FireNet: Real-time Segmentation of Fire Perimeter from Aerial Video
This addresses a critical problem for humanitarian aid and disaster response by improving fire monitoring efficiency.
The paper tackles real-time segmentation of fire perimeters from aerial infrared video, achieving 92 F1 score accuracy and 20 frames per second inference speed.
In this paper, we share our approach to real-time segmentation of fire perimeter from aerial full-motion infrared video. We start by describing the problem from a humanitarian aid and disaster response perspective. Specifically, we explain the importance of the problem, how it is currently resolved, and how our machine learning approach improves it. To test our models we annotate a large-scale dataset of 400,000 frames with guidance from domain experts. Finally, we share our approach currently deployed in production with inference speed of 20 frames per second and an accuracy of 92 (F1 Score).