Convolutional neural network for smoke and fire semantic segmentation
Abstract In recent decades, global warming has contributed to an increase in the number and intensity of wildfires destroying millions hectares of forest areas and causing many casualties each year. Firemen must therefore have the most effective means to prevent any wildfire from breaking out and to...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-02-01
|
| Series: | IET Image Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/ipr2.12046 |
| _version_ | 1828096366455291904 |
|---|---|
| author | Sebastien Frizzi Moez Bouchouicha Jean‐Marc Ginoux Eric Moreau Mounir Sayadi |
| author_facet | Sebastien Frizzi Moez Bouchouicha Jean‐Marc Ginoux Eric Moreau Mounir Sayadi |
| author_sort | Sebastien Frizzi |
| collection | DOAJ |
| description | Abstract In recent decades, global warming has contributed to an increase in the number and intensity of wildfires destroying millions hectares of forest areas and causing many casualties each year. Firemen must therefore have the most effective means to prevent any wildfire from breaking out and to fight the blaze before being unable to contain and extinguish it. This article will present a new network architecture based on Convolutional Neural Network to detect and locate smoke and fire. This network generates fire and smoke masks in an RGB image by segmentation. The purpose of this work is to help firemen in assessing the extent of fire or monitor an incipient fire in real time with a camera embedded in a vehicle. To train this network, a database with the corresponding images and masks has been created. Such a database will allow to compare the performances of different networks. A comparison of this network with the best segmentation networks such as U‐Net and Yuan networks has highlighted its efficiency in terms of location accuracy, reduction of false positive classifications such as clouds or haze. This architecture is also efficient in real time. |
| first_indexed | 2024-04-11T07:29:14Z |
| format | Article |
| id | doaj.art-ed2aa61e6c93494db16cf2a170f351d7 |
| institution | Directory Open Access Journal |
| issn | 1751-9659 1751-9667 |
| language | English |
| last_indexed | 2024-04-11T07:29:14Z |
| publishDate | 2021-02-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Image Processing |
| spelling | doaj.art-ed2aa61e6c93494db16cf2a170f351d72022-12-22T04:36:59ZengWileyIET Image Processing1751-96591751-96672021-02-0115363464710.1049/ipr2.12046Convolutional neural network for smoke and fire semantic segmentationSebastien Frizzi0Moez Bouchouicha1Jean‐Marc Ginoux2Eric Moreau3Mounir Sayadi4Aix Marseille Univ Université de Toulon CNRS LIS Toulon FranceAix Marseille Univ Université de Toulon CNRS LIS Toulon FranceAix Marseille Univ Université de Toulon CNRS LIS Toulon FranceAix Marseille Univ Université de Toulon CNRS LIS Toulon FranceUniversity of Tunis ENSIT LR13ES03 SIME Montfleury Tunis 1008 TunisiaAbstract In recent decades, global warming has contributed to an increase in the number and intensity of wildfires destroying millions hectares of forest areas and causing many casualties each year. Firemen must therefore have the most effective means to prevent any wildfire from breaking out and to fight the blaze before being unable to contain and extinguish it. This article will present a new network architecture based on Convolutional Neural Network to detect and locate smoke and fire. This network generates fire and smoke masks in an RGB image by segmentation. The purpose of this work is to help firemen in assessing the extent of fire or monitor an incipient fire in real time with a camera embedded in a vehicle. To train this network, a database with the corresponding images and masks has been created. Such a database will allow to compare the performances of different networks. A comparison of this network with the best segmentation networks such as U‐Net and Yuan networks has highlighted its efficiency in terms of location accuracy, reduction of false positive classifications such as clouds or haze. This architecture is also efficient in real time.https://doi.org/10.1049/ipr2.12046Atmosphere (environmental science)Data and information; acquisition, processing, storage and dissemination in geophysicsInstrumentation and techniques for geophysical, hydrospheric and lower atmosphere researchImage recognitionGeophysical techniques and equipmentComputer vision and image processing techniques |
| spellingShingle | Sebastien Frizzi Moez Bouchouicha Jean‐Marc Ginoux Eric Moreau Mounir Sayadi Convolutional neural network for smoke and fire semantic segmentation IET Image Processing Atmosphere (environmental science) Data and information; acquisition, processing, storage and dissemination in geophysics Instrumentation and techniques for geophysical, hydrospheric and lower atmosphere research Image recognition Geophysical techniques and equipment Computer vision and image processing techniques |
| title | Convolutional neural network for smoke and fire semantic segmentation |
| title_full | Convolutional neural network for smoke and fire semantic segmentation |
| title_fullStr | Convolutional neural network for smoke and fire semantic segmentation |
| title_full_unstemmed | Convolutional neural network for smoke and fire semantic segmentation |
| title_short | Convolutional neural network for smoke and fire semantic segmentation |
| title_sort | convolutional neural network for smoke and fire semantic segmentation |
| topic | Atmosphere (environmental science) Data and information; acquisition, processing, storage and dissemination in geophysics Instrumentation and techniques for geophysical, hydrospheric and lower atmosphere research Image recognition Geophysical techniques and equipment Computer vision and image processing techniques |
| url | https://doi.org/10.1049/ipr2.12046 |
| work_keys_str_mv | AT sebastienfrizzi convolutionalneuralnetworkforsmokeandfiresemanticsegmentation AT moezbouchouicha convolutionalneuralnetworkforsmokeandfiresemanticsegmentation AT jeanmarcginoux convolutionalneuralnetworkforsmokeandfiresemanticsegmentation AT ericmoreau convolutionalneuralnetworkforsmokeandfiresemanticsegmentation AT mounirsayadi convolutionalneuralnetworkforsmokeandfiresemanticsegmentation |