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

Automated Crowd Parameter Estimation and Crowd Movement Analysis in Kumbh Mela

Choubey, N and Verma, A and Chakraborty, A (2023) Automated Crowd Parameter Estimation and Crowd Movement Analysis in Kumbh Mela. In: 6th International Conference of Transportation Research Group of India, CTRG 2021, 14 - 17 December 2021, Tiruchirappalli, pp. 303-318.

Full text not available from this repository.
Official URL: https://doi.org/10.1007/978-981-19-4204-4_18

Abstract

Understanding crowd behavior is essential in mass religious gatherings for crowd managers. Surveillance devices such as CCTV provide data in real time in the form of raw video, while the crowd manager estimates the crowd state from video based on their experience. In this study, we propose a methodology to automate the crowd parameter estimation process using an object detection model and tracking algorithm, which will assist crowd managers in estimating the state of the crowd. There are two key contributions to this study. First, the study proposes a methodology to automate crowd parameter estimation from video in a mass religious gathering. Second, the existing state-of-the-art object detection model has been improved to adapt to the challenging situation of mass religious gatherings with high density, high diversity crowd videos. CCTV videos from Kumbh Mela 2016 are used for this study. © 2023, Transportation Research Group of India.

Item Type: Conference Paper
Publication: Lecture Notes in Civil Engineering
Publisher: Springer Science and Business Media Deutschland GmbH
Additional Information: The copyright for this article belongs to Springer Science and Business Media Deutschland GmbH.
Keywords: Behavioral research; Convolutional neural networks; Managers; Object detection; Object recognition; Parameter estimation; Security systems, Convolutional neural network; Crowd movements; Detection models; Kumbh mela; Mass religious gathering; Neural-networks; Objects detection; Parameters estimation; Pedestrian count; Pedestrian detection, Computer vision
Department/Centre: Division of Interdisciplinary Sciences > Computational and Data Sciences
Division of Interdisciplinary Sciences > Robert Bosch Centre for Cyber Physical Systems
Division of Mechanical Sciences > Civil Engineering
Date Deposited: 14 Nov 2022 05:56
Last Modified: 14 Nov 2022 05:56
URI: https://eprints.iisc.ac.in/id/eprint/77799

Actions (login required)

View Item View Item