-agent navigation , 2008, 2008 IEEE International Conference on Robotics and Automation.

[14]  Dirk Helbing,et al.  How simple rules determine pedestrian behavior and crowd disasters , 2011, Proceedings of the National Academy of Sciences.

[15]  Gerta Köster,et al.  Pedestrian Group Behavior in a Cellular Automaton , 2014 .

[16]  Dirk Helbing,et al.  Specification of the Social Force Pedestrian Model by Evolutionary Adjustment to Video Tracking Data , 2007, Adv. Complex Syst..

[17]  Robert E. Kraut,et al.  Communication and social cognition. , 1984 .

[18]  Dinesh Manocha,et al.  PLEdestrians: a least-effort approach to crowd simulation , 2010, SCA '10.

[19]  Sébastien Paris,et al.  Pedestrian Reactive Navigation for Crowd Simulation: a Predictive Approach , 2007, Comput. Graph. Forum.

[20]  Norman I. Badler,et al.  Controlling individual agents in high-density crowd simulation , 2007, SCA '07.

[21]  S. Wong,et al.  A higher-order macroscopic model for pedestrian flows , 2010 .

[22]  J. Pettré,et al.  A synthetic-vision based steering approach for crowd simulation , 2010, ACM Trans. Graph..

[23]  Wolfram Klein,et al.  On modelling the influence of group formations in a crowd , 2011 .

[24]  Michael Lees,et al.  Title Density-based evolutionary framework for crowd model calibration , 2018 .

[25]  Xiaogang Wang,et al.  Understanding collective crowd behaviors: Learning a Mixture model of Dynamic pedestrian-Agents , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

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

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

[28]  Yiorgos Chrysanthou,et al.  The PAG Crowd: A Graph Based Approach for Efficient Data‐Driven Crowd Simulation , 2014, Comput. Graph. Forum.

[29]  Abdullah Zawawi Talib,et al.  Modeling Groups of Pedestrians in Least Effort Crowd Movements Using Cellular Automata , 2009, 2009 Third Asia International Conference on Modelling & Simulation.

[30]  Wentong Cai,et al.  Learning Behavior Patterns from Video: A Data-driven Framework for Agent-based Crowd Modeling , 2015, AAMAS.

[31]  Norman I. Badler,et al.  Improving the realism of agent movement for high density crowd simulation , 2006 .

[32]  T. Gärling,et al.  Weighing the past and the future in decision making , 2005 .

[33]  Mark H. Overmars,et al.  Simulating the local behaviour of small pedestrian groups , 2010, VRST '10.

[34]  William H Warren,et al.  Follow the leader: visual control of speed in pedestrian following. , 2014, Journal of vision.

[35]  J. Drury,et al.  Modelling subgroup behaviour in crowd dynamics DEM simulation , 2009 .

[36]  Shing Chung Josh Wong,et al.  Bidirectional Pedestrian Stream Model with Oblique Intersecting Angle , 2010 .

[37]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[38]  Victor J. Blue,et al.  Cellular automata microsimulation for modeling bi-directional pedestrian walkways , 2001 .

[39]  Stéphane Donikian,et al.  Experiment-based modeling, simulation and validation of interactions between virtual walkers , 2009, SCA '09.

[40]  K. Kitazawa,et al.  Pedestrian Vision and Collision Avoidance Behavior: Investigation of the Information Process Space of Pedestrians Using an Eye Tracker , 2010 .

[41]  Dani Lischinski,et al.  Crowds by Example , 2007, Comput. Graph. Forum.

[42]  A. Birenbaum,et al.  People in places : the sociology of the familiar , 1973 .

[43]  S. Yantis,et al.  Visual attention: control, representation, and time course. , 1997, Annual review of psychology.