Violence Detection: A Serious-Gaming Approach

Derkjan Elzinga, Stan Ruessink, Giuseppe Cascavilla, Damian Tamburri, Francesco Leotta, Massimo Mecella, Willem-Jan Van Den Heuvel

2024

Abstract

Widespread use of IoT, like surveillance cameras, raises privacy concerns in citizens’ lives. However, limited studies explore AI-based automatic recognition of criminal incidents due to a lack of real data, constrained by legal and privacy regulations, preventing effective training and testing of deep learning models. To address dataset limitations, we propose using generative technology and virtual gaming data, such as the Grand Theft Auto (GTA-V) platform. However, it’s unclear if synthetic data accurately mirrors real-world videos for effective deep learning model performance. This research aims to explore the potential of identifying criminal scenarios using deep learning models based on gaming data. We propose a deep-learning violence detection framework using virtual gaming data. The 3-stage deep learning model focuses on person identification and violence activity recognition. We introduce a new dataset for supervised training and find virtual persons closely resembling real-world individuals. Our research demonstrates a 15% higher accuracy in identifying violent scenarios compared to three established real-world datasets, showcasing the effectiveness of a serious gaming approach.

Paper Citation

in Harvard Style

Elzinga D., Ruessink S., Cascavilla G., Tamburri D., Leotta F., Mecella M. and Van Den Heuvel W. (2024). Violence Detection: A Serious-Gaming Approach. In Proceedings of the 21st International Conference on Security and Cryptography - Volume 1: SECRYPT; ISBN 978-989-758-709-2, SciTePress, pages 163-174. DOI: 10.5220/0012762300003767

in Bibtex Style

@conference{secrypt24,
author={Derkjan Elzinga and Stan Ruessink and Giuseppe Cascavilla and Damian Tamburri and Francesco Leotta and Massimo Mecella and Willem-Jan Van Den Heuvel},
title={Violence Detection: A Serious-Gaming Approach},
booktitle={Proceedings of the 21st International Conference on Security and Cryptography - Volume 1: SECRYPT},
year={2024},
pages={163-174},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012762300003767},
isbn={978-989-758-709-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 21st International Conference on Security and Cryptography - Volume 1: SECRYPT
TI - Violence Detection: A Serious-Gaming Approach
SN - 978-989-758-709-2
AU - Elzinga D.
AU - Ruessink S.
AU - Cascavilla G.
AU - Tamburri D.
AU - Leotta F.
AU - Mecella M.
AU - Van Den Heuvel W.
PY - 2024
SP - 163
EP - 174
DO - 10.5220/0012762300003767
PB - SciTePress