ArticlePublisher preview available

A review on technological advancements in crowd management

June 2018
Journal of Ambient Intelligence and Humanized Computing 9(3):1-11

DOI:10.1007/s12652-016-0432-x

Authors:

Deepak Sharma

National Physical Laboratory - India

Amol P Bhondekar

Council of Scientific and Industrial Research (CSIR), New Delhi

Awdhesh Kumar Shukla

CSIR-CSIO

C. Ghanshyam

CSIR-CSIO,

With more and more people attending public gatherings, and with a continuous rise in crowd density in urban areas, the management of crowd has become more challenging than ever before. Every year, many people lose their lives due to inefficient crowd planning and management. Crowd management is an interdisciplinary area, and it requires understanding of engineering and technological aspects, along with an understanding of crowd behavior and crowd flow management, i.e. psychological and sociological aspects. This paper presents a broad, but not exhaustive overview of the recent technological advancements in the area of crowd planning and monitoring techniques for an effective crowd management system. It discusses the crowd modeling aspects during the planning of crowded scenario, and the technological advancements in crowd data acquisition techniques [based on Vision, Wireless/Radio-Frequency (RF) and Web/Social-media data mining technologies] during execution of crowded event. The paper also considers

Technological aspect of crowd management system during different phases of an event

…

a Flow rate Vs crowd density (Still); b A visualization tool to plan the crowd numbers and density at key locations (Still 2011) (Reprinted with permission from http://www.gkstill.com)

…

Event data collection and visualization in Ushahidi system (Ushahidi) (Reprinted with permission from http://www.ushahidi.com)

…

Figures - available from: Journal of Ambient Intelligence and Humanized Computing

This content is subject to copyright. Terms and conditions apply.

A preview of this full-text is provided by Springer Nature.

Learn more

Content available from Journal of Ambient Intelligence and Humanized Computing

This content is subject to copyright. Terms and conditions apply.

ORIGINAL RESEARCH

A review on technological advancements in crowd management

Deepak Sharma

1,2

•Amol P. Bhondekar

1,2

•A. K. Shukla

1,2

•C. Ghanshyam

1,2

Received: 9 August 2016 / Accepted: 2 November 2016 / Published online: 18 November 2016

ÓSpringer-Verlag Berlin Heidelberg 2016

Abstract With more and more people attending public

gatherings, and with a continuous rise in crowd density in

urban areas, the management of crowd has become more

challenging than ever before. Every year, many people lose

their lives due to inefﬁcient crowd planning and manage-

ment. Crowd management is an interdisciplinary area, and

it requires understanding of engineering and technological

aspects, along with an understanding of crowd behavior

and crowd ﬂow management, i.e. psychological and soci-

ological aspects. This paper presents a broad, but not

exhaustive overview of the recent technological advance-

ments in the area of crowd planning and monitoring tech-

niques for an effective crowd management system. It

discusses the crowd modeling aspects during the planning

of crowded scenario, and the technological advancements

in crowd data acquisition techniques [based on Vision,

Wireless/Radio-Frequency (RF) and Web/Social-media

data mining technologies] during execution of crowded

event. The paper also considers technological applications

in some highly crowded scenarios on earth as case studies,

along with future research directions in the area.

Keywords Crowd management Crowd data acquisition 

Crowd modeling Wireless technologies Computational

instrumentation Data mining

1 Introduction

In a recent stampede during Hajj on September 24, 2015,

more than 700 people died and more than 850 got injured

(MOH-SA 2015). Every year, hundreds of lives are lost and

thousands get injured in crowded events due to insufﬁcient

and/or inefﬁcient crowd management measures. Based on

an UN report (UN 2014), in 1950, 30% of the world’s

population was urban; which became 54% in 2014; and

66% of the world’s population is projected to be urban by

2050. Considering example of a developing nation, e.g.

India; As on July 1, 2014 three Indian cities: Delhi,

Mumbai and Kolkata were ranked at number 2, 6 and 14

respectively in the ranking of global urban agglomerations

based on population size, with prospects of further increase

in population in future, e.g. population of Delhi (25 million

in 2014) is projected to rise swiftly to 36 million by 2030.

In Mumbai suburban railway (India) about 8 million

commuters travel every day, which faces the highest pas-

senger density in the world (MRVCL 2016). Consideration

of crowd management is not only required for managing

crowded events, but it has become equally important while

planning public infrastructure in urban areas, where a high

crowd density is expected.

Crowd management is a complex process, some of its

important elements are crowd modeling for planning the

event and infrastructure; crowd data acquisition during

crowd monitoring; data analysis for decision making;

provisioning and applying crowd control measures, etc.

Crowd management requires a collaboration of various

areas of engineering and science, e.g. physics, computer

science, civil engineering, psychology, management, etc.

The crowd modeling, based on simulating the crowd

scenarios under various circumstances, can help in devising

better crowd control and management strategies. The

&Deepak Sharma

deepakskc@yahoo.com; deepaksharma@csio.res.in

CSIR-Central Scientiﬁc Instruments Organisation,

Sector-30C, Chandigarh 160030, India

Academy of Scientiﬁc and Innovative Research, New Delhi,

India

123

J Ambient Intell Human Comput (2018) 9:485–495

https://doi.org/10.1007/s12652-016-0432-x

Content courtesy of Springer Nature, terms of use apply. Rights reserved.

Crowd-counting technology within the Smart City context: understanding, trust, and acceptance

Article

Full-text available

Nov 2024

In city centers worldwide, including the UNESCO World Heritage Site of Bamberg’s old town in Germany, alleviating pedestrian overcrowding is a pressing concern. Leveraging crowd-counting technologies with real-time data collection offers promising solutions, yet poses challenges regarding data privacy and informed consent. This preregistered study examines public response to a Smart City Bamberg project aimed at addressing pedestrian congestion through crowd-counting methods. We investigate informed consent by looking at understanding and acceptance of the project, as well as influencing factors, such as effectiveness of project explanation and trust. Through a three-stage study comprising exploratory interviews, a field study, and an online study, we reveal that the focus of project explanations significantly impacts understanding: Functional explanations, emphasizing project purpose, enhance comprehension compared to mechanistic explanations detailing project components. Additionally, project trust positively correlates with acceptance. Notably, understanding impacts acceptance through increased project trust. These findings underscore the importance of fostering understanding to garner public acceptance of crowd-counting projects. It is important, especially in the case of projects which aim to improve quality of life while also prioritizing robust data protection, that decisions regarding informed consent are grounded in comprehension rather than on preconceived biases against data sharing. Efforts should prioritize effective explanations to bolster project trust and consequently, promote acceptance.

Rethinking Urban Planning and Development for the Post-Pandemic Urban Crowd Management

Chapter

Full-text available

Sep 2024

The demand for collective gatherings and recreational space has been rising as a response to the three-year itch of staying indoors and social distancing due to the global COVID-19 pandemic. Crowds are spilling out in the city and rejuvenating places, yet also causing dangerously overcrowded and uncontrolled situations. Planning is also challenged by the temporary use of space and the unpredictable nature of crowds during events, requiring a deep understanding of the crowd flow and flexibility in planning. How can places be prepared to accommodate the sudden influx of crowds safely? This chapter focuses on the case study of the tragic crowd crush in a once-festive alley celebrating Halloween in Itaewon, Seoul, the Republic of Korea, in 2022. What sort of planning methods could have prevented the crowd crush? Many past similar events worldwide reported a significant number of casualties and deaths, especially related to stampedes. This chapter analyzes the tragedy in retrospect in terms of form, programming, and the roles of stakeholders while reviewing and drawing lessons learned from relevant crowd-control measures elsewhere that could have been applied to avoid such an incident. Ultimately, this chapter offers insights and guidelines for planning for future crowd-raising occasions in limited spaces.

Detecting Facial Emotion Expression to Mentor and Manage Crowds Using a Deep Convolutional Neural Network

Article

Full-text available

Jun 2024

Human interactions are heavily reliant on facial expressions. An individual’s emotional state can affect their safety and security in crowd places. Thus, monitoring and detecting emotions in facial expression in real time contributes to preventing potentially harmful situations. However, performing such tasks is difficult and complex and requires advanced computational methods. This study aimed to use a deep convolution neural network to detect and monitor facial emotion expressions in crowds. In addition, the effectiveness of transfer learning using VGG16, ResNet50 and Xception with DCNN models to improve accuracy was investigated. To achieve this, an FER2013 dataset with more than 35,000 images classified in terms of anger, fear, disgust, happiness, surprise, sadness and neutral was used. The results showed that transfer learning improved the accuracy and performance of an ensemble of the three models.

How Social Attributes Affect the Movement Process of Subgroups When Facing a Static Obstacle

Article

Full-text available

Nov 2024

With the increasing number of studies on crowd behavior analysis, there has been a widespread interest in treating subgroups as an important topic. A previous experimental study has investigated the decision-making and motion behavior of subgroups when facing a static obstacle during movement. However, it is hard to quantify social attributes (e.g., interpersonal relationships and sense of identity) and little is known about how they affect the movement process of subgroups. Here, we propose a vision-driven model to solve this problem, in which two key model parameters are defined to control the spatial cohesion and attraction intensity, respectively. Numerical simulations demonstrate that the optimal regions of model parameters vary depending on different conditions of the three control variables (obstacle width, time pressure, and subgroup size). The spatial cohesion and attraction intensity barely change the movement process of subgroups in the maintaining state but significantly affect it in the splitting-merging state. This model can reproduce the herding effect of subgroup members in the merging process, which is affected to varying degrees by the modulation of model parameters. Overall, this work contributes to the simulation of subgroup behaviors from a sociopsychological perspective.

Estimation of Abnormal Crowd Density Using Transfer Learning Techniques

Conference Paper

Jun 2024

Modelling Groups of Humans: Towards Crowd Digital Twins

Conference Paper

Jun 2024

Role of Deindividuation Between Perceived Crowding and Tourist Behaviors: Moderating Effect of Environmental Knowledge

Article

Sep 2024

Destination crowding has emerged as a serious issue for tourist sites and visitors alike. This research delves into the correlation between two‐dimensional perceived (spatial and human) crowding and two tourist behaviors (pro‐environmental and deviant behavior). Additionally, it explores the influence of deindividuation and environmental knowledge on these relationships. The study, based on 313 Chinese domestic tourists who recently visited the Great Wall, reveals that perceptions of spatial and human crowding significantly trigger deviant behavior. Conversely, pro‐environmental behavior is indirectly impeded by both forms of perceived crowding, with deindividuation acting as a mediating factor. The presence of environmental knowledge proves crucial in empowering tourists to make well‐informed behavioral decisions and mitigating the negative effects of deindividuation on their actions. This research contributes to the tourism literature by incorporating deindividuation to enhance the understanding of how perceived crowding affects tourist behaviors. It further advances the field by differentiating between pro‐environmental and deviant.

Crowd Anomaly Estimation and Detection: A Review

Article

Oct 2024

Towards Fairness-aware Crowd Management System and Surge Prevention in Smart Cities

Conference Paper

May 2024

Edge-assisted federated learning framework for smart crowd management

Article

Jun 2024

Self-organized pedestrian crowd dynamics: Experiments, simulations, and design solutions

Article

Full-text available

Jan 2013

Real-time crowd motion analysis

Article

Full-text available

Jan 2008

A landscape of crowd-management support: An integrative approach

Article

Full-text available

Jul 2016
SAFETY SCI

Of the many crowd behavior models, very few have been used in assisting crowd management practice. This lack of usage is partly due to crowd management involving a diversity of situations that require competencies in observing, sense-making, anticipating and acting. Crowd research is similarly scattered across disciplines and needs integration to advance the field towards supporting practice. To address these needs, we present inCrowd, an integrated framework detailing a high-level architecture of a decision-support system for crowd management and model development. It also offers a lens for categorizing crowd literature, allowing us to present a structured literature review.

Data fusion for city life event detection

Article

Full-text available

Feb 2017

The automatic detection of events happening in urban areas from mobile phones’ and social networks’ datasets is an important problem that would enable novel services ranging from city management and emergency response, to social and entertainment applications. In this work we present a simple yet effective method for discovering events from spatio-temporal datasets, based on statistical anomaly detection. Our approach can combine multiple sources of information to improve results. We also present a method to automatically generate a keyword-based description of the events being detected. We run experiments in two cities with data coming from a mobile phone operator (call detail records–CDRs) and from Twitter. We show that this method gives interesting results in terms of precision and recall. We analyze the parameters of our approach and discuss its strengths and weaknesses.

A Framework to Identify Best Practices

Chapter

Jan 2012

Social media is used in a variety of domains, including emergency management. However, the question of which technologies are most appropriate for a given emergency remains open. We present a framework of dimensions of emergencies that can assist in selecting appropriate social media for an emergency situation. Social media is not a panacea but can be used effectively given the proper functions available from the particular services provided by each of the Web 2.0 technologies available. The main objective of this paper is to identify the best practices for social media to leverage its ability given the complexities that coincide with events. This is a conceptual paper based on the results of preliminary studies involving group interactions with emergency professionals with various backgrounds. In addition, emergency management students who are professionals in the field followed by another interview soliciting information from information systems scientist were surveyed. We found that each situation called forth various dimensions where only sub phases of the stated dimension may be used given the task type derived from the event characteristics. This lays a foundation upon which a more formal approach can be taken to help tame the social media mania into a manageable set of ‘best practices’ from which emergencies can be managed more effectively given Web 2.0 technologies and social collaborative online tools.

Social media and disasters: Current uses, future options and policy considerations

Article

Jan 2011

B.R. Lindsay

Cyber-physical Modeling and Control of Crowd of Pedestrians: A Review and New Framework

Article

Jul 2015

Recent advances in modeling and control of crowd of pedestrians are briefly surveyed in this paper. Possibilities of applying fractional calculus in the modeling of crowd of pedestrians have been shortly reviewed and discussed from different aspects such as descriptions of motion, interactions of long range and effects of memory. Control of the crowd of pedestrians have also been formulated using the framework of cyber-physical systems and been realized using networked Segways with onboard emergency response personnels to regulate the velocity and flux of the crowd. Platform for verification of the theoretical results are also provided in this paper.

A Fractional Micro-Macro Model for Crowds of Pedestrians Based on Fractional Mean Field Games

Article

Jul 2016

Modeling a crowd of pedestrians has been considered in this paper from different aspects. Based on fractional microscopic model that may be much more close to reality, a fractional macroscopic model has been proposed using conservation law of mass. Then in order to characterize the competitive and cooperative interactions among pedestrians, fractional mean field games are utilized in the modeling problem when the number of pedestrians goes to infinity and fractional dynamic model composed of fractional backward and fractional forward equations are constructed in macro scale. Fractional micro-macro model for crowds of pedestrians are obtained in the end. Simulation results are also included to illustrate the proposed fractional microscopic model and fractional macroscopic model, respectively.

Human behaviours in evacuation crowd dynamics: From modelling to “big data” toward crisis management

Article

May 2016
PHYS LIFE REV

This paper proposes an essay concerning the understanding of human behaviours and crisis management of crowds in extreme situations, such as evacuation through complex venues. The first part focuses on the understanding of the main features of the crowd viewed as a living, hence complex system. The main concepts are subsequently addressed, in the second part, to a critical analysis of mathematical models suitable to capture them, as far as it is possible. Then, the third part focuses on the use, toward safety problems, of a model derived by the methods of the mathematical kinetic theory and theoretical tools of evolutionary game theory. It is shown how this model can depict critical situations and how these can be managed with the aim of minimizing the risk of catastrophic events.

A Fractional Micro-Macro Model for Crowds of Pedestrians based on Fractional Mean Field Games

Article

Feb 2016

Modeling of crowds of pedestrians has been considered in this paper from different aspects. Based on fractional microscopic model that may be much more close to reality, a fractional macroscopic model has been proposed using conservation law of mass. Then in order to characterize the competitive and cooperative interactions among pedestrians, fractional mean field games are utilized in the modeling problem when the number of pedestrians goes to infinity and fractional dynamic model composed of fractional backward and fractional forward equations are constructed in macro scale. Fractional micro-macro model for crowds of pedestrians are obtained in the end. Simulation results are also included to illustrate the proposed fractional microscopic model and fractional macroscopic model respectively.