EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Conv3D-Based Video Violence Detection Network Using Optical Flow and RGB Data

Jae-Hyuk Park, Mohamed Mahmoud iD, Hyun-Soo Kang iD

Sensors · 05.01.2024 · 24 (2) · 317

DOI: 10.3390/s24020317 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 05.01.2024. Verfasst von Jae-Hyuk Park und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information and Communication Engineering, School of Electrical and Computer Engineering, Chungbuk National University, Cheongju-si 286…. Hauptthemen laut MEDLINE: Optic Flow. Die Arbeit wurde bisher 44-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Technology development Program of MSS, MSIT(Ministry of Science and ICT), Korea, under the Grand Information Technology Research Center support program, MSIT (Ministry of Science and ICT), Korea.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Detecting violent behavior in videos to ensure public safety and security poses a significant challenge. Precisely identifying and categorizing instances of violence in real-life closed-circuit television, which vary across specifications and locations, requires comprehensive understanding and processing of the sequential information embedded in these videos. This study aims to introduce a model that adeptly grasps the spatiotemporal context of videos within diverse settings and specifications of violent scenarios. We propose a method to accurately capture spatiotemporal features linked to violent behaviors using optical flow and RGB data. The approach leverages a Conv3D-based ResNet-3D model as the foundational network, capable of handling high-dimensional video data. The efficiency and accuracy of violence detection are enhanced by integrating an attention mechanism, which assigns greater weight to the most crucial frames within the RGB and optical-flow sequences during instances of violence. Our model was evaluated on the UBI-Fight, Hockey, Crowd, and Movie-Fights datasets; the proposed method outperformed existing state-of-the-art techniques, achieving area under the curve scores of 95.4, 98.1, 94.5, and 100.0 on the respective datasets. Moreover, this research not only has the potential to be applied in real-time surveillance systems but also promises to contribute to a broader spectrum of research in video analysis and understanding.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Optic FlowViolenceComputer Systems

Stichwörter der Autor:innen

CCTV anomaly detectionattention networkdeep learningoptical flow

Autor:innen und Institutionen

  • Department of Information and Communication Engineering, School of Electrical and Computer Engineering, Chungbuk National University, Cheongju-si 28644, Republic of Korea.
  • Information Technology Department, Faculty of Computers and Information, Assiut University, Assiut 71515, Egypt.

ORCID-Profile: Mohamed Mahmoud, Hyun-Soo Kang

Förderung

  • Technology development Program of MSS
  • MSIT(Ministry of Science and ICT), Korea, under the Grand Information Technology Research Center support program
  • MSIT (Ministry of Science and ICT), Korea

Zitieren

APA

Park, J. H., Mahmoud, M., & Kang, H. S. (2024). Conv3D-Based Video Violence Detection Network Using Optical Flow and RGB Data. Sensors, 24(2), 317. https://doi.org/10.3390/s24020317

Vancouver

Park JH, Mahmoud M, Kang HS. Conv3D-Based Video Violence Detection Network Using Optical Flow and RGB Data. Sensors. 2024;24(2):317. doi:10.3390/s24020317

BibTeX
@article{Park2024,
  author = {Park, Jae-Hyuk and Mahmoud, Mohamed and Kang, Hyun-Soo},
  title = {Conv3D-Based Video Violence Detection Network Using Optical Flow and RGB Data},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {2},
  pages = {317},
  doi = {10.3390/s24020317}
}
Kostenlos starten →