CSAF-YOLO: An Improved Smoke and Fire Object Detection Algorithm for Complex Scenes Based on YOLOv11n
Informatica · 06.08.2026 · 50 (14)
DOI: 10.31449/inf.v50i14.14573 ↗Kurz gefasst
Fachartikel in der Zeitschrift Informatica, online erschienen am 06.08.2026. Verfasst von Yuanpan Zheng und 4 weiteren Autor:innen.
Abstract (Originalsprache)
Early detection of flames and smoke is crucial for fire warning systems, yet blurred smoke boundaries, small-scale targets, and complex background interference still limit existing methods. This paper proposes CSAF-YOLO, an improved detection model based on YOLOv11n. A C3-MCG module is introduced into the backbone to enhance multi-scale contextual feature representation. A DB-SAFM module is designed in the feature fusion stage to improve semantic and spatial feature alignment through a dual-branch self-attention mechanism. AWHIoU is adopted as the loss function, combined with a bi-phase focusing strategy and a scale-adaptive weighting mechanism to achieve adaptive optimisation for sampl0065s with different IoU qualities and targets of different scales. Experimental results show that CSAF-YOLO significantly improves detection performance over mainstream models, achieving 2.2% and 2.3% gains in precision and mAP50 over YOLOv11n, respectively, while maintaining a high FPS of 177.75, demonstrating strong potential for complex monitoring and real-time detection.
Zitieren
APA
Zheng, Y., Wang, C., Zhang, Y., Liu, X., & Zhong, W. (2026). CSAF-YOLO: An Improved Smoke and Fire Object Detection Algorithm for Complex Scenes Based on YOLOv11n. Informatica, 50(14). https://doi.org/10.31449/inf.v50i14.14573
Vancouver
Zheng Y, Wang C, Zhang Y, Liu X, Zhong W. CSAF-YOLO: An Improved Smoke and Fire Object Detection Algorithm for Complex Scenes Based on YOLOv11n. Informatica. 2026;50(14). doi:10.31449/inf.v50i14.14573
BibTeX
@article{Zheng2026,
author = {Zheng, Yuanpan and Wang, Chao and Zhang, Yu and Liu, Xuhang and Zhong, Wenbin},
title = {CSAF-YOLO: An Improved Smoke and Fire Object Detection Algorithm for Complex Scenes Based on YOLOv11n},
journal = {Informatica},
year = {2026},
volume = {50},
number = {14},
doi = {10.31449/inf.v50i14.14573}
}
EUVIMED