EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

FireCLIP: Enhancing Forest Fire Detection with Multimodal Prompt Tuning and Vision-Language Understanding

Shanjunxia Wu, Yuming Qiao, Sen He, Jiahao Zhou, Zhi Wang, Xin Li, Fei Wang

Fire · 19.06.2025 · 8 (6) · 237

DOI: 10.3390/fire8060237 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Fire, online erschienen am 19.06.2025. Verfasst von Shanjunxia Wu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Yunnan Provincial Science and Technology Plan Project (Forest-Grass Joint Project), Shenzhen Science and Technology Innovation Commission, Key Field Research and Development Program of Guangdong, China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Forest fires are a global environmental threat to human life and ecosystems. This study compiles smoke alarm images from five high-definition surveillance cameras in Foshan City, Guangdong, China, collected over one year, to create a smoke-based early warning dataset. The dataset presents two key challenges: (1) high false positive rates caused by pseudo-smoke interference, including non-fire conditions like cooking smoke and industrial emissions, and (2) significant regional data imbalances, influenced by varying human activity intensities and terrain features, which impair the generalizability of traditional pre-train–fine-tune strategies. To address these challenges, we explore the use of visual language models to differentiate between true alarms and false alarms. Additionally, our method incorporates a prompt tuning strategy which helps to improve performance by at least 12.45% in zero-shot learning tasks and also enhances performance in few-shot learning tasks, demonstrating enhanced regional generalization compared to baselines.

Förderung

  • Yunnan Provincial Science and Technology Plan Project (Forest-Grass Joint Project)
  • Shenzhen Science and Technology Innovation Commission
  • Key Field Research and Development Program of Guangdong, China

Zitieren

APA

Wu, S., Qiao, Y., He, S., Zhou, J., Wang, Z., Li, X., & Wang, F. (2025). FireCLIP: Enhancing Forest Fire Detection with Multimodal Prompt Tuning and Vision-Language Understanding. Fire, 8(6), 237. https://doi.org/10.3390/fire8060237

Vancouver

Wu S, Qiao Y, He S, Zhou J, Wang Z, Li X, et al. FireCLIP: Enhancing Forest Fire Detection with Multimodal Prompt Tuning and Vision-Language Understanding. Fire. 2025;8(6):237. doi:10.3390/fire8060237

BibTeX
@article{Wu2025,
  author = {Wu, Shanjunxia and Qiao, Yuming and He, Sen and Zhou, Jiahao and Wang, Zhi and Li, Xin and Wang, Fei},
  title = {FireCLIP: Enhancing Forest Fire Detection with Multimodal Prompt Tuning and Vision-Language Understanding},
  journal = {Fire},
  year = {2025},
  volume = {8},
  number = {6},
  pages = {237},
  doi = {10.3390/fire8060237}
}
Kostenlos starten →