Object detection with RetinaNet on aerial imagery: the Algarve landscape

Bibliographic Details
Main Author: Coelho, C.
Publication Date: 2021
Other Authors: Costa, M. Fernanda P., Ferrás, Luís Jorge Lima, Soares, A. J.
Language: eng
Source: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
Download full: http://hdl.handle.net/1822/75255
Summary: This work presents a study of the different existing object detection algorithms and the implementation of a Deep Learning model capable of detecting swimming pools from satellite images. In order to obtain the best results for this particular task, the RetinaNet algorithm was chosen. The model was trained using a customised dataset from Kaggle and tested with a newly developed dataset containing aerial images of the Algarve landscape and a random dataset of images obtained from Google Maps. The performance of the trained model is discussed using several metrics. The model can be used by the authorities to detect illegal swimming pools in any region, especially in the Algarve region due to the high density of pools there.
id RCAP_3fecaf1e0e2bdcef3bd602c41e29550f
oai_identifier_str oai:repositorium.sdum.uminho.pt:1822/75255
network_acronym_str RCAP
network_name_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository_id_str https://opendoar.ac.uk/repository/7160
spelling Object detection with RetinaNet on aerial imagery: the Algarve landscapeComputer visionNeural networksDeep learningObject detectionRetinaNetCiências Naturais::MatemáticasScience & TechnologyThis work presents a study of the different existing object detection algorithms and the implementation of a Deep Learning model capable of detecting swimming pools from satellite images. In order to obtain the best results for this particular task, the RetinaNet algorithm was chosen. The model was trained using a customised dataset from Kaggle and tested with a newly developed dataset containing aerial images of the Algarve landscape and a random dataset of images obtained from Google Maps. The performance of the trained model is discussed using several metrics. The model can be used by the authorities to detect illegal swimming pools in any region, especially in the Algarve region due to the high density of pools there.Supported by FCT - Fundacao para a Ciencia e a Tecnologia, through projects UIDB/00013/2020 and UIDP/00013/2020 of CMAT-UM.SpringerUniversidade do MinhoCoelho, C.Costa, M. Fernanda P.Ferrás, Luís Jorge LimaSoares, A. J.2021-09-112021-09-11T00:00:00Zconference paperinfo:eu-repo/semantics/publishedVersionapplication/pdfhttp://hdl.handle.net/1822/75255engCoelho C., Costa M.F.P., Ferrás L.L., Soares A.J. (2021) Object Detection with RetinaNet on Aerial Imagery: The Algarve Landscape. In: Gervasi O. et al. (eds) Computational Science and Its Applications – ICCSA 2021. ICCSA 2021. Lecture Notes in Computer Science, vol 12950. Springer, Cham. https://doi.org/10.1007/978-3-030-86960-1_35978-3-030-86959-50302-974310.1007/978-3-030-86960-1_35978-3-030-86960-1https://link.springer.com/chapter/10.1007/978-3-030-86960-1_35info:eu-repo/semantics/openAccessreponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiainstacron:RCAAP2024-05-11T05:26:01Zoai:repositorium.sdum.uminho.pt:1822/75255Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireinfo@rcaap.ptopendoar:https://opendoar.ac.uk/repository/71602025-05-28T15:18:18.899793Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiafalse
dc.title.none.fl_str_mv Object detection with RetinaNet on aerial imagery: the Algarve landscape
title Object detection with RetinaNet on aerial imagery: the Algarve landscape
spellingShingle Object detection with RetinaNet on aerial imagery: the Algarve landscape
Coelho, C.
Computer vision
Neural networks
Deep learning
Object detection
RetinaNet
Ciências Naturais::Matemáticas
Science & Technology
title_short Object detection with RetinaNet on aerial imagery: the Algarve landscape
title_full Object detection with RetinaNet on aerial imagery: the Algarve landscape
title_fullStr Object detection with RetinaNet on aerial imagery: the Algarve landscape
title_full_unstemmed Object detection with RetinaNet on aerial imagery: the Algarve landscape
title_sort Object detection with RetinaNet on aerial imagery: the Algarve landscape
author Coelho, C.
author_facet Coelho, C.
Costa, M. Fernanda P.
Ferrás, Luís Jorge Lima
Soares, A. J.
author_role author
author2 Costa, M. Fernanda P.
Ferrás, Luís Jorge Lima
Soares, A. J.
author2_role author
author
author
dc.contributor.none.fl_str_mv Universidade do Minho
dc.contributor.author.fl_str_mv Coelho, C.
Costa, M. Fernanda P.
Ferrás, Luís Jorge Lima
Soares, A. J.
dc.subject.por.fl_str_mv Computer vision
Neural networks
Deep learning
Object detection
RetinaNet
Ciências Naturais::Matemáticas
Science & Technology
topic Computer vision
Neural networks
Deep learning
Object detection
RetinaNet
Ciências Naturais::Matemáticas
Science & Technology
description This work presents a study of the different existing object detection algorithms and the implementation of a Deep Learning model capable of detecting swimming pools from satellite images. In order to obtain the best results for this particular task, the RetinaNet algorithm was chosen. The model was trained using a customised dataset from Kaggle and tested with a newly developed dataset containing aerial images of the Algarve landscape and a random dataset of images obtained from Google Maps. The performance of the trained model is discussed using several metrics. The model can be used by the authorities to detect illegal swimming pools in any region, especially in the Algarve region due to the high density of pools there.
publishDate 2021
dc.date.none.fl_str_mv 2021-09-11
2021-09-11T00:00:00Z
dc.type.driver.fl_str_mv conference paper
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/1822/75255
url http://hdl.handle.net/1822/75255
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Coelho C., Costa M.F.P., Ferrás L.L., Soares A.J. (2021) Object Detection with RetinaNet on Aerial Imagery: The Algarve Landscape. In: Gervasi O. et al. (eds) Computational Science and Its Applications – ICCSA 2021. ICCSA 2021. Lecture Notes in Computer Science, vol 12950. Springer, Cham. https://doi.org/10.1007/978-3-030-86960-1_35
978-3-030-86959-5
0302-9743
10.1007/978-3-030-86960-1_35
978-3-030-86960-1
https://link.springer.com/chapter/10.1007/978-3-030-86960-1_35
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Springer
publisher.none.fl_str_mv Springer
dc.source.none.fl_str_mv reponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron:RCAAP
instname_str FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron_str RCAAP
institution RCAAP
reponame_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
collection Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository.name.fl_str_mv Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
repository.mail.fl_str_mv info@rcaap.pt
_version_ 1833595232558514176

Similar Items