EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Indoor fire and smoke detection based on optimized YOLOv5

Md Shafak Shahriar Sozol, M Rubaiyat Hossain Mondal iD, Achmad Husni Thamrin

PLOS One · 29.04.2025 · 20 (4) · e0322052

DOI: 10.1371/journal.pone.0322052 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 29.04.2025. Verfasst von Md Shafak Shahriar Sozol und 2 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Information and Communication Technology, Bangladesh University of Engineering and Technology, Dhaka, Bangladesh. Hauptthemen laut MEDLINE: Fires, Smoke, Environmental Monitoring. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Ensuring safety and safeguarding indoor properties require reliable fire detection methods. Traditional detection techniques that use smoke, heat, or fire sensors often fail due to false positives and slow response time. Existing deep learning-based object detectors fall short of improved accuracy in indoor settings and real-time tracking, considering the dynamic nature of fire and smoke. This study aimed to address these challenges in fire and smoke detection in indoor settings. It presents a hyperparameter-optimized YOLOv5 (HPO-YOLOv5) model optimized by a genetic algorithm. To cover all prospective scenarios, we created a novel dataset comprising indoor fire and smoke images. There are 5,000 images in the dataset, split into training, validation, and testing samples at a ratio of 80:10:10. It also used the Grad-CAM technique to provide visual explanations for model predictions, ensuring interpretability and transparency. This research combined YOLOv5 with DeepSORT (which uses deep learning features to improve the tracking of objects over time) to provide real-time monitoring of fire progression. Thus, it allows for the notification of actual fire hazards. With a mean average precision ( mAP@0.5 ) of 92.1%, the HPO-YOLOv5 model outperformed state-of-the-art models, including Faster R-CNN, YOLOv5, YOLOv7 and YOLOv8. The proposed model achieved a 2.4% improvement in mAP@0.5 over the original YOLOv5 baseline model. The research has laid the foundation for future developments in fire hazard detection technology, a system that is dependable and effective in indoor scenarios.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

FiresSmokeEnvironmental MonitoringAlgorithmsDeep LearningHumans

Substanzen

Smoke

Autor:innen und Institutionen

  • Institute of Information and Communication Technology, Bangladesh University of Engineering and Technology, Dhaka, Bangladesh.
  • Keio University, Japan.

ORCID-Profile: M Rubaiyat Hossain Mondal

Zitieren

APA

Sozol, M. S. S., Mondal, M. R. H., & Thamrin, A. H. (2025). Indoor fire and smoke detection based on optimized YOLOv5. PLOS One, 20(4), e0322052. https://doi.org/10.1371/journal.pone.0322052

Vancouver

Sozol MSS, Mondal MRH, Thamrin AH. Indoor fire and smoke detection based on optimized YOLOv5. PLOS One. 2025;20(4):e0322052. doi:10.1371/journal.pone.0322052

BibTeX
@article{Sozol2025,
  author = {Sozol, Md Shafak Shahriar and Mondal, M Rubaiyat Hossain and Thamrin, Achmad Husni},
  title = {Indoor fire and smoke detection based on optimized YOLOv5},
  journal = {PLOS One},
  year = {2025},
  volume = {20},
  number = {4},
  pages = {e0322052},
  doi = {10.1371/journal.pone.0322052}
}
Kostenlos starten →