EUVIMEDEUVIMED entdecken
Crossref

A Lightweight Safety Helmet Compliance Detection via Multimodal Fusion (Student Abstract)

Jeong Hwan Ryu, Azimjon Akhtamov, Md Azher Uddin, Aziz Nasridinov

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41373-41374

DOI: 10.1609/aaai.v40i48.42274 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Jeong Hwan Ryu und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Ensuring proper use of personal protective equipment (PPE), especially helmets, is essential for workplace safety. Conventional object detectors often fail to distinguish whether a helmet is worn correctly, and existing approaches relying on single-model pipelines are prone to localization errors and false alarms. Moreover, most prior studies do not guarantee real-time performance. To resolve these challenges, we propose a lightweight multimodal approach that integrates a YOLO11-based object detector with a pose estimation model, achieving higher F1 scores and lower false alarm rates while maintaining real-time performance.

Zitieren

APA

Ryu, J. H., Akhtamov, A., Uddin, M. A., & Nasridinov, A. (2026). A Lightweight Safety Helmet Compliance Detection via Multimodal Fusion (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41373-41374. https://doi.org/10.1609/aaai.v40i48.42274

Vancouver

Ryu JH, Akhtamov A, Uddin MA, Nasridinov A. A Lightweight Safety Helmet Compliance Detection via Multimodal Fusion (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41373-41374. doi:10.1609/aaai.v40i48.42274

BibTeX
@article{Ryu2026,
  author = {Ryu, Jeong Hwan and Akhtamov, Azimjon and Uddin, Md Azher and Nasridinov, Aziz},
  title = {A Lightweight Safety Helmet Compliance Detection via Multimodal Fusion (Student Abstract)},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {48},
  pages = {41373--41374},
  doi = {10.1609/aaai.v40i48.42274}
}
Kostenlos starten →