EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Early Detection of Aggressive Human Behavior in Video Streams Using Deep Spatiotemporal Models

Aida Issembayeva, Anargul Shaushenova, Ardak Nurpeisova, Aidar Ispussinov, Buldyryk Suleimenova, Anargul Bekenova, Aliya Satybaldieva, Aigul Zholmukhanova, Galiya Mauina

Computers · 23.04.2026 · 15 (5) · 267

DOI: 10.3390/computers15050267 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computers, online erschienen am 23.04.2026. Verfasst von Aida Issembayeva und 8 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science Committee of the Ministry of Science and Higher Education of the Republic of Kazakhstan.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this paper, we propose a spatiotemporal approach for binary classification of violent and non-violent behavior in real-world settings. The experimental pipeline includes video preprocessing, stratified data splitting, generation of temporally structured clips, and comparative evaluation of baseline models, including a convolutional neural network. We also developed a Residual Adaptive Motion Temporal Binary Heat Network model that combines frame color characteristics, residual motion descriptions, temporal feature fusion, an early risk assessment mechanism, and interpretable localization maps. Experiments were conducted on a balanced dataset of 2000 video clips. The proposed model demonstrated the best early warning performance: a supervision rate of 0.6, an F1 score of 0.9527, and a balanced accuracy of 0.9533. With full supervision, the F1 score was 0.9342, and the area under the receiver operating characteristic curve (AUC) was 0.9871. The practical significance of the work is that the proposed approach can be used as a decision support tool for the preliminary identification of potentially dangerous video fragments with subsequent manual verification, without the assumption of autonomous use in high-risk scenarios.

Förderung

  • Science Committee of the Ministry of Science and Higher Education of the Republic of Kazakhstan

Zitieren

APA

Issembayeva, A., Shaushenova, A., Nurpeisova, A., Ispussinov, A., Suleimenova, B., Bekenova, A., Satybaldieva, A., Zholmukhanova, A., & Mauina, G. (2026). Early Detection of Aggressive Human Behavior in Video Streams Using Deep Spatiotemporal Models. Computers, 15(5), 267. https://doi.org/10.3390/computers15050267

Vancouver

Issembayeva A, Shaushenova A, Nurpeisova A, Ispussinov A, Suleimenova B, Bekenova A, et al. Early Detection of Aggressive Human Behavior in Video Streams Using Deep Spatiotemporal Models. Computers. 2026;15(5):267. doi:10.3390/computers15050267

BibTeX
@article{Issembayeva2026,
  author = {Issembayeva, Aida and Shaushenova, Anargul and Nurpeisova, Ardak and Ispussinov, Aidar and Suleimenova, Buldyryk and Bekenova, Anargul and Satybaldieva, Aliya and Zholmukhanova, Aigul and Mauina, Galiya},
  title = {Early Detection of Aggressive Human Behavior in Video Streams Using Deep Spatiotemporal Models},
  journal = {Computers},
  year = {2026},
  volume = {15},
  number = {5},
  pages = {267},
  doi = {10.3390/computers15050267}
}
Kostenlos starten →