Show simple item record

dc.creatorChasco Hernández, Danieles_ES
dc.creatorSanz Delgado, José Antonioes_ES
dc.creatorGarcía Morales, Víctores_ES
dc.creatorÁlvarez-Mozos, Jesúses_ES
dc.date.accessioned2020-07-09T09:51:35Z
dc.date.issued2020
dc.identifier.isbn978-3-030-41199-2
dc.identifier.issn2195-4356
dc.identifier.urihttps://hdl.handle.net/2454/37313
dc.description.abstractThe correct classification of power lines in LiDAR point clouds has attracted the interest of the mapping community in the last years. The objective of this research is the detection and automatic extraction of high-voltage transmission lines from LiDAR data using data mining techniques. With this aim, a Single Photon LiDAR (SPL) survey acquired over the region of Navarre (Spain) in 2017 was used, with a mean point density of 14 pt/m2. Different data mining techniques were evaluated, including decision trees (C4.5 and CART) and ensemble learning algorithms (Random Forests, Bagging and AdaBoost). Fifteen test sites were studied corresponding to areas with high-voltage power lines over different conditions regarding the underlying vegetation and topography. For these sites 92,104 LiDAR points were identified as power lines and more than 4M points as not power lines using existing cartography. This dataset was randomly split in train and test sets and then balanced two obtain a similar amount of data for the two classes. The results obtained show the importance of balancing the training data with improvements in accuracy of ~10% with respect to the imbalanced case. Accuracies higher than 87% were obtained in all balanced cases, with particularly successful results for ensemble learning techniques, being AdaBoost the technique with the highest accuracy 91%. These results suggest that the combination of SPL surveys and data mining tools can be successfully used for the operational mapping of high voltage power lines.en
dc.description.sponsorshipThe Government of Navarre and Tracasa are acknowledged for the provision of the SPL LiDAR data, the TerraScan software license and their expertise.en
dc.format.extent9 p.
dc.format.mimetypeapplication/pdfen
dc.language.isoengen
dc.publisherSpringeren
dc.relation.ispartofCavas-Martínez, F., Sanz-Adan, F., Morer Camo, P., Lostado Lorza, R., Santamaría Peña, J. (Eds.) Advances in Design Engineering: Proceedings of the XXIX International Congress INGEGRAF, 20-21 June 2019, Logroño, Spain. Cham: Springer, 2020, pp. 568-575. ISBN 978-3-030-41199-2en
dc.rights© Springer Nature Switzerland AG 2020en
dc.subjectLiDAR Data miningen
dc.subjectSingle Photon LiDARen
dc.subjectPower linesen
dc.subjectSupervised classificationen
dc.titleAutomatic detection of high-voltage power lines in LiDAR surveys using data mining techniquesen
dc.typeinfo:eu-repo/semantics/conferenceObjecten
dc.typeContribución a congreso / Biltzarrerako ekarpenaes
dc.contributor.departmentUniversidad Pública de Navarra. Departamento de Ingenieríaes_ES
dc.contributor.departmentNafarroako Unibertsitate Publikoa. Ingeniaritza Sailaeu
dc.contributor.departmentUniversidad Pública de Navarra. Departamento de Estadística, Informática y Matemáticases_ES
dc.contributor.departmentNafarroako Unibertsitate Publikoa. Estatistika, Informatika eta Matematikak Sailaeu
dc.rights.accessRightsinfo:eu-repo/semantics/embargoedAccessen
dc.rights.accessRightsAcceso embargado / Sarbidea bahitua dagoes
dc.embargo.lift2021-03-10
dc.embargo.terms2021-03-10
dc.identifier.doi10.1007/978-3-030-41200-5_62
dc.relation.projectIDinfo:eu-repo/grantAgreement/ES/1PE/MTM2015-63608-Pen
dc.relation.projectIDinfo:eu-repo/grantAgreement/ES/1PE/ECO2015-65031en
dc.relation.publisherversionhttps://doi.org/10.1007/978-3-030-41200-5_62
dc.type.versioninfo:eu-repo/semantics/acceptedVersionen
dc.type.versionVersión aceptada / Onetsi den bertsioaes


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record