EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ASCA-YOLO: Adaptive Sparse and Context-Aware YOLO Algorithm for Forest Wildfire Detection

Yu Hao, Kangning Wang, Li Zhang iD, Zibo Yuan

Sensors · 29.05.2026 · 26 (11) · 3444

DOI: 10.3390/s26113444 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 29.05.2026. Verfasst von Yu Hao und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Airspace Science and Engineering, Shandong University, Weihai 264209, China. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shandong Provincial Nature Science Foundation, Nation Natural Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Combining Unmanned Aerial Vehicle (UAV) remote sensing with computer vision has become an efficient approach to detect forest wildfires. Nevertheless, existing methods still face several challenges, including missed detection of small fire spots and slender smoke under limited computational resources, false alarms caused by complex forest backgrounds, and insufficient adaptability to the irregular and dynamic morphology of fire and smoke. To address these issues, an improved YOLO26-based model, termed ASCA-YOLO, is proposed. Specifically, FWAMSConv module is introduced to improve multi-scale indicator representation of small and sparse targets. In addition, FWSCSAttention mechanism is designed to reduce background interference by modeling contextual feature distributions. Moreover, FWASIoU loss is developed to improve bounding box regression for non-rigid targets. The experimental evaluation indicates that, relative to YOLO26, the proposed model decreases the parameter count and FLOPs by 19.2% and 21.3%, respectively. Meanwhile, recall reaches 0.809 and precision reaches 0.870, indicating improved detection performance under complex conditions. In addition, mAP50-95 is improved by 12.9%, reflecting more stable localization for irregular wildfire targets. Overall, ASCA-YOLO attains a better equilibrium between detection quality and computational cost than several mainstream object detection models, indicating its potential for real-time UAV-based wildfire monitoring.

Schlagwörter

Stichwörter der Autor:innen

IoU-based lossUAVYOLO26contextual saliency attentionmulti-scale feature representationwildfire detection

Autor:innen und Institutionen

  • School of Airspace Science and Engineering, Shandong University, Weihai 264209, China.
  • Shandong Key Laboratory of Intelligent Electronic Packaging Test and Application, Shandong University, Weihai 264209, China.
  • Discipline Inspection and Supervision School, Shandong University, Weihai 264209, China.

ORCID-Profile: Li Zhang

Förderung

  • Shandong Provincial Nature Science Foundation
  • Nation Natural Science Foundation

Zitieren

APA

Hao, Y., Wang, K., Zhang, L., & Yuan, Z. (2026). ASCA-YOLO: Adaptive Sparse and Context-Aware YOLO Algorithm for Forest Wildfire Detection. Sensors, 26(11), 3444. https://doi.org/10.3390/s26113444

Vancouver

Hao Y, Wang K, Zhang L, Yuan Z. ASCA-YOLO: Adaptive Sparse and Context-Aware YOLO Algorithm for Forest Wildfire Detection. Sensors. 2026;26(11):3444. doi:10.3390/s26113444

BibTeX
@article{Hao2026,
  author = {Hao, Yu and Wang, Kangning and Zhang, Li and Yuan, Zibo},
  title = {ASCA-YOLO: Adaptive Sparse and Context-Aware YOLO Algorithm for Forest Wildfire Detection},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {11},
  pages = {3444},
  doi = {10.3390/s26113444}
}
Kostenlos starten →