Research on Point Cloud Power Line Segmentation and fitting algorithm

Guo, Tong; Xu, Liyun; Chen, Yuran; Liu, Yong; Zhao, Jian; Luo, Xiao Nan; Wu, Songhua

doi:10.1109/iaeac47372.2019.8997632

Cited by 5 publications

(5 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike methods presented in the literature that require pre-processing to fit each segment into a single file ( e.g . Guo et al, 2019 ), our method works independently of the tiling pattern. Each tile is loaded with a buffer, thus ensuring that the virtual towers that are added at its edges are actually out of the processed region and do not affect the classification.…”

Section: Discussionmentioning

confidence: 99%

“…Full-size  DOI: 10.7717/peerj-cs.672/fig- 2 designed and tested on much smaller datasets (640 m of power lines for , 2 km for Jwa, Sohn & Kim (2009) and Munir, Awrangjeb & Stantic (2019), 750 m for Sohn, Jwa & Kim (2012), 4 km for Guo et al (2019), 1 to 2 km for Melzer & Briese (2004) and Zhu & Hyyppä (2014), 10 km for Yang & Kang (2018)), often with linear network topologies with no network forking and few deflections. Finally, none of the existing studies we have reviewed provided access to software for users to implement the method or at least access the source code.…”

Section: Introductionmentioning

confidence: 99%

“…Despite the diversity and high accuracy of power line segmentation methods described in the literature, none applied to the context of this study. In addition to differences in point cloud densities and the urban vs forested context, previous studies have been designed and tested on much smaller datasets (640 m of power lines for Jwa & Sohn (2012) , 2 km for Jwa, Sohn & Kim (2009) and Munir, Awrangjeb & Stantic (2019) , 750 m for Sohn, Jwa & Kim (2012) , 4 km for Guo et al (2019) , 1 to 2 km for Melzer & Briese (2004) and Zhu & Hyyppä (2014) , 10 km for Yang & Kang (2018) ), often with linear network topologies with no network forking and few deflections. Finally, none of the existing studies we have reviewed provided access to software for users to implement the method or at least access the source code.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Classification of high-voltage power line structures in low density ALS data acquired over broad non-urban areas

Roussel

Achim

Auty

2021

PeerJ Computer Science

View full text Add to dashboard Cite

Airborne laser scanning (ALS) has gained importance over recent decades for multiple uses related to the cartography of landscapes. Processing ALS data over large areas for forest resource estimation and ecological assessments requires efficient algorithms to filter out some points from the raw data and remove human-made structures that would otherwise be mistaken for natural objects. In this paper, we describe an algorithm developed for the segmentation and cleaning of electrical network facilities in low density (2.5 to 13 points/m2) ALS point clouds. The algorithm was designed to identify transmission towers, conductor wires and earth wires from high-voltage power lines in natural landscapes. The method is based on two priors i.e. (1) the availability of a map of the high-voltage power lines across the area of interest and (2) knowledge of the type of transmission towers that hold the conductors along a given power line. It was tested on a network totalling 200 km of wires supported by 415 transmission towers with diverse topographies and topologies with an accuracy of 98.6%. This work will help further the automated detection capacity of power line structures, which had previously been limited to high density point clouds in small, urbanised areas. The method is open-source and available online.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Classification of high-voltage power line structures in low density ALS data acquired over broad non-urban areas

Roussel

Achim

Auty

2021

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…At present,scholars at home and abroad have made many studies in the detection and extraction of point cloud of objects,Yadav et al proposed a method for collecting point clouds of different road environments for power line extraction 7 .Through the four steps to evaluate the urban.suburban and rural power line corridor of three scenes.At the same time.extract the obscure power line from a complex environment.Munir et al proposal to layer high-voltage power line extraction and reconstruction methods.Based on the visual angle,according to the characteristics that the power line is not perpendicular to the ground and the shape and properties of the electric towerand.Then use Hough transform to extract the power line point from noise and surrounding vegetation points 8 . Guo et al proposal a point cloud segmentation algorithm based on two models,at the XOY plane K-means cluster and complete the segmentation according to the model 9 . Even the power line of lack of point cloud still can get very good effect,the method in the service of power cruising tasks.Awrangjeb et al convert the input point to a binary cover,and extract the long line from it 10 .…”

Section: Introductionmentioning

confidence: 99%

A method of laser point cloud electric line positioning for drone avoidance

zhu,

zeng

2023

Third International Conference on Electronics, Electrical and Information Engineering (ICEEIE 2023)

View full text Add to dashboard Cite

In response to the problem of drone avoidance problems under low energy visibility, a laser point cloud power line positioning method was proposed. This method solves ground equations by POS data instead of traditional iterative methods to improve system real time performance. Then reduce the number of clouds through sub-sampling. Then use Euclidean clustering to separate target point clouds. Because the power line point cloud is different from the targets such as common vehicles, architecture and other goals, has low density and non-rigidity characteristics, we use the point cloud registration method to obtain the power line position. For this purpose, this method has built a power line model with a range of ten meters and collects multiple power line cloud data as experimental materials. The results show that the method can obtain the target power line position quickly and accurately in the selected scenes.

show abstract

“…Por meio da integração dos sistemas de varredura a LASER, de posicionamento GNSS (Global Navigation Satellite System) e de orientação, constituído por uma IMU (Inertial Measurement Unit), o sistema LiDAR fornece diretamente um conjunto de pontos tridimensionais com coordenadas conhecidas, conjunto este denominado nuvem de pontos, nuvem de pontos 3D ou nuvem de pontos LiDAR (EL-SHEIMY; VALEO;HABIB, 2005). Nas últimas duas décadas têm-se notado um crescimento da utilização desses dados para as mais variadas aplicações, como por exemplo a geração de Modelos Digitais de Superfície (MDS) e Modelos Digitais de Terreno (MDT) (HUI et al, 2019), detecção e extração de edificações (DOS SANTOS et al, 2019;SHAO et al, 2021), modelagem de fachadas (SOUSA; CENTENO, 2021), detecção de linhas de transmissão (GUO et al, 2019, OLIVEIRA, 2022, detecção de vegetação (JASKIERNIAK et al, 2021;ITAKURA, MIYATANI e HOSOI, 2022) e detecção de estradas (RATO;SANTOS, 2021).…”

Section: Introductionunclassified

Uso de Descritores 3D e Intensidade na Detecção de Árvores em Ambiente Urbano por meio de Dados LiDAR

Alencar,

Galo,

Santos

2023

Rev. Bras. Cartogr.

View full text Add to dashboard Cite

A detecção de vegetação por meio de dados LiDAR possui aplicações em diferentes áreas do conhecimento, sendo importante para o manejo e preservação florestal, planejamento urbano, detecção de objetos obstruídos pelas copas das árvores, dentre outras. Nesse sentido, este artigo tem o propósito de avaliar a aplicabilidade dos descritores geométricos 3D baseados em autovalores e da intensidade na detecção de pontos amostrados sobre árvores. No cálculo dos atributos geométricos, vizinhanças do tipo esférica e cilíndrica foram definidas para o cálculo dos descritores, visando avaliar sua influência nos resultados. Após análises visuais dos resultados, os descritores omnivariância, curvatura, planaridade e entropia dos autovalores, além da intensidade, foram utilizados como atributos para a classificação dos pontos com o algoritmo K-Médias. Na classificação os pontos foram separados em duas classes: pontos de vegetação e não vegetação, sendo os resultados da classificação avaliados quantitativamente, com base em dados de referência e no uso dos indicadores de completeza, nível de acerto e F-Score. A completeza obtida para os atributos omnivariância, entropia dos autovalores, planaridade e intensidade foram superiores a 90%, o que sugere uma boa confiabilidade por parte dos descritores selecionados na detecção de árvores. No entanto, os valores de nível de acerto, em torno de 62%, não foram tão altos devido ao grande número de falsos positivos, devido a confusão entre pontos de árvores e pontos de bordas de edificação e linhas de transmissão. Analisando os valores de F-Score, a classificação usando o atributo omnivariância calculado numa vizinhança esférica de raio igual a 1 m se destacou, resultando em F-Score superior a 80%.

show abstract

Research on Point Cloud Power Line Segmentation and fitting algorithm

Cited by 5 publications

References 3 publications

Classification of high-voltage power line structures in low density ALS data acquired over broad non-urban areas

Classification of high-voltage power line structures in low density ALS data acquired over broad non-urban areas

A method of laser point cloud electric line positioning for drone avoidance

Uso de Descritores 3D e Intensidade na Detecção de Árvores em Ambiente Urbano por meio de Dados LiDAR

Contact Info

Product

Resources

About