Feedback

Faculté des Sciences appliquées
Faculté des Sciences appliquées
MASTER THESIS
VIEW 107 | DOWNLOAD 926

Detection of forest fires using artificial intelligence

Download
Cajot, Antoine ULiège
Promotor(s) : Van Droogenbroeck, Marc ULiège
Date of defense : 24-Jun-2021/25-Jun-2021 • Permalink : http://hdl.handle.net/2268.2/11670
Details
Title : Detection of forest fires using artificial intelligence
Translated title : [fr] Détection de feux de forêts avec l'intelligence artificielle
[es] Detección de incendios forestales mediante inteligencia artificial
[nl] Detectie van bosbranden met kunstmatige intelligentie
Author : Cajot, Antoine ULiège
Date of defense  : 24-Jun-2021/25-Jun-2021
Advisor(s) : Van Droogenbroeck, Marc ULiège
Committee's member(s) : Marée, Raphaël ULiège
Wehenkel, Louis ULiège
Language : English
Number of pages : 166
Keywords : [en] deep learning
[en] segmentation
[en] forest fires
[en] uav
[en] corsican fire database
Discipline(s) : Engineering, computing & technology > Computer science
Target public : Researchers
Professionals of domain
Student
Institution(s) : Université de Liège, Liège, Belgique
Degree: Master en ingénieur civil en informatique, à finalité spécialisée en "intelligent systems"
Faculty: Master thesis of the Faculté des Sciences appliquées

Abstract

[en] With the advent of climate change comes the fear wildfires will become a rising concern in the near future as is hinted by several environmental studies. This fear has already become a reality for some parts of the globe. This work implements and compares different deep learning architectures for flame semantic segmentation on RGB images of fires occurring in a natural environment taken from the ground or from an unmanned aerial vehicle (UAV). The Corsican Fire Database is exploited after comparing it to other candidate public datasets. Results are compared in terms of the intersection over union (IoU), the mean squared error (MSE), the binary accuracy and the recall metrics as well as their number of network parameters. The implemented architectures are the FLAME U-Net, the DeepLabv3+ architecture considering the EfficientNet-B4 and the ResNet-50 backbones, the Squeeze U-Net as well as the ATT Squeeze U-Net. Notable among the evaluated architectures, the DeepLabV3+ with an EfficientNet backbone was the one that achieved the best results with an IoU of 0.93 and a recall of 0.967 while exploiting 22M parameters; and the ATT Squeeze U-Net that scored very decently with an IoU of 0.893, a recall of 0.928 and the least amount of network parameters (885K). All implementations were made public.


File(s)

Document(s)

File
Access Thesis.pdf
Description: Full Text Thesis
Size: 5.7 MB
Format: Adobe PDF
File
Access OnePageSummary.pdf
Description: One Page Summary
Size: 1.84 MB
Format: Adobe PDF

Author

  • Cajot, Antoine ULiège Université de Liège > Master ingé. civ. info., à fin.

Promotor(s)

Committee's member(s)

  • Marée, Raphaël ULiège Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Méthodes stochastiques
    ORBi View his publications on ORBi
  • Wehenkel, Louis ULiège Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Méthodes stochastiques
    ORBi View his publications on ORBi
  • Total number of views 107
  • Total number of downloads 926










All documents available on MatheO are protected by copyright and subject to the usual rules for fair use.
The University of Liège does not guarantee the scientific quality of these students' works or the accuracy of all the information they contain.