Estimation of linear motion in dense crowd videos using Langevin model

Behera, Shreetam; Dogra, Debi Prosad; Bandyopadhyay, Malay; Roy, Partha Pratim

doi:10.1016/j.eswa.2020.113333

Cited by 6 publications

(2 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…particles that exit the domain on one side re-enter it from the opposite side. Random, human motion can be calculated with the Langevin equation [ 12 ]

where m is the mass of the particle, v is the velocity and γ f is a friction coefficient. F REP is an interparticle repulsive force that prevents particles from overlapping.…”

Section: Methodsmentioning

confidence: 99%

Simulation of pandemics in real cities: enhanced and accurate digital laboratories

et al. 2021

View full text Add to dashboard Cite

This study develops a modelling framework for simulating the spread of infectious diseases within real cities. Digital copies of Birmingham (UK) and Bogotá (Colombia) are generated, reproducing their urban environment, infrastructure and population. The digital inhabitants have the same statistical features of the real population. Their motion is a combination of predictable trips (commute to work, school, etc.) and random walks (shopping, leisure, etc.). Millions of individuals, their encounters and the spread of the disease are simulated by means of high-performance computing and massively parallel algorithms for several months and a time resolution of 1 minute. Simulations accurately reproduce the COVID-19 data for Birmingham and Bogotá both before and during the lockdown. The model has only one adjustable parameter calculable in the early stages of the pandemic. Policymakers can use our digital cities as virtual laboratories for testing, predicting and comparing the effects of policies aimed at containing epidemics.

show abstract

“…particles that exit the domain on one side re-enter it from the opposite side. Random, human motion can be calculated with the Langevin equation [ 12 ]

where m is the mass of the particle, v is the velocity and γ f is a friction coefficient. F REP is an interparticle repulsive force that prevents particles from overlapping.…”

Section: Methodsmentioning

confidence: 99%

Simulation of pandemics in real cities: enhanced and accurate digital laboratories

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Crowd behavior analysis is the application field of many disciplines such as artificial intelligence [ 1 , 2 ], safety management [ 3 , 4 ], and computer vision [ 5 , 6 ]. There are three kinds of research methods for crowd behavior analysis, i.e., controlled experiment [ 7 , 8 ], crowd simulation [ 9 , 10 ], and crowd video monitoring [ 11 , 12 ].…”

Section: Introductionmentioning

confidence: 99%

Fuzzy Evaluation of Crowd Safety Based on Pedestrians’ Number and Distribution Entropy

Zhang

Wang

2020

Entropy

View full text Add to dashboard Cite

Crowd video monitoring and analysis is a hot topic in computer vision and public management. The pre-evaluation of crowd safety is beneficial to the prediction of crowd status to avoid the occurrence of catastrophic events. This paper proposes a method to evaluate crowd safety based on fuzzy inference. Pedestrian’s number and distribution uniformity are considered in a fuzzy inference system as two kinds of attributes of a crowd. Firstly, the pedestrian’s number is estimated by the number of foreground pixels. Then, the distribution uniformity of a crowd is calculated using distribution entropy by dividing the monitoring scene into several small areas. Furthermore, through the fuzzy operation, the fuzzy system is constructed by using two input variables (pedestrian’s number and distribution entropy) and one output variable (crowd safety status). Finally, inference rules between the crowd safety state and the pedestrian’s number and distribution uniformity are constructed to obtain the pre-evaluation of the safety state of the crowd. Three video sequences extracted from different scenes are used in the experiment. Experimental results show that the proposed method can be used to evaluate the safety status of the crowd in a monitoring scene.

show abstract