FIgLib & SmokeyNet: Dataset and Deep Learning Model for Real-Time Wildland Fire Smoke Detection

TL;DR

This paper introduces FIgLib, a large wildfire smoke image dataset, and SmokeyNet, a deep learning model that uses spatiotemporal data for real-time smoke detection, outperforming baselines and approaching human accuracy.

Contribution

The work provides a new extensive dataset and a novel deep learning architecture for wildfire smoke detection from fixed cameras.

Findings

SmokeyNet outperforms comparable baseline models.

The FIgLib dataset enables better training and evaluation.

SmokeyNet approaches human performance in detection accuracy.

Abstract

The size and frequency of wildland fires in the western United States have dramatically increased in recent years. On high-fire-risk days, a small fire ignition can rapidly grow and become out of control. Early detection of fire ignitions from initial smoke can assist the response to such fires before they become difficult to manage. Past deep learning approaches for wildfire smoke detection have suffered from small or unreliable datasets that make it difficult to extrapolate performance to real-world scenarios. In this work, we present the Fire Ignition Library (FIgLib), a publicly available dataset of nearly 25,000 labeled wildfire smoke images as seen from fixed-view cameras deployed in Southern California. We also introduce SmokeyNet, a novel deep learning architecture using spatiotemporal information from camera imagery for real-time wildfire smoke detection. When trained on the FIgLib dataset, SmokeyNet outperforms comparable baselines and rivals human performance. We hope that the availability of the FIgLib dataset and the SmokeyNet architecture will inspire further research into deep learning methods for wildfire smoke detection, leading to automated notification systems that reduce the time to wildfire response.