A Framework for Wildfire Inspection Using Deep Convolutional Neural Networks

Iuliu Novac; Kenneth Richard Geipel; Jacobo Eduardo de Domingo Gil; Lucas Goncalves de Paula; Kristian Hyttel Pedersen; Dimitrios Chrysostomou

doi:10.1109/SII46433.2020.9026244

A Framework for Wildfire Inspection Using Deep Convolutional Neural Networks

Iuliu Novac, Kenneth Richard Geipel, Jacobo Eduardo de Domingo Gil, Lucas Goncalves de Paula, Kristian Hyttel Pedersen, Dimitrios Chrysostomou

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

11 Citationer (Scopus)

165 Downloads (Pure)

Abstract

This paper presents the details of a holistic framework designed for wildfire inspection and estimation of its geolocation. The system is built around a low-cost, commercial quadcopter, and the main areas of interest we address in this paper are the semi-autonomous navigation of the drone, the training and classification of fire using deep convolutional neural networks, the estimation of the size and location of the wildfire and the real-time feedback and communication with the user. The evaluation of the functionality of the system demonstrates that with the combination of the proposed techniques we can successfully detect and classify fire in video streams at 19.2 FPS while we can calculate the size and location of the fire with an accuracy of 60.76%.

Originalsprog	Engelsk
Titel	IEEE/SICE International Symposium on System Integration
Antal sider	6
Forlag	IEEE
Publikationsdato	9 mar. 2020
Sider	867-872
Artikelnummer	9026244
ISBN (Trykt)	78-1-7281-6668-1
ISBN (Elektronisk)	978-1-7281-6667-4
DOI	https://doi.org/10.1109/SII46433.2020.9026244
Status	Udgivet - 9 mar. 2020
Begivenhed	IEEE/SICE International Symposium on System Integration - Hawaii Convention Center, Honolulu, USA Varighed: 12 jan. 2020 → 15 jan. 2020

Konference

Konference	IEEE/SICE International Symposium on System Integration
Lokation	Hawaii Convention Center
Land/Område	USA
By	Honolulu
Periode	12/01/2020 → 15/01/2020

Navn	Proceedings of the 2020 IEEE/SICE International Symposium on System Integration
ISSN	2474-2325

Adgang til dokumentet

10.1109/SII46433.2020.9026244

SII20_0001_FIAccepteret manuskript, 1,16 MBLicens: CC BY-NC-ND 4.0

AUB Link

Søg efter materialet i Aalborg Universitetsbiblioteks søgemaskine

Andre filer og links

http://www.scopus.com/inward/record.url?scp=85082622553&partnerID=8YFLogxK

1 Organisering af eller deltagelse i workshop, kursus, seminar, udstilling eller lignende

Special Session on Deep Learning As a Mean for Enabling Self-Learning and Self-Optimizing Capabilities in Real-World Industrial Applications
Simon Bøgh (Arrangør), Nestor Arana-Arexolaleiba (Arrangør) & Dimitrios Chrysostomou (Arrangør)
14 jan. 2020
Aktivitet: Deltagelse i faglig begivenhed › Organisering af eller deltagelse i workshop, kursus, seminar, udstilling eller lignende

Citationsformater

@inproceedings{f9af3e11d0ba4802b7fbebff9908be17,

title = "A Framework for Wildfire Inspection Using Deep Convolutional Neural Networks",

abstract = "This paper presents the details of a holistic framework designed for wildfire inspection and estimation of its geolocation. The system is built around a low-cost, commercial quadcopter, and the main areas of interest we address in this paper are the semi-autonomous navigation of the drone, the training and classification of fire using deep convolutional neural networks, the estimation of the size and location of the wildfire and the real-time feedback and communication with the user. The evaluation of the functionality of the system demonstrates that with the combination of the proposed techniques we can successfully detect and classify fire in video streams at 19.2 FPS while we can calculate the size and location of the fire with an accuracy of 60.76%.",

keywords = "DCNN, quadcopter navigation, wildfire inspection, drone control, deep convolutional neural networks",

author = "Iuliu Novac and Geipel, {Kenneth Richard} and Gil, {Jacobo Eduardo de Domingo} and Paula, {Lucas Goncalves de} and Pedersen, {Kristian Hyttel} and Dimitrios Chrysostomou",

year = "2020",

month = mar,

day = "9",

doi = "10.1109/SII46433.2020.9026244",

language = "English",

isbn = "78-1-7281-6668-1",

series = "Proceedings of the 2020 IEEE/SICE International Symposium on System Integration",

pages = "867--872",

booktitle = "IEEE/SICE International Symposium on System Integration",

publisher = "IEEE",

address = "United States",

note = "IEEE/SICE International Symposium on System Integration ; Conference date: 12-01-2020 Through 15-01-2020",

}

Novac, I, Geipel, KR, Gil, JEDD, Paula, LGD, Pedersen, KH & Chrysostomou, D 2020, A Framework for Wildfire Inspection Using Deep Convolutional Neural Networks. i IEEE/SICE International Symposium on System Integration., 9026244, IEEE, Proceedings of the 2020 IEEE/SICE International Symposium on System Integration, s. 867-872, IEEE/SICE International Symposium on System Integration, Honolulu, Hawaii, USA, 12/01/2020. https://doi.org/10.1109/SII46433.2020.9026244

A Framework for Wildfire Inspection Using Deep Convolutional Neural Networks. / Novac, Iuliu; Geipel, Kenneth Richard; Gil, Jacobo Eduardo de Domingo et al.
IEEE/SICE International Symposium on System Integration. IEEE, 2020. s. 867-872 9026244 (Proceedings of the 2020 IEEE/SICE International Symposium on System Integration).

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

TY - GEN

T1 - A Framework for Wildfire Inspection Using Deep Convolutional Neural Networks

AU - Novac, Iuliu

AU - Geipel, Kenneth Richard

AU - Gil, Jacobo Eduardo de Domingo

AU - Paula, Lucas Goncalves de

AU - Pedersen, Kristian Hyttel

AU - Chrysostomou, Dimitrios

PY - 2020/3/9

Y1 - 2020/3/9

N2 - This paper presents the details of a holistic framework designed for wildfire inspection and estimation of its geolocation. The system is built around a low-cost, commercial quadcopter, and the main areas of interest we address in this paper are the semi-autonomous navigation of the drone, the training and classification of fire using deep convolutional neural networks, the estimation of the size and location of the wildfire and the real-time feedback and communication with the user. The evaluation of the functionality of the system demonstrates that with the combination of the proposed techniques we can successfully detect and classify fire in video streams at 19.2 FPS while we can calculate the size and location of the fire with an accuracy of 60.76%.

AB - This paper presents the details of a holistic framework designed for wildfire inspection and estimation of its geolocation. The system is built around a low-cost, commercial quadcopter, and the main areas of interest we address in this paper are the semi-autonomous navigation of the drone, the training and classification of fire using deep convolutional neural networks, the estimation of the size and location of the wildfire and the real-time feedback and communication with the user. The evaluation of the functionality of the system demonstrates that with the combination of the proposed techniques we can successfully detect and classify fire in video streams at 19.2 FPS while we can calculate the size and location of the fire with an accuracy of 60.76%.

KW - DCNN

KW - quadcopter navigation

KW - wildfire inspection

KW - drone control

KW - deep convolutional neural networks

UR - http://www.scopus.com/inward/record.url?scp=85082622553&partnerID=8YFLogxK

U2 - 10.1109/SII46433.2020.9026244

DO - 10.1109/SII46433.2020.9026244

M3 - Article in proceeding

SN - 78-1-7281-6668-1

T3 - Proceedings of the 2020 IEEE/SICE International Symposium on System Integration

SP - 867

EP - 872

BT - IEEE/SICE International Symposium on System Integration

PB - IEEE

T2 - IEEE/SICE International Symposium on System Integration

Y2 - 12 January 2020 through 15 January 2020

ER -

A Framework for Wildfire Inspection Using Deep Convolutional Neural Networks

Abstract

Konference

Adgang til dokumentet

AUB Link

Andre filer og links

Fingeraftryk

Aktiviteter

Special Session on Deep Learning As a Mean for Enabling Self-Learning and Self-Optimizing Capabilities in Real-World Industrial Applications

Citationsformater