A deep crowd density classification model for Hajj pilgrimage using fully convolutional neural network

Md Roman Bhuiyan; Junaidi Abdullah; Noramiza Hashim; Fahmid Al Farid; Mohammad Ahsanul Haque; Jia Uddin; Wan Noorshahida Mohd Isa; Mohd Nizam Husen; Norra Abdullah

doi:10.7717/peerj-cs.895

A deep crowd density classification model for Hajj pilgrimage using fully convolutional neural network

PeerJ Comput Sci. 2022 Mar 25:8:e895. doi: 10.7717/peerj-cs.895. eCollection 2022.

Authors

Md Roman Bhuiyan¹, Junaidi Abdullah¹, Noramiza Hashim¹, Fahmid Al Farid¹, Mohammad Ahsanul Haque², Jia Uddin³, Wan Noorshahida Mohd Isa¹, Mohd Nizam Husen⁴, Norra Abdullah⁵

Affiliations

¹ Faculty of Computing and Informatics, Multimedia University, Cyberjaya, Selengor, Malaysia.
² Data Scientist and Machine Learning Developer, Aalborg University, Aalborg, Aalborg, Denmark.
³ Technology Studies Department, Woosong University, Daejeon, South Korea.
⁴ Information Technology, Malaysian Institute of Information Technology Universiti Kuala Lumpur, Kuala Lumpur, Malaysia.
⁵ Computer Science, WSA Venture Australia (M) Sdn Bhd, Cyberjaya, Malaysia.

Abstract

This research enhances crowd analysis by focusing on excessive crowd analysis and crowd density predictions for Hajj and Umrah pilgrimages. Crowd analysis usually analyzes the number of objects within an image or a frame in the videos and is regularly solved by estimating the density generated from the object location annotations. However, it suffers from low accuracy when the crowd is far away from the surveillance camera. This research proposes an approach to overcome the problem of estimating crowd density taken by a surveillance camera at a distance. The proposed approach employs a fully convolutional neural network (FCNN)-based method to monitor crowd analysis, especially for the classification of crowd density. This study aims to address the current technological challenges faced in video analysis in a scenario where the movement of large numbers of pilgrims with densities ranging between 7 and 8 per square meter. To address this challenge, this study aims to develop a new dataset based on the Hajj pilgrimage scenario. To validate the proposed method, the proposed model is compared with existing models using existing datasets. The proposed FCNN based method achieved a final accuracy of 100%, 98%, and 98.16% on the proposed dataset, the UCSD dataset, and the JHU-CROWD dataset, respectively. Additionally, The ResNet based method obtained final accuracy of 97%, 89%, and 97% for the proposed dataset, UCSD dataset, and JHU-CROWD dataset, respectively. The proposed Hajj-Crowd-2021 crowd analysis dataset and the model outperformed the other state-of-the-art datasets and models in most cases.

Keywords: Crowd analysis; Crowd density classification; Fully convolutional neural network (FCNN); Hajj crowd dataset.