EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

FSD-YOLO26: A Fire and Smoke Detection Method Based on YOLO26 for Forest Wildfire Detection

Dan Shan, Zanqi Qiu, Carlos Ferran, Xuan Tong, Dongming Liu

Sensors · 12.11.2026 · 26 (22) · 7139

DOI: 10.3390/s26227139 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 12.11.2026. Verfasst von Dan Shan und 4 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Department of Science and Technology of Liaoning Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Forest fires pose a serious threat to ecological environments and public safety, while reliable fire and smoke detection remains challenging due to small target scales, diffuse smoke boundaries, complex vegetation backgrounds, and substantial variations in target appearance. This study aims to develop a lightweight and effective object detection framework for forest fire and smoke detection by enhancing fine-grained feature representation, spatial-semantic contextual modeling, and multi-scale feature interaction. To achieve this objective, FSD-YOLO26 is developed based on YOLO26n. A Fine-grained Feature Enhancement Module (FFEM) is introduced to strengthen the representation of small and fine-grained fire features. A Spatial-Semantic Context Enhancement Module (SSCEM) is designed to enhance spatial-semantic representation for diffuse and irregular smoke regions. Furthermore, a Dynamic Multi-scale Enhancement Fusion Module (DEMF) is proposed to improve multi-scale feature interaction and utilization under complex forest backgrounds. Under a consistent training protocol with 100 training epochs, a batch size of 10, and the AdamW optimizer with cosine learning-rate scheduling, the proposed method is evaluated on the FASDD, Multi-Scene Forest Fire-Smoke Dataset (MSFFSD), and D-Fire2 datasets using comparative, ablation, class-specific, scale-aware, and visualization experiments. On FASDD, FSD-YOLO26 achieves 77.74% Precision, 74.82% Recall, 83.23% mAP@0.5, and 56.76% mAP@0.5:0.95, improving the corresponding mAP@0.5 and mAP@0.5:0.95 of YOLO26n by 4.79 and 5.74 percentage points, respectively. On MSFFSD, the proposed method achieves 89.40% Precision, 83.12% Recall, 89.87% mAP@0.5, and 69.76% mAP@0.5:0.95, while on D-Fire2 it obtains 76.25% Precision, 68.23% Recall, 72.88% mAP@0.5, and 51.46% mAP@0.5:0.95. The ablation, comparative, class-specific, scale-aware, and visualization experiments further demonstrate the effectiveness of the proposed modules. With 3.04 M parameters, 6.0 GFLOPs, and an inference speed of 79.33 FPS, FSD-YOLO26 provides a lightweight solution for forest fire and smoke detection.

Förderung

  • Department of Science and Technology of Liaoning Province

Zitieren

APA

Shan, D., Qiu, Z., Ferran, C., Tong, X., & Liu, D. (2026). FSD-YOLO26: A Fire and Smoke Detection Method Based on YOLO26 for Forest Wildfire Detection. Sensors, 26(22), 7139. https://doi.org/10.3390/s26227139

Vancouver

Shan D, Qiu Z, Ferran C, Tong X, Liu D. FSD-YOLO26: A Fire and Smoke Detection Method Based on YOLO26 for Forest Wildfire Detection. Sensors. 2026;26(22):7139. doi:10.3390/s26227139

BibTeX
@article{Shan2026,
  author = {Shan, Dan and Qiu, Zanqi and Ferran, Carlos and Tong, Xuan and Liu, Dongming},
  title = {FSD-YOLO26: A Fire and Smoke Detection Method Based on YOLO26 for Forest Wildfire Detection},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {22},
  pages = {7139},
  doi = {10.3390/s26227139}
}
Kostenlos starten →