EUVIMEDEUVIMED entdecken
Crossref

Comparative Evaluation of Yolo-Based Models for Multi-Class Weapon Detection

Selinay Erdinç, Mehmet Dikmen

Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering · 30.06.2026 · 68 (1) · 38-56

DOI: 10.33769/aupse.1772978 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering, online erschienen am 30.06.2026. Verfasst von Selinay Erdinç und 1 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study explores the effectiveness of various real-time object detectors for the problem of classifying different weapon types. To that end, the performance of YOLOv9, YOLOv10, YOLOv11, YOLOX, and YOLOR models were evaluated on a balanced dataset of 15,387 images across 5 weapon classes. All models are trained with 5-fold stratified cross-validation and YOLOR achieved the best overall performance with an mAP@0.5 of 0.8654 and mAP@0.5:0.95 of 0.8380. In addition, YOLOR obtained a precision of 0.8550, recall of 0.9570, and F1-score of 0.9210. Results show YOLOR’s suitability for high-precision, critical applications, while YOLOX offers advantages for recall-focused, resource-constrained deployments with a recall of 0.9628 despite a lower precision of 0.6902. The experiments highlighted the potential of real-time AI-based object detectors for enhancing security systems.

Zitieren

APA

Erdinç, S., & Dikmen, M. (2026). Comparative Evaluation of Yolo-Based Models for Multi-Class Weapon Detection. Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering, 68(1), 38-56. https://doi.org/10.33769/aupse.1772978

Vancouver

Erdinç S, Dikmen M. Comparative Evaluation of Yolo-Based Models for Multi-Class Weapon Detection. Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering. 2026;68(1):38-56. doi:10.33769/aupse.1772978

BibTeX
@article{Erdin2026,
  author = {Erdinç, Selinay and Dikmen, Mehmet},
  title = {Comparative Evaluation of Yolo-Based Models for Multi-Class Weapon Detection},
  journal = {Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering},
  year = {2026},
  volume = {68},
  number = {1},
  pages = {38--56},
  doi = {10.33769/aupse.1772978}
}
Kostenlos starten →