ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Integration of image processing and crowd simulation for understanding crowd dynamics in Kumbh Mela

Karthika, PS and Verma, A and Pal, S (2020) Integration of image processing and crowd simulation for understanding crowd dynamics in Kumbh Mela. In: 2019 World Conference Transport Research, WCTR 2019, 26-31 May 2019, Indian Institute of Technology Mumbai, Mumbai; India, pp. 2906-2915.

tra_res_pro_48_2906-2915_2020.pdf - Published Version

Download (2MB) | Preview
Official URL: https://dx.doi.org/10.1016/j.trpro.2020.08.229


The paper highlights the need to study crowd dynamics in mass religious gatherings. Kumbh Mela, the largest peaceful mass gathering in the world is considered for this purpose. The aim of this study was to evaluate the performance of an image processing module when combined with a crowd simulator. The pedestrian inflow as obtained from the image processing module is automatically fed into the crowd simulator. The pedestrian movements are simulated by using the social force model and a demo heat map is generated for assessing the crowd risk situations. The image processing module has an average accuracy of 73.45. The effect of varying border threshold on the pedestrian movement is also explored. With a more accurate and realistic heat map, it can be used by the concerned authorities to make timely decisions on ensuring crowd safety in large gatherings. © 2020 The Authors. Published by Elsevier B.V.

Item Type: Conference Paper
Publication: Transportation Research Procedia
Publisher: Elsevier B.V.
Additional Information: The copyright of this article belongs to Elsevier B.V.
Department/Centre: Division of Interdisciplinary Sciences > Robert Bosch Centre for Cyber Physical Systems
Division of Mechanical Sciences > Civil Engineering
Date Deposited: 01 Dec 2020 09:30
Last Modified: 01 Dec 2020 09:30
URI: http://eprints.iisc.ac.in/id/eprint/67126

Actions (login required)

View Item View Item