Cited 1 time in webofscience Cited 3 time in scopus

Weakly supervised power line detection algorithm using a recursive noisy label update with refined broken line segments

Title
Weakly supervised power line detection algorithm using a recursive noisy label update with refined broken line segments
Authors
Choi, H.Koo, GyogwonKim, B.J.Kim, S.W.
DGIST Authors
Koo, Gyogwon
Issue Date
2021-03
Citation
Expert Systems with Applications, 165, 113895
Type
Article
Article Type
Article
Author Keywords
Weakly supervised learningPower linesSemantic segmentationLine segmentsIndustrial application
Keywords
LOCALIZATION
ISSN
0957-4174
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
URI
http://hdl.handle.net/20.500.11750/12730
DOI
10.1016/j.eswa.2020.113895
Publisher
Elsevier Ltd
Related Researcher
Files:
There are no files associated with this item.
Collection:
ICT Research Institute1. Journal Articles


qrcode mendeley

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

BROWSE