eprintid: 17392
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/01/73/92
datestamp: 2023-12-19 03:23:47
lastmod: 2023-12-19 03:23:47
status_changed: 2023-12-19 03:07:58
type: article
metadata_visibility: show
creators_name: Farooq, M.U.
creators_name: Mohamad Saad, M.N.
creators_name: Saleh, Y.
creators_name: Daud Khan, S.
title: Deep Learning Approach for Divergence Behavior Detection at High Density Crowd
ispublished: pub
keywords: Behavioral research; Deep learning; Lyapunov methods; Time and motion study, Behavior detection; Convolution neural network; Divergence; Finite-time Lyapunov exponent; Human lives; Image shape; Lagrangian coherent structures; Learning approach; Motion pattern; Unexpected events, Motion estimation
note: cited By 0; Conference of 1st International Conference on Artificial Intelligence for Smart Community, AISC 2020 ; Conference Date: 17 December 2020 Through 18 December 2020; Conference Code:286319
abstract: At high-density crowd gatherings, people naturally escape from the region where any unexpected event happens. Escape in high-density crowds appears as a divergence pattern in the scene and timely detecting divergence patterns can save many human lives. In this paper, we propose to physically capture crowd normal and divergence motion patterns (or motion shapes) in form of images and train a shallow convolution neural network (CNN) on motion shape images for divergence behavior detection. Crowd motion pattern shape is obtained by extracting ridges of Lagrangian Coherent Structure (LCS) from the Finite-Time Lyapunov Exponent (FTLE) field and convert ridges into the grey-scale image. We also propose a divergence localization algorithm to pinpoint anomaly location(s). Experimentation is carried out on synthetic crowd datasets simulating normal and divergence behaviors at the high-density crowd. Comparison with state-of-the-art methods shows our method can obtain better accuracy for both divergence behavior detection and localization problems. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
date: 2022
publisher: Springer Science and Business Media Deutschland GmbH
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85142720874&doi=10.1007%2f978-981-16-2183-3_83&partnerID=40&md5=9c5c7d43a72376018a4bea17f89f3ae6
id_number: 10.1007/978-981-16-2183-3₈₃
full_text_status: none
publication: Lecture Notes in Electrical Engineering
volume: 758
pagerange: 875-888
refereed: TRUE
isbn: 9789811621826
issn: 18761100
citation:   Farooq, M.U. and Mohamad Saad, M.N. and Saleh, Y. and Daud Khan, S.  (2022) Deep Learning Approach for Divergence Behavior Detection at High Density Crowd.  Lecture Notes in Electrical Engineering, 758.  pp. 875-888.  ISSN 18761100