Real-Time LiDAR-based Power Lines Detection for Unmanned Aerial Vehicles
Autor(a) principal: | |
---|---|
Data de Publicação: | 2018 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10400.22/13991 |
Resumo: | The growing dependence of modern-day societies on electricity leads to the increasing importance of effective monitoring and maintenance of power lines. Due to the population’s renouncement to the installation of new electric power lines, the existing ones are constantly operating at maximum capacity. This leaves no room for breakdowns, as it leads to major economic losses for the electrical companies and blackouts for the consumers. Endowing Unmanned Aerial Vehicles (UAVs) with the appropriate sensors for inspection the power lines, the costs and risks associated with the traditional foot patrol and helicopter-based inspections can be reduced. However, this implies the development of algorithms to make the inspection process reliable and autonomous. Visual detection methods are usually applied to locate the power lines and their components. Although, they are generally too sensitive to atmospheric conditions and noisy background. Poor light conditions or a background rich in edges may compromise their results. In order to overcome those limitations, this dissertation addresses the problem of power line detection and modeling based on the use of a Light Detection And Ranging (LiDAR) sensor. A novel approach to the power line detection was developed, the Power Line LiDARbased Detection and Modeling (PL2DM). It is based in a scan-by-scan adaptive neighbor minimalist comparison for all the points in a point cloud. In the segmentation, the breaking cluster points are detected by an analysis of their planar properties. Exporting the potential power line points to a further step, it performs a scan based straight line detection. The final model of the power line is obtained by matching and grouping the several line segments detected using their collinearity properties. Horizontally, the power lines are modeled as a straight line, while vertically are approximated to a catenary curve. The algorithm was tested with a real dataset, showing promising results both in terms of outputs and processing time. From there, it was demonstrated that the proposed algorithm can be applied to real-time operations of the UAV, adding object-based perception capabilities for other layers of processing. |
id |
RCAP_cd962fb41e882e117d3b8be3fc8dfd12 |
---|---|
oai_identifier_str |
oai:recipp.ipp.pt:10400.22/13991 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Real-Time LiDAR-based Power Lines Detection for Unmanned Aerial VehiclesPower lineLiDARReal-timeUAVPoint cloudSegmentationCatenaryLinhas elétricasTempo realNuvem de pontosSegmentaçãoCatenáriaSistemas AutónomosThe growing dependence of modern-day societies on electricity leads to the increasing importance of effective monitoring and maintenance of power lines. Due to the population’s renouncement to the installation of new electric power lines, the existing ones are constantly operating at maximum capacity. This leaves no room for breakdowns, as it leads to major economic losses for the electrical companies and blackouts for the consumers. Endowing Unmanned Aerial Vehicles (UAVs) with the appropriate sensors for inspection the power lines, the costs and risks associated with the traditional foot patrol and helicopter-based inspections can be reduced. However, this implies the development of algorithms to make the inspection process reliable and autonomous. Visual detection methods are usually applied to locate the power lines and their components. Although, they are generally too sensitive to atmospheric conditions and noisy background. Poor light conditions or a background rich in edges may compromise their results. In order to overcome those limitations, this dissertation addresses the problem of power line detection and modeling based on the use of a Light Detection And Ranging (LiDAR) sensor. A novel approach to the power line detection was developed, the Power Line LiDARbased Detection and Modeling (PL2DM). It is based in a scan-by-scan adaptive neighbor minimalist comparison for all the points in a point cloud. In the segmentation, the breaking cluster points are detected by an analysis of their planar properties. Exporting the potential power line points to a further step, it performs a scan based straight line detection. The final model of the power line is obtained by matching and grouping the several line segments detected using their collinearity properties. Horizontally, the power lines are modeled as a straight line, while vertically are approximated to a catenary curve. The algorithm was tested with a real dataset, showing promising results both in terms of outputs and processing time. From there, it was demonstrated that the proposed algorithm can be applied to real-time operations of the UAV, adding object-based perception capabilities for other layers of processing.A crescente dependência das sociedades modernas no uso de eletricidade conduz a uma crescente importância da eficiência da monitorização e manutenção das linhas elétricas. A renitência das populações `a instalação de novas linhas elétricas faz com que as existentes estejam constantemente a operar na sua máxima capacidade. Isto faz com que não possam existir falhas, uma vez que resultariam em grandes perdas económicas para as companhias elétricas e em falhas energéticas para os consumidores. Equipando um Unmanned Aerial Vehicle (UAV) com os sensores adequados `a inspeção de linhas elétricas, podem ser reduzidos os custos e riscos de operação associados `as inspeções tradicionais, baseadas em patrulhas pedonais e no uso de um helicóptero. No entanto, isto implica o desenvolvimento de algoritmos para que o processo de inspeção seja fiável e autónomo. As linhas elétricas e os componentes associados são geralmente localizados através de métodos de deteção visual. Estes m´métodos são, geralmente, muito sensíveis `as condições atmosféricas e a fundos ruidosos. Condições de luz deficientes ou fundos ricos em contrastes são alguns dos fatores que podem comprometer os seus resultados. De forma a ultrapassar essas limitações, esta dissertação endereça o problema da deteção e modelação de linhas elétricas, tendo por base o uso de um sensor Light Detection And Ranging (LiDAR). Foi desenvolvida uma nova abordagem aos métodos de deteção de linhas elétricas, o Power Line LiDAR-based Detection and Modeling (PL2DM). Esta abordagem ´e baseada numa análise individual de varrimentos, em que ´e feita uma comparação minimalista de todos os pontos, presentes numa dada nuvem de pontos, com uma vizinhança adaptativa. Na segmentação, os pontos de quebra dos grupos criados são detetados tendo em conta as suas propriedades planares. Passando os pontos passíveis de pertencerem a linhas elétricas para o processamento seguinte, é realizada, em cada varrimento, uma deteção de linhas retas. O modelo final das linhas elétricas é obtido a partir da associação e agrupamento dos diversos segmentos de reta detetados, tendo por base a sua colinearidade. Na sua projeção horizontal, as linhas elétricas são modeladas como linhas retas. Verticalmente, são aproximadas ao modelo de uma curva catenária. O algoritmo foi testado com um conjunto de dados reais, tendo mostrado resultados promissores, tanto em termos de dados gerados como de tempo de processamento. Com isso, ficou demonstrado que o algoritmo proposto pode ser aplicado nas operações do UAV em tempo real, adicionando capacidades de perceção baseada em objetos para outras camadas de processamento.Almeida, José Miguel Soares deRepositório Científico do Instituto Politécnico do PortoAzevedo, Fábio André Costa2019-06-13T14:43:48Z20182018-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10400.22/13991TID:202166228enginfo: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:RCAAP2023-03-13T12:56:28Zoai:recipp.ipp.pt:10400.22/13991Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T17:33:50.617146Repositório 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 |
Real-Time LiDAR-based Power Lines Detection for Unmanned Aerial Vehicles |
title |
Real-Time LiDAR-based Power Lines Detection for Unmanned Aerial Vehicles |
spellingShingle |
Real-Time LiDAR-based Power Lines Detection for Unmanned Aerial Vehicles Azevedo, Fábio André Costa Power line LiDAR Real-time UAV Point cloud Segmentation Catenary Linhas elétricas Tempo real Nuvem de pontos Segmentação Catenária Sistemas Autónomos |
title_short |
Real-Time LiDAR-based Power Lines Detection for Unmanned Aerial Vehicles |
title_full |
Real-Time LiDAR-based Power Lines Detection for Unmanned Aerial Vehicles |
title_fullStr |
Real-Time LiDAR-based Power Lines Detection for Unmanned Aerial Vehicles |
title_full_unstemmed |
Real-Time LiDAR-based Power Lines Detection for Unmanned Aerial Vehicles |
title_sort |
Real-Time LiDAR-based Power Lines Detection for Unmanned Aerial Vehicles |
author |
Azevedo, Fábio André Costa |
author_facet |
Azevedo, Fábio André Costa |
author_role |
author |
dc.contributor.none.fl_str_mv |
Almeida, José Miguel Soares de Repositório Científico do Instituto Politécnico do Porto |
dc.contributor.author.fl_str_mv |
Azevedo, Fábio André Costa |
dc.subject.por.fl_str_mv |
Power line LiDAR Real-time UAV Point cloud Segmentation Catenary Linhas elétricas Tempo real Nuvem de pontos Segmentação Catenária Sistemas Autónomos |
topic |
Power line LiDAR Real-time UAV Point cloud Segmentation Catenary Linhas elétricas Tempo real Nuvem de pontos Segmentação Catenária Sistemas Autónomos |
description |
The growing dependence of modern-day societies on electricity leads to the increasing importance of effective monitoring and maintenance of power lines. Due to the population’s renouncement to the installation of new electric power lines, the existing ones are constantly operating at maximum capacity. This leaves no room for breakdowns, as it leads to major economic losses for the electrical companies and blackouts for the consumers. Endowing Unmanned Aerial Vehicles (UAVs) with the appropriate sensors for inspection the power lines, the costs and risks associated with the traditional foot patrol and helicopter-based inspections can be reduced. However, this implies the development of algorithms to make the inspection process reliable and autonomous. Visual detection methods are usually applied to locate the power lines and their components. Although, they are generally too sensitive to atmospheric conditions and noisy background. Poor light conditions or a background rich in edges may compromise their results. In order to overcome those limitations, this dissertation addresses the problem of power line detection and modeling based on the use of a Light Detection And Ranging (LiDAR) sensor. A novel approach to the power line detection was developed, the Power Line LiDARbased Detection and Modeling (PL2DM). It is based in a scan-by-scan adaptive neighbor minimalist comparison for all the points in a point cloud. In the segmentation, the breaking cluster points are detected by an analysis of their planar properties. Exporting the potential power line points to a further step, it performs a scan based straight line detection. The final model of the power line is obtained by matching and grouping the several line segments detected using their collinearity properties. Horizontally, the power lines are modeled as a straight line, while vertically are approximated to a catenary curve. The algorithm was tested with a real dataset, showing promising results both in terms of outputs and processing time. From there, it was demonstrated that the proposed algorithm can be applied to real-time operations of the UAV, adding object-based perception capabilities for other layers of processing. |
publishDate |
2018 |
dc.date.none.fl_str_mv |
2018 2018-01-01T00:00:00Z 2019-06-13T14:43:48Z |
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/10400.22/13991 TID:202166228 |
url |
http://hdl.handle.net/10400.22/13991 |
identifier_str_mv |
TID:202166228 |
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_ |
1799131430426509312 |