Authors:
Rui Valente de Almeida
1
;
2
;
Fernando Crivellaro
2
;
Maria Narciso
2
;
Ana Isabel Sousa
2
and
Pedro Vieira
2
Affiliations:
1
Compta, S.A., Alameda Fernão Lopes 12, 10th floor, 1495-190 Algés, Portugal
;
2
Physics Department, FCT NOVA, Campus de Caparica, 2829-516 Caparica, Portugal
Keyword(s):
Forest Fire Detection, Deep Learning, PyTorch, FastAI, IBM Watson.
Abstract:
Bee2Fire is a commercial system for forest fire detection, inheriting from the Forest Fire Finder System. Designed in Portugal, it aims to address one of Southern Europe’s main concern, forest fires. It is a well known fact that the sooner a wildfire is detected, the quicker it can be put out, which highlights the importance of early detection. By scanning the landscape using regular cameras and Deep Artificial Neural Networks, Bee2Fire searches for smoke columns above the horizon with a image classification approach. After these networks were trained, the system was deployed in the field, obtaining a sensitivity score between 74% and 93%, a specificity of more than 99% and a precision of around 82%.