FIgLib & SmokeyNet: Dataset and Deep Learning Model for Real-Time Wildland Fire Smoke Detection
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 befo...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/4/1007 |
| _version_ | 1797476774870777856 |
|---|---|
| author | Anshuman Dewangan Yash Pande Hans-Werner Braun Frank Vernon Ismael Perez Ilkay Altintas Garrison W. Cottrell Mai H. Nguyen |
| author_facet | Anshuman Dewangan Yash Pande Hans-Werner Braun Frank Vernon Ismael Perez Ilkay Altintas Garrison W. Cottrell Mai H. Nguyen |
| author_sort | Anshuman Dewangan |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-09T21:08:30Z |
| format | Article |
| id | doaj.art-bc1722ecb8a7465885a5d6653a300fa8 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T21:08:30Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-bc1722ecb8a7465885a5d6653a300fa82023-11-23T21:55:28ZengMDPI AGRemote Sensing2072-42922022-02-01144100710.3390/rs14041007FIgLib & SmokeyNet: Dataset and Deep Learning Model for Real-Time Wildland Fire Smoke DetectionAnshuman Dewangan0Yash Pande1Hans-Werner Braun2Frank Vernon3Ismael Perez4Ilkay Altintas5Garrison W. Cottrell6Mai H. Nguyen7Computer Science and Engineering Department, University of California, San Diego, CA 92093, USAComputer Science and Engineering Department, University of California, San Diego, CA 92093, USASan Diego Supercomputer Center, University of California, San Diego, CA 92093, USAScripps Institution of Oceanography, University of California, San Diego, CA 92093, USASan Diego Supercomputer Center, University of California, San Diego, CA 92093, USASan Diego Supercomputer Center, University of California, San Diego, CA 92093, USAComputer Science and Engineering Department, University of California, San Diego, CA 92093, USASan Diego Supercomputer Center, University of California, San Diego, CA 92093, USAThe 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.https://www.mdpi.com/2072-4292/14/4/1007wildland fire mitigationsmoke detectiondeep learningcomputer visionartificial intelligencemachine learning |
| spellingShingle | Anshuman Dewangan Yash Pande Hans-Werner Braun Frank Vernon Ismael Perez Ilkay Altintas Garrison W. Cottrell Mai H. Nguyen FIgLib & SmokeyNet: Dataset and Deep Learning Model for Real-Time Wildland Fire Smoke Detection Remote Sensing wildland fire mitigation smoke detection deep learning computer vision artificial intelligence machine learning |
| title | FIgLib & SmokeyNet: Dataset and Deep Learning Model for Real-Time Wildland Fire Smoke Detection |
| title_full | FIgLib & SmokeyNet: Dataset and Deep Learning Model for Real-Time Wildland Fire Smoke Detection |
| title_fullStr | FIgLib & SmokeyNet: Dataset and Deep Learning Model for Real-Time Wildland Fire Smoke Detection |
| title_full_unstemmed | FIgLib & SmokeyNet: Dataset and Deep Learning Model for Real-Time Wildland Fire Smoke Detection |
| title_short | FIgLib & SmokeyNet: Dataset and Deep Learning Model for Real-Time Wildland Fire Smoke Detection |
| title_sort | figlib smokeynet dataset and deep learning model for real time wildland fire smoke detection |
| topic | wildland fire mitigation smoke detection deep learning computer vision artificial intelligence machine learning |
| url | https://www.mdpi.com/2072-4292/14/4/1007 |
| work_keys_str_mv | AT anshumandewangan figlibsmokeynetdatasetanddeeplearningmodelforrealtimewildlandfiresmokedetection AT yashpande figlibsmokeynetdatasetanddeeplearningmodelforrealtimewildlandfiresmokedetection AT hanswernerbraun figlibsmokeynetdatasetanddeeplearningmodelforrealtimewildlandfiresmokedetection AT frankvernon figlibsmokeynetdatasetanddeeplearningmodelforrealtimewildlandfiresmokedetection AT ismaelperez figlibsmokeynetdatasetanddeeplearningmodelforrealtimewildlandfiresmokedetection AT ilkayaltintas figlibsmokeynetdatasetanddeeplearningmodelforrealtimewildlandfiresmokedetection AT garrisonwcottrell figlibsmokeynetdatasetanddeeplearningmodelforrealtimewildlandfiresmokedetection AT maihnguyen figlibsmokeynetdatasetanddeeplearningmodelforrealtimewildlandfiresmokedetection |