EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Efficient Human Violence Recognition for Surveillance in Real Time

Herwin Alayn Huillcen Baca iD, Flor de Luz Palomino Valdivia iD, Juan Carlos Gutierrez Caceres iD

Sensors · 2024

DOI: 10.3390/s24020668 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2024. Verfasst von Herwin Alayn Huillcen Baca und 2 weiteren Autor:innen. Beteiligte Einrichtung: Academic Department of Engineering and Information Technology, Professional School of Systems Engineering, Faculty of Engineering, Jose Maria Argueda…. Hauptthemen laut MEDLINE: Violence, Movement. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universidad Nacional José María Arguedas, Jose Maria Arguedas National University, Peru.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human violence recognition is an area of great interest in the scientific community due to its broad spectrum of applications, especially in video surveillance systems, because detecting violence in real time can prevent criminal acts and save lives. The majority of existing proposals and studies focus on result precision, neglecting efficiency and practical implementations. Thus, in this work, we propose a model that is effective and efficient in recognizing human violence in real time. The proposed model consists of three modules: the Spatial Motion Extractor (SME) module, which extracts regions of interest from a frame; the Short Temporal Extractor (STE) module, which extracts temporal characteristics of rapid movements; and the Global Temporal Extractor (GTE) module, which is responsible for identifying long-lasting temporal features and fine-tuning the model. The proposal was evaluated for its efficiency, effectiveness, and ability to operate in real time. The results obtained on the Hockey, Movies, and RWF-2000 datasets demonstrated that this approach is highly efficient compared to various alternatives. In addition, the VioPeru dataset was created, which contains violent and non-violent videos captured by real video surveillance cameras in Peru, to validate the real-time applicability of the model. When tested on this dataset, the effectiveness of our model was superior to the best existing models.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ViolenceMovementHumansMotionRecognition, PsychologyVideotape Recording

Stichwörter der Autor:innen

VioPeruglobal temporal extractorhuman violence recognitionreal timeshort temporal extractorspatial attentionspatial motion extractorvideo surveillance

Autor:innen und Institutionen

  • Academic Department of Engineering and Information Technology, Professional School of Systems Engineering, Faculty of Engineering, Jose Maria Arguedas National University, Andahuaylas 03701, Peru.
  • Academic Department of Systems and Informatics Engineering, Professional School of Computer Science, Faculty of Production and Services Engineering, San Agustin of Arequipa National University, Arequipa 04001, Peru.

ORCID-Profile: Herwin Alayn Huillcen Baca, Flor de Luz Palomino Valdivia, Juan Carlos Gutierrez Caceres

Förderung

  • Universidad Nacional José María Arguedas
  • Jose Maria Arguedas National University, Peru

Zitieren

APA

Huillcen Baca, H. A., Palomino Valdivia, F. L., & Gutierrez Caceres, J. C. (2024). Efficient Human Violence Recognition for Surveillance in Real Time. Sensors. https://doi.org/10.3390/s24020668

Vancouver

Huillcen Baca HA, Palomino Valdivia FL, Gutierrez Caceres JC. Efficient Human Violence Recognition for Surveillance in Real Time. Sensors. 2024. doi:10.3390/s24020668

BibTeX
@article{HuillcenBaca2024,
  author = {Huillcen Baca, Herwin Alayn and Palomino Valdivia, Flor de Luz and Gutierrez Caceres, Juan Carlos},
  title = {Efficient Human Violence Recognition for Surveillance in Real Time},
  journal = {Sensors},
  year = {2024},
  doi = {10.3390/s24020668}
}
Kostenlos starten →