EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Lightweight Fire and Smoke Detection with YOLO11: A Two-Benchmark, Multi-Seed Study of Wise-IoU and GhostConv

Tang Tang, Xinsheng Jiang, Biao He, Dongliang Zhou, Run Li, Keyu Lin, Yunxiong Cai

Fire · 06.09.2026 · 9 (9) · 386

DOI: 10.3390/fire9090386 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Fire, online erschienen am 06.09.2026. Verfasst von Tang Tang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Chongqing Technology Innovation and Application Development Special Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Vision-based fire and smoke detection must be both accurate and lightweight for edge cameras and unmanned aerial vehicles (UAVs). Most lightweight fire detectors, however, are validated on a single dataset from a single run, which leaves the accuracy–efficiency trade-off and its external validity only partially examined. Rather than a new state of the art, we take an evaluation-centered stance and study two lightweight operating points of YOLO11n: an accuracy-first variant (LFS-YOLO11-A) that adopts the Wise-IoU (WIoU) loss at no extra parameters, and a lightweight variant (LFS-YOLO11-B) that further adds GhostConv. Both are evaluated on the public D-Fire dataset, retrained on a second dataset (DFS) over eight seeds, and profiled across GPU/CPU under PyTorch and ONNX Runtime. LFS-YOLO11-A matches the baseline on D-Fire (mAP@0.5 0.760 versus 0.758), while LFS-YOLO11-B reduces parameters by 12.4% and computation by 11%, both exceeding 160 FPS end-to-end (batch = 1) on a desktop-class GPU. On DFS, WIoU yields a small, exploratory +0.6-point improvement (nominal paired p = 0.037; seed-sensitive, with a confidence interval lower bound near zero), whereas an apparent +6.1-point gain from an early, uncontrolled run proved to be train/test contamination introduced before the data pipeline was frozen, not a genuine effect. Frozen-pipeline, multi-seed, two-benchmark evaluation is therefore necessary to separate genuine effects from the artifacts of uncontrolled single runs in lightweight fire and smoke detection.

Förderung

  • Chongqing Technology Innovation and Application Development Special Project

Zitieren

APA

Tang, T., Jiang, X., He, B., Zhou, D., Li, R., Lin, K., & Cai, Y. (2026). Lightweight Fire and Smoke Detection with YOLO11: A Two-Benchmark, Multi-Seed Study of Wise-IoU and GhostConv. Fire, 9(9), 386. https://doi.org/10.3390/fire9090386

Vancouver

Tang T, Jiang X, He B, Zhou D, Li R, Lin K, et al. Lightweight Fire and Smoke Detection with YOLO11: A Two-Benchmark, Multi-Seed Study of Wise-IoU and GhostConv. Fire. 2026;9(9):386. doi:10.3390/fire9090386

BibTeX
@article{Tang2026,
  author = {Tang, Tang and Jiang, Xinsheng and He, Biao and Zhou, Dongliang and Li, Run and Lin, Keyu and Cai, Yunxiong},
  title = {Lightweight Fire and Smoke Detection with YOLO11: A Two-Benchmark, Multi-Seed Study of Wise-IoU and GhostConv},
  journal = {Fire},
  year = {2026},
  volume = {9},
  number = {9},
  pages = {386},
  doi = {10.3390/fire9090386}
}
Kostenlos starten →