Full metadata record

DC Field Value Language
dc.contributor.author Choi, H. ko
dc.contributor.author Koo, Gyogwon ko
dc.contributor.author Kim, B.J. ko
dc.contributor.author Kim, S.W. ko
dc.date.accessioned 2021-01-22T07:20:39Z -
dc.date.available 2021-01-22T07:20:39Z -
dc.date.created 2020-09-24 -
dc.date.issued 2021-03 -
dc.identifier.citation Expert Systems with Applications, v.165, pp.113895 -
dc.identifier.issn 0957-4174 -
dc.identifier.uri http://hdl.handle.net/20.500.11750/12730 -
dc.description.abstract Detection of power lines in aerial images is an important problem to prevent accidents of unmanned aerial vehicles operating at low altitudes in the electrical industry. Recently, pixel-level power line detection using deep learning has been studied but production of the pixel-level annotations for massive dataset is difficult. In this study, we propose a power line detection algorithm using weakly supervised learning method to reduce the labeling cost for dataset generation. The algorithm is divided into two stages. First, an approximately localized mask was generated based on a convolutional neural network which was trained with only patch-level labels. Second, recursive training of segmentation network with refined broken line segments was executed. A refinement algorithm, line segment connecting (LSC) is a power-line-specialized refinement module that connects broken lines by approximating the segments as partially straight. In proposed algorithm, predicted image at each recursive step was updated as a label of the next training and the label was developed by itself with LSC. The comprehensive experimental results of our algorithm showed state-of-art F1-score of 94.3% in weakly supervised learning approaches on public dataset. This result suggests that the proposed algorithm is useful for low labeling cost with high performance in line detection application. © 2020 Elsevier Ltd -
dc.language English -
dc.publisher Elsevier Ltd -
dc.title Weakly supervised power line detection algorithm using a recursive noisy label update with refined broken line segments -
dc.type Article -
dc.identifier.doi 10.1016/j.eswa.2020.113895 -
dc.identifier.wosid 000602356300010 -
dc.identifier.scopusid 2-s2.0-85090697067 -
dc.type.local Article(Overseas) -
dc.type.rims ART -
dc.description.journalClass 1 -
dc.contributor.localauthor Koo, Gyogwon -
dc.contributor.nonIdAuthor Choi, H. -
dc.contributor.nonIdAuthor Kim, B.J. -
dc.contributor.nonIdAuthor Kim, S.W. -
dc.identifier.citationVolume 165 -
dc.identifier.citationStartPage 113895 -
dc.identifier.citationTitle Expert Systems with Applications -
dc.type.journalArticle Article -
dc.description.isOpenAccess N -
dc.subject.keywordAuthor Weakly supervised learning -
dc.subject.keywordAuthor Power lines -
dc.subject.keywordAuthor Semantic segmentation -
dc.subject.keywordAuthor Line segments -
dc.subject.keywordAuthor Industrial application -
dc.subject.keywordPlus LOCALIZATION -

qrcode mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.