EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multimodal Fire Salient Object Detection for Unregistered Data in Real-World Scenarios

Ning Sun, Jianmeng Zhou, Kai Hu, Chen Wei, Zihao Wang, Lipeng Song

Fire · 26.10.2025 · 8 (11) · 415

DOI: 10.3390/fire8110415 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Fire, online erschienen am 26.10.2025. Verfasst von Ning Sun und 5 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jiangsu Postgraduate Innovation Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In real-world fire scenarios, complex lighting conditions and smoke interference significantly challenge the accuracy and robustness of traditional fire detection systems. Fusion of complementary modalities, such as visible light (RGB) and infrared (IR), is essential to enhance detection robustness. However, spatial shifts and geometric distortions occur in multi-modal image pairs collected by multi-source sensors due to installation deviations and inconsistent intrinsic parameters. Existing multi-modal fire detection frameworks typically depend on pre-registered data, which struggles to handle modal misalignment in practical deployment. To overcome this limitation, we propose an end-to-end multi-modal Fire Salient Object Detection framework capable of dynamically fusing cross-modal features without pre-registration. Specifically, the Channel Cross-enhancement Module (CCM) facilitates semantic interaction across modalities in salient regions, suppressing noise from spatial misalignment. The Deformable Alignment Module (DAM) achieves adaptive correction of geometric deviations through cascaded deformation compensation and dynamic offset learning. For validation, we constructed an unregistered indoor fire dataset (Indoor-Fire) covering common fire scenarios. Generalizability was further evaluated on an outdoor dataset (RGB-T Wildfire). To fully validate the effectiveness of the method in complex building fire scenarios, we conducted experiments using the Fire in historic buildings (Fire in historic buildings) dataset. Experimental results demonstrate that the F1-score reaches 83% on both datasets, with the IoU maintained above 70%. Notably, while maintaining high accuracy, the number of parameters (91.91 M) is only 28.1% of the second-best SACNet (327 M). This method provides a robust solution for unaligned or weakly aligned modal fusion caused by sensor differences and is highly suitable for deployment in intelligent firefighting systems.

Förderung

  • Jiangsu Postgraduate Innovation Project

Zitieren

APA

Sun, N., Zhou, J., Hu, K., Wei, C., Wang, Z., & Song, L. (2025). Multimodal Fire Salient Object Detection for Unregistered Data in Real-World Scenarios. Fire, 8(11), 415. https://doi.org/10.3390/fire8110415

Vancouver

Sun N, Zhou J, Hu K, Wei C, Wang Z, Song L. Multimodal Fire Salient Object Detection for Unregistered Data in Real-World Scenarios. Fire. 2025;8(11):415. doi:10.3390/fire8110415

BibTeX
@article{Sun2025,
  author = {Sun, Ning and Zhou, Jianmeng and Hu, Kai and Wei, Chen and Wang, Zihao and Song, Lipeng},
  title = {Multimodal Fire Salient Object Detection for Unregistered Data in Real-World Scenarios},
  journal = {Fire},
  year = {2025},
  volume = {8},
  number = {11},
  pages = {415},
  doi = {10.3390/fire8110415}
}
Kostenlos starten →