FIgLib & SmokeyNet: Dataset and Deep Learning Model for Real-Time Wildland Fire Smoke Detection
Preprint
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.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- DeepSmoke: Deep learning model for smoke detection and segmentation in outdoor environmentsExpert Systems with Applications, 2021
- Economic footprint of California wildfires in 2018Nature Sustainability, 2020
- An Attention Enhanced Bidirectional LSTM for Early Forest Fire Smoke RecognitionIEEE Access, 2019
- Deep smoke segmentationNeurocomputing, 2019
- Dual Deep Learning Model for Image Based Smoke DetectionFire Technology, 2019
- Recurrent convolutional network for video-based smoke detectionMultimedia Tools and Applications, 2018
- Wildland Forest Fire Smoke Detection Based on Faster R-CNN using Synthetic Smoke ImagesProcedia Engineering, 2018
- Fire smoke detection algorithm based on motion characteristic and convolutional neural networksMultimedia Tools and Applications, 2017
- Machine vision-based real-time early flame and smoke detectionMeasurement Science and Technology, 2009
- Efficient adaptive density estimation per image pixel for the task of background subtractionPattern Recognition Letters, 2006