EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

FireFormer: an efficient Transformer to identify forest fire from surveillance cameras

Yuming Qiao, Wenyu Jiang, Fei Wang, Guofeng Su, Xin Li, Juncai Jiang

International Journal of Wildland Fire · 19.09.2023 · 32 (9) · 1364-1380

DOI: 10.1071/wf22220 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Wildland Fire, online erschienen am 14.08.2023. Verfasst von Yuming Qiao und 5 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 71 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Disciplines Distribution Project of Shenzhen, China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

An effective identification model is crucial to realise the real-time monitoring and early warning of forest fires from surveillance cameras. However, existing models are prone to generate numerous false alarms under the interference of artificial smoke such as industrial smoke and villager cooking smoke, therefore a superior identification model is urgently needed.

Aims

In this study, we tested the Transformer-based model FireFormer to predict the risk probability of forest fire from the surveillance images.

Methods

FireFormer uses a shifted window self-attention module to extract similarities of divided patches in the image. The similarity in characteristics indicated the probability of forest fires. The GradCAM algorithm was then applied to analyse the interest area of FireFormer model and visualise the contribution of different image patches by calculating gradient reversely. To verify our model, the monitoring data from the high-point camera in Nandan Mountain, Foshan City, was collected and further constructed as a forest fire alarm dataset. Key results Our results showed that FireFormer achieved a competitive performance (OA: 82.21%, Recall: 86.635% and F1-score: 74.68%).

Conclusions

FireFormer proves to be superior to traditional methods.

Implications

FireFormer provides an efficient way to reduce false alarms and avoid heavy manual re-checking work.

Förderung

  • Disciplines Distribution Project of Shenzhen, China

Zitieren

APA

Qiao, Y., Jiang, W., Wang, F., Su, G., Li, X., & Jiang, J. (2023). FireFormer: an efficient Transformer to identify forest fire from surveillance cameras. International Journal of Wildland Fire, 32(9), 1364-1380. https://doi.org/10.1071/wf22220

Vancouver

Qiao Y, Jiang W, Wang F, Su G, Li X, Jiang J. FireFormer: an efficient Transformer to identify forest fire from surveillance cameras. International Journal of Wildland Fire. 2023;32(9):1364-1380. doi:10.1071/wf22220

BibTeX
@article{Qiao2023,
  author = {Qiao, Yuming and Jiang, Wenyu and Wang, Fei and Su, Guofeng and Li, Xin and Jiang, Juncai},
  title = {FireFormer: an efficient Transformer to identify forest fire from surveillance cameras},
  journal = {International Journal of Wildland Fire},
  year = {2023},
  volume = {32},
  number = {9},
  pages = {1364--1380},
  doi = {10.1071/wf22220}
}
Kostenlos starten →