A Generic Bi-Layer Data-Driven Crowd Behaviors Modeling Approach

Weiwei XING; Shibo ZHAO; Shunli ZHANG; Yuanyuan CAI

doi:10.1587/transinf.2016EDP7438

A Generic Bi-Layer Data-Driven Crowd Behaviors Modeling Approach

Weiwei XING, Shibo ZHAO, Shunli ZHANG, Yuanyuan CAI

Full Text Views

0

Share
Cite this

Summary :

Crowd modeling and simulation is an active research field that has drawn increasing attention from industry, academia and government recently. In this paper, we present a generic data-driven approach to generate crowd behaviors that can match the video data. The proposed approach is a bi-layer model to simulate crowd behaviors in pedestrian traffic in terms of exclusion statistics, parallel dynamics and social psychology. The bottom layer models the microscopic collision avoidance behaviors, while the top one focuses on the macroscopic pedestrian behaviors. To validate its effectiveness, the approach is applied to generate collective behaviors and re-create scenarios in the Informatics Forum, the main building of the School of Informatics at the University of Edinburgh. The simulation results demonstrate that the proposed approach is able to generate desirable crowd behaviors and offer promising prediction performance.

Publication: IEICE TRANSACTIONS on Information Vol.E100-D No.8 pp.1827-1836

Publication Date: 2017/08/01

Publicized: 2017/04/21

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2016EDP7438

Type of Manuscript: PAPER

Category: Information Network

Authors

Weiwei XING
  Beijing Jiaotong University
Shibo ZHAO
  Beijing Jiaotong University
Shunli ZHANG
  Beijing Jiaotong University
Yuanyuan CAI
  Beijing Technology and Business University

Keyword

agent-based modeling, crowd simulation, data-driven approach, pedestrian behaviors

Cite this

Copy

Weiwei XING, Shibo ZHAO, Shunli ZHANG, Yuanyuan CAI, "A Generic Bi-Layer Data-Driven Crowd Behaviors Modeling Approach" in IEICE TRANSACTIONS on Information, vol. E100-D, no. 8, pp. 1827-1836, August 2017, doi: 10.1587/transinf.2016EDP7438.
Abstract: Crowd modeling and simulation is an active research field that has drawn increasing attention from industry, academia and government recently. In this paper, we present a generic data-driven approach to generate crowd behaviors that can match the video data. The proposed approach is a bi-layer model to simulate crowd behaviors in pedestrian traffic in terms of exclusion statistics, parallel dynamics and social psychology. The bottom layer models the microscopic collision avoidance behaviors, while the top one focuses on the macroscopic pedestrian behaviors. To validate its effectiveness, the approach is applied to generate collective behaviors and re-create scenarios in the Informatics Forum, the main building of the School of Informatics at the University of Edinburgh. The simulation results demonstrate that the proposed approach is able to generate desirable crowd behaviors and offer promising prediction performance.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.2016EDP7438/_p

Copy

@ARTICLE{e100-d_8_1827,
author={Weiwei XING, Shibo ZHAO, Shunli ZHANG, Yuanyuan CAI, },
journal={IEICE TRANSACTIONS on Information},
title={A Generic Bi-Layer Data-Driven Crowd Behaviors Modeling Approach},
year={2017},
volume={E100-D},
number={8},
pages={1827-1836},
abstract={Crowd modeling and simulation is an active research field that has drawn increasing attention from industry, academia and government recently. In this paper, we present a generic data-driven approach to generate crowd behaviors that can match the video data. The proposed approach is a bi-layer model to simulate crowd behaviors in pedestrian traffic in terms of exclusion statistics, parallel dynamics and social psychology. The bottom layer models the microscopic collision avoidance behaviors, while the top one focuses on the macroscopic pedestrian behaviors. To validate its effectiveness, the approach is applied to generate collective behaviors and re-create scenarios in the Informatics Forum, the main building of the School of Informatics at the University of Edinburgh. The simulation results demonstrate that the proposed approach is able to generate desirable crowd behaviors and offer promising prediction performance.},
keywords={},
doi={10.1587/transinf.2016EDP7438},
ISSN={1745-1361},
month={August},}

Copy

TY - JOUR
TI - A Generic Bi-Layer Data-Driven Crowd Behaviors Modeling Approach
T2 - IEICE TRANSACTIONS on Information
SP - 1827
EP - 1836
AU - Weiwei XING
AU - Shibo ZHAO
AU - Shunli ZHANG
AU - Yuanyuan CAI
PY - 2017
DO - 10.1587/transinf.2016EDP7438
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E100-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2017
AB - Crowd modeling and simulation is an active research field that has drawn increasing attention from industry, academia and government recently. In this paper, we present a generic data-driven approach to generate crowd behaviors that can match the video data. The proposed approach is a bi-layer model to simulate crowd behaviors in pedestrian traffic in terms of exclusion statistics, parallel dynamics and social psychology. The bottom layer models the microscopic collision avoidance behaviors, while the top one focuses on the macroscopic pedestrian behaviors. To validate its effectiveness, the approach is applied to generate collective behaviors and re-create scenarios in the Informatics Forum, the main building of the School of Informatics at the University of Edinburgh. The simulation results demonstrate that the proposed approach is able to generate desirable crowd behaviors and offer promising prediction performance.
ER -