Wild animals detection in Camera Trapping images: A Machine Learning approach

Detalhes bibliográficos
Autor(a) principal: Sá, Carolina Filipa Abreu
Data de Publicação: 2024
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10362/163579
Resumo: Project Work presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Data Science
id RCAP_53ffbac1d4c8242f8adbeea7dd7cd6c5
oai_identifier_str oai:run.unl.pt:10362/163579
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Wild animals detection in Camera Trapping images: A Machine Learning approachCamera-trappingImage ProcessingDeep Convolutional Neural NetworksMachine learningSDG 8 - Decent work and economic growthSDG 15 - Life on landDomínio/Área Científica::Ciências Naturais::Ciências da Computação e da InformaçãoProject Work presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Data ScienceIn the field of wildlife conservation and research, Camera Trapping (CT) images have become invaluable tools. However, the sheer volume of images, often captured in challenging conditions, presents a significant obstacle to accurately identifying animals. This Thesis proposes to develop an effective solution for identifying animals in CT images through the use of Machine Learning (ML) algorithms, within the context of the “Sistema de Armadilhagem Fotográfica e Análise Inteligente” (SAFArI) project. It addresses the unique challenges of processing images from the wild, by incorporating a comprehensive review of existing literature, with a specific emphasis on identifying the most suitable ML methodologies for analysing CT images. Based on this review, extensive exploration of various pre-existing object detection models, such as Faster Region-Based Convolutional Neural Network (Faster R-CNN) and You Only Look Once (YOLO), is conducted, considering the unique features of each model, and incorporating movement detection methods like Background Subtraction (BS). Benchmarking becomes essential as this study seeks to evaluate the performance of each model, providing valuable insights into their efficacy. It is within these benchmarks that a path toward a custom-tailored architecture for the SAFArI project emerges. It is vital that the developed model not only demonstrates effectiveness but also integrates seamlessly with the project's objectives, contributing to advancements in wildlife research and conservation.Santos, Vitor Manuel Pereira Duarte dosRodrigues, VitorRUNSá, Carolina Filipa Abreu2024-02-15T16:05:21Z2024-01-292024-01-29T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10362/163579TID:203518314enginfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-03-11T05:47:35Zoai:run.unl.pt:10362/163579Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:59:28.671538Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Wild animals detection in Camera Trapping images: A Machine Learning approach
title Wild animals detection in Camera Trapping images: A Machine Learning approach
spellingShingle Wild animals detection in Camera Trapping images: A Machine Learning approach
Sá, Carolina Filipa Abreu
Camera-trapping
Image Processing
Deep Convolutional Neural Networks
Machine learning
SDG 8 - Decent work and economic growth
SDG 15 - Life on land
Domínio/Área Científica::Ciências Naturais::Ciências da Computação e da Informação
title_short Wild animals detection in Camera Trapping images: A Machine Learning approach
title_full Wild animals detection in Camera Trapping images: A Machine Learning approach
title_fullStr Wild animals detection in Camera Trapping images: A Machine Learning approach
title_full_unstemmed Wild animals detection in Camera Trapping images: A Machine Learning approach
title_sort Wild animals detection in Camera Trapping images: A Machine Learning approach
author Sá, Carolina Filipa Abreu
author_facet Sá, Carolina Filipa Abreu
author_role author
dc.contributor.none.fl_str_mv Santos, Vitor Manuel Pereira Duarte dos
Rodrigues, Vitor
RUN
dc.contributor.author.fl_str_mv Sá, Carolina Filipa Abreu
dc.subject.por.fl_str_mv Camera-trapping
Image Processing
Deep Convolutional Neural Networks
Machine learning
SDG 8 - Decent work and economic growth
SDG 15 - Life on land
Domínio/Área Científica::Ciências Naturais::Ciências da Computação e da Informação
topic Camera-trapping
Image Processing
Deep Convolutional Neural Networks
Machine learning
SDG 8 - Decent work and economic growth
SDG 15 - Life on land
Domínio/Área Científica::Ciências Naturais::Ciências da Computação e da Informação
description Project Work presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Data Science
publishDate 2024
dc.date.none.fl_str_mv 2024-02-15T16:05:21Z
2024-01-29
2024-01-29T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10362/163579
TID:203518314
url http://hdl.handle.net/10362/163579
identifier_str_mv TID:203518314
dc.language.iso.fl_str_mv eng
language eng
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.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799138174368219136

Registros relacionados