Deep Learning Approaches for Enhanced Oasis Fire Detection
Mathematical Modeling and Computing · 2026 · 13 (2) · 510-517
DOI: 10.23939/mmc2026.02.510 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematical Modeling and Computing, 2026. Verfasst von M. Benzyane und 3 weiteren Autor:innen. Die Arbeit nennt 20 Literaturangaben.
Abstract (Originalsprache)
Accurate fire detection is essential for timely intervention and minimizing damage. This article offers an in-depth comparative study of advanced object detection models for oasis fire detection, including YOLOv6, YOLOv7, YOLOv8, and Faster R-CNN. We leverage a carefully curated dataset featuring diverse fire scenarios to train and fine-tune each model, optimizing its performance. To evaluate the models' effectiveness in accurately identifying and localizing fire instances, we focus on key metrics such as recall, precision, and mAP. Our analysis also examines detection speed, model complexity, and resource requirements. The results of our experiments show that YOLOv8 outperforms the other YOLO versions and Faster R-CNN. These findings offer valuable insights for researchers and practitioners, guiding the selection of the most suitable model for fire detection applications and contributing to advancements in fire detection systems, bridging the gap between computer vision technology and fire safety applications.
Zitieren
APA
Benzyane, M., Agoujil, S., Abdullah, M. A., & Alabdulatif, A. (2026). Deep Learning Approaches for Enhanced Oasis Fire Detection. Mathematical Modeling and Computing, 13(2), 510-517. https://doi.org/10.23939/mmc2026.02.510
Vancouver
Benzyane M, Agoujil S, Abdullah MA, Alabdulatif A. Deep Learning Approaches for Enhanced Oasis Fire Detection. Mathematical Modeling and Computing. 2026;13(2):510-517. doi:10.23939/mmc2026.02.510
BibTeX
@article{Benzyane2026,
author = {Benzyane, M. and Agoujil, S. and Abdullah, M. Alnajim and Alabdulatif, A.},
title = {Deep Learning Approaches for Enhanced Oasis Fire Detection},
journal = {Mathematical Modeling and Computing},
year = {2026},
volume = {13},
number = {2},
pages = {510--517},
doi = {10.23939/mmc2026.02.510}
}
EUVIMED