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