% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@INPROCEEDINGS{Alia:1008638,
author = {Alia, Ahmed and Maree, Mohammed and Chraibi, Mohcine},
title = {{A} {N}ovel {V}oronoi-based {C}onvolutional {N}eural
{N}etwork {A}pproach for {C}rowd {V}ideo {A}nalysis and
{P}ushing {P}erson {D}etection},
reportid = {FZJ-2023-02439},
year = {2023},
abstract = {At crowded event entrances, some individuals attempt to
push others to move quickly and enter the event faster. Such
behavior can increase the density over time, which could not
only threaten the comfort of pedestrians but also cause
life-threatening situations. To prevent such incidents,
event organizers and security personnel need to understand
the pushing dynamics in crowds. One effective way to achieve
this is by detecting pushing individuals from video
recordings of crowds. Recently, some automatic approaches
have been developed to help researchers identify pushing
behavior in crowd videos. However, these approaches only
detect the regions where pushing occurs rather than the
pushing individuals, limiting their contribution to
understanding pushing dynamics in crowds. To overcome the
limitations of previous methods, this work presents a novel
Voronoi-based Convolutional Neural Network (CNN) approach
for pushing person detection in crowd videos. As depicted in
Figure 1, the proposed approach comprises two main phases:
feature extraction and labeling. In the first phase, a new
Voronoi-based method is developed and utilized to identify
the local regions of individuals, employing both the video
and the associated trajectory data as inputs. It then uses
EfficientNetB0 CNN to extract the deep features of
individual behavior from the identified regions. In
contrast, the labeling phase utilizes a fully connected
layer with a Sigmoid activation function to analyze the
extracted deep features and identify the pushing persons.
Finally, this phase annotates the pushing persons in the
video. Furthermore, this work produces a novel dataset using
five real-world experiments with their associated ground
truths, which is utilized for training and evaluating the
proposed approach. The resulting dataset consists of 11717
local regions, of which 3067 represent pushing samples, and
8650 represent nonpushing samples. The experimental outcomes
demonstrate that the proposed approach attained an accuracy
of $83\%$ and a f1-score of $80\%.$},
month = {Jun},
date = {2023-06-12},
organization = {Helmholtz AI Conference 2023, Hamburg
(Germany), 12 Jun 2023 - 14 Jun 2023},
subtyp = {After Call},
cin = {IAS-7},
cid = {I:(DE-Juel1)IAS-7-20180321},
pnm = {5111 - Domain-Specific Simulation $\&$ Data Life Cycle Labs
(SDLs) and Research Groups (POF4-511) / Pilotprojekt zur
Entwicklung eines palästinensisch-deutschen Forschungs- und
Promotionsprogramms 'Palestinian-German Science Bridge'
(01DH16027)},
pid = {G:(DE-HGF)POF4-5111 / G:(BMBF)01DH16027},
typ = {PUB:(DE-HGF)6},
doi = {10.34734/FZJ-2023-02439},
url = {https://juser.fz-juelich.de/record/1008638},
}