A Coarse-to-Fine Approach for Rock Bolt Detection From 3D Point Clouds

Rock bolts have been widely used to enhance the structural stability of underground infrastructures. Careful tracking of rock bolt positions is highly significant since it assists with operational success of ground support and has applications to predictive maintenance practices. This paper presents...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Sarp Saydam, Boge Liu, Binghao Li, Wenjie Zhang, Sarvesh Kumar Singh, Simit Raval
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Rock bolt point cloud LiDAR neural network Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/159ffc47340c486c82b6fbdf0ce1bfd4
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:159ffc47340c486c82b6fbdf0ce1bfd4
record_format	dspace
spelling	oai:doaj.org-article:159ffc47340c486c82b6fbdf0ce1bfd42021-11-18T00:10:44ZA Coarse-to-Fine Approach for Rock Bolt Detection From 3D Point Clouds2169-353610.1109/ACCESS.2021.3120207https://doaj.org/article/159ffc47340c486c82b6fbdf0ce1bfd42021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9570310/https://doaj.org/toc/2169-3536Rock bolts have been widely used to enhance the structural stability of underground infrastructures. Careful tracking of rock bolt positions is highly significant since it assists with operational success of ground support and has applications to predictive maintenance practices. This paper presents a practical algorithm, <monospace>CFBolt</monospace>, to detect rock bolts from a 3D laser scanned point cloud. Considering that rock bolts are relatively tiny objects, <monospace>CFBolt</monospace> follows a two-step coarse-to-fine strategy. It first computes a single-scale proportion of variance (POV) for each point as the local point descriptor and filters out near 95% not-bolt points with a simple but effective classifier, Linear Discriminant Analysis (LDA), which allows for the pruned point cloud to be then used as a compatible input to a deep neural network, designed and trained to precisely detect rock bolts from the pruned point cloud. <monospace>CFBolt</monospace> was tested for detecting rock bolts from LiDAR scan data collected from Sydney’s civil tunnelling project site. The entire dataset contains more than 160 million points. The obtained scores of Intersection over Union (IoU) and precision for individual bolt points were 89.33% and 92.04%, respectively. For rock bolt objects, the precision and recall were 98.34% and 98.73%, respectively. The detection quality of <monospace>CFBolt</monospace> is superior to the state-of-the-art 3D object detection algorithms and the newest rock bolt detection algorithm, demonstrating the robustness and effectiveness of <monospace>CFBolt</monospace>.Sarp SaydamBoge LiuBinghao LiWenjie ZhangSarvesh Kumar SinghSimit RavalIEEEarticleRock boltpoint cloudLiDARneural networkElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 148873-148883 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Rock bolt point cloud LiDAR neural network Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Rock bolt point cloud LiDAR neural network Electrical engineering. Electronics. Nuclear engineering TK1-9971 Sarp Saydam Boge Liu Binghao Li Wenjie Zhang Sarvesh Kumar Singh Simit Raval A Coarse-to-Fine Approach for Rock Bolt Detection From 3D Point Clouds
description	Rock bolts have been widely used to enhance the structural stability of underground infrastructures. Careful tracking of rock bolt positions is highly significant since it assists with operational success of ground support and has applications to predictive maintenance practices. This paper presents a practical algorithm, <monospace>CFBolt</monospace>, to detect rock bolts from a 3D laser scanned point cloud. Considering that rock bolts are relatively tiny objects, <monospace>CFBolt</monospace> follows a two-step coarse-to-fine strategy. It first computes a single-scale proportion of variance (POV) for each point as the local point descriptor and filters out near 95% not-bolt points with a simple but effective classifier, Linear Discriminant Analysis (LDA), which allows for the pruned point cloud to be then used as a compatible input to a deep neural network, designed and trained to precisely detect rock bolts from the pruned point cloud. <monospace>CFBolt</monospace> was tested for detecting rock bolts from LiDAR scan data collected from Sydney’s civil tunnelling project site. The entire dataset contains more than 160 million points. The obtained scores of Intersection over Union (IoU) and precision for individual bolt points were 89.33% and 92.04%, respectively. For rock bolt objects, the precision and recall were 98.34% and 98.73%, respectively. The detection quality of <monospace>CFBolt</monospace> is superior to the state-of-the-art 3D object detection algorithms and the newest rock bolt detection algorithm, demonstrating the robustness and effectiveness of <monospace>CFBolt</monospace>.
format	article
author	Sarp Saydam Boge Liu Binghao Li Wenjie Zhang Sarvesh Kumar Singh Simit Raval
author_facet	Sarp Saydam Boge Liu Binghao Li Wenjie Zhang Sarvesh Kumar Singh Simit Raval
author_sort	Sarp Saydam
title	A Coarse-to-Fine Approach for Rock Bolt Detection From 3D Point Clouds
title_short	A Coarse-to-Fine Approach for Rock Bolt Detection From 3D Point Clouds
title_full	A Coarse-to-Fine Approach for Rock Bolt Detection From 3D Point Clouds
title_fullStr	A Coarse-to-Fine Approach for Rock Bolt Detection From 3D Point Clouds
title_full_unstemmed	A Coarse-to-Fine Approach for Rock Bolt Detection From 3D Point Clouds
title_sort	coarse-to-fine approach for rock bolt detection from 3d point clouds
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/159ffc47340c486c82b6fbdf0ce1bfd4
work_keys_str_mv	AT sarpsaydam acoarsetofineapproachforrockboltdetectionfrom3dpointclouds AT bogeliu acoarsetofineapproachforrockboltdetectionfrom3dpointclouds AT binghaoli acoarsetofineapproachforrockboltdetectionfrom3dpointclouds AT wenjiezhang acoarsetofineapproachforrockboltdetectionfrom3dpointclouds AT sarveshkumarsingh acoarsetofineapproachforrockboltdetectionfrom3dpointclouds AT simitraval acoarsetofineapproachforrockboltdetectionfrom3dpointclouds AT sarpsaydam coarsetofineapproachforrockboltdetectionfrom3dpointclouds AT bogeliu coarsetofineapproachforrockboltdetectionfrom3dpointclouds AT binghaoli coarsetofineapproachforrockboltdetectionfrom3dpointclouds AT wenjiezhang coarsetofineapproachforrockboltdetectionfrom3dpointclouds AT sarveshkumarsingh coarsetofineapproachforrockboltdetectionfrom3dpointclouds AT simitraval coarsetofineapproachforrockboltdetectionfrom3dpointclouds
_version_	1718425145229443072

A Coarse-to-Fine Approach for Rock Bolt Detection From 3D Point Clouds

Ejemplares similares