EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Cross-Domain Fire Detection Across Indoor and Outdoor Scenes

Jingxiang Li, Xuenong Gao, Mingyang Xu, Jinzhao Zhang iD, Zhifeng Liu, Ruikang Luo

Sensors · 10.05.2026 · 26 (10) · 3008

DOI: 10.3390/s26103008 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 10.05.2026. Verfasst von Jingxiang Li und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Chemistry and Chemical Engineering, South China University of Technology, Guangzhou 510640, China. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Robotic Innovation Research Fund, Nanyang Technological University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Vision-based fire detection is highly sensitive to domain shifts between indoor and outdoor scenes, which often degrades the generalization of supervised models trained on a single domain. To study this problem, the Fire Detection Dataset is curated from multiple public sources as a large-scale benchmark for cross-domain fire and smoke recognition. Cross-domain deployment faces two main challenges: substantial appearance variations in fire and smoke, and highly diverse negative classes that can easily trigger false alarms. To address these issues, a tailored cross-domain framework is studied by combining adversarial alignment and discrepancy-based statistical alignment to learn more domain-invariant features and mitigate negative transfer. Experimental results show that domain adaptation substantially improves target-domain generalization over weak alignment baselines. In particular, Domain-Adversarial Neural Networks (DANN) achieve 89.44% accuracy on Indoor → Outdoor and 79.10% on Outdoor → Indoor, while Multi-Kernel Maximum Mean Discrepancy (MK-MMD) attains the best fire-class F1-score of 78.04% on Outdoor → Indoor. These results highlight the value of domain alignment for improving robust fire detection across heterogeneous deployment environments.

Schlagwörter

Stichwörter der Autor:innen

domain adaptationfire detectionfire detection dataset

Autor:innen und Institutionen

  • School of Chemistry and Chemical Engineering, South China University of Technology, Guangzhou 510640, China.
  • School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore 639798, Singapore.

ORCID-Profile: Jinzhao Zhang

Förderung

  • Robotic Innovation Research Fund, Nanyang Technological University

Zitieren

APA

Li, J., Gao, X., Xu, M., Zhang, J., Liu, Z., & Luo, R. (2026). Cross-Domain Fire Detection Across Indoor and Outdoor Scenes. Sensors, 26(10), 3008. https://doi.org/10.3390/s26103008

Vancouver

Li J, Gao X, Xu M, Zhang J, Liu Z, Luo R. Cross-Domain Fire Detection Across Indoor and Outdoor Scenes. Sensors. 2026;26(10):3008. doi:10.3390/s26103008

BibTeX
@article{Li2026,
  author = {Li, Jingxiang and Gao, Xuenong and Xu, Mingyang and Zhang, Jinzhao and Liu, Zhifeng and Luo, Ruikang},
  title = {Cross-Domain Fire Detection Across Indoor and Outdoor Scenes},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {10},
  pages = {3008},
  doi = {10.3390/s26103008}
}
Kostenlos starten →