Integrated pixel-level CNN-FCN crack detection via photogrammetric 3D texture mapping of concrete structures

Although multiple learning-based crack detection systems show promising results in detecting cracks with pixel accuracy on individual images, few effectively enable inspection of larger structures. This paper thereby proposes an advanced inspection reporting system based on an integrated CNN-FCN cra...

Full description

Main Authors: Chaiyasarn, K., Buatik, A., Mohamad, H., Zhou, M., Kongsilp, S., Poovarodom, N.
Format: Article
Institution: Universiti Teknologi Petronas
Record Id / ISBN-0: utp-eprints.33348 /
Published: Elsevier B.V. 2022
Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85131460599&doi=10.1016%2fj.autcon.2022.104388&partnerID=40&md5=314e85acc5fdd91ac70a6289be5d41ce
http://eprints.utp.edu.my/33348/
Tags: Add Tag
No Tags, Be the first to tag this record!
id utp-eprints.33348
recordtype eprints
spelling utp-eprints.333482022-07-26T08:19:35Z Integrated pixel-level CNN-FCN crack detection via photogrammetric 3D texture mapping of concrete structures Chaiyasarn, K. Buatik, A. Mohamad, H. Zhou, M. Kongsilp, S. Poovarodom, N. Although multiple learning-based crack detection systems show promising results in detecting cracks with pixel accuracy on individual images, few effectively enable inspection of larger structures. This paper thereby proposes an advanced inspection reporting system based on an integrated CNN-FCN crack detection system applied on the texture space of a footing, enabling crack inspection and display for larger structures. The system, a Convolutional Neural Network (CNN) and a Fully Convolutional Network (FCN), segments cracks at the pixel-level on the texture space, acquired from a 3D model created with photogrammetry techniques. Firstly, the trained CNN is employed to detect crack patches, then imported to the trained FCN system to segment cracks at the pixel-level, and a crack map is then generated which is projected onto a 3D model. This system indicates promising results for footing textures as represented by: Accuracy (99.88), Precision (82.2), Recall (90.2), and F1 Score (86.01). © 2022 Elsevier B.V. 2022 Article NonPeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85131460599&doi=10.1016%2fj.autcon.2022.104388&partnerID=40&md5=314e85acc5fdd91ac70a6289be5d41ce Chaiyasarn, K. and Buatik, A. and Mohamad, H. and Zhou, M. and Kongsilp, S. and Poovarodom, N. (2022) Integrated pixel-level CNN-FCN crack detection via photogrammetric 3D texture mapping of concrete structures. Automation in Construction, 140 . http://eprints.utp.edu.my/33348/
institution Universiti Teknologi Petronas
collection UTP Institutional Repository
description Although multiple learning-based crack detection systems show promising results in detecting cracks with pixel accuracy on individual images, few effectively enable inspection of larger structures. This paper thereby proposes an advanced inspection reporting system based on an integrated CNN-FCN crack detection system applied on the texture space of a footing, enabling crack inspection and display for larger structures. The system, a Convolutional Neural Network (CNN) and a Fully Convolutional Network (FCN), segments cracks at the pixel-level on the texture space, acquired from a 3D model created with photogrammetry techniques. Firstly, the trained CNN is employed to detect crack patches, then imported to the trained FCN system to segment cracks at the pixel-level, and a crack map is then generated which is projected onto a 3D model. This system indicates promising results for footing textures as represented by: Accuracy (99.88), Precision (82.2), Recall (90.2), and F1 Score (86.01). © 2022
format Article
author Chaiyasarn, K.
Buatik, A.
Mohamad, H.
Zhou, M.
Kongsilp, S.
Poovarodom, N.
spellingShingle Chaiyasarn, K.
Buatik, A.
Mohamad, H.
Zhou, M.
Kongsilp, S.
Poovarodom, N.
Integrated pixel-level CNN-FCN crack detection via photogrammetric 3D texture mapping of concrete structures
author_sort Chaiyasarn, K.
title Integrated pixel-level CNN-FCN crack detection via photogrammetric 3D texture mapping of concrete structures
title_short Integrated pixel-level CNN-FCN crack detection via photogrammetric 3D texture mapping of concrete structures
title_full Integrated pixel-level CNN-FCN crack detection via photogrammetric 3D texture mapping of concrete structures
title_fullStr Integrated pixel-level CNN-FCN crack detection via photogrammetric 3D texture mapping of concrete structures
title_full_unstemmed Integrated pixel-level CNN-FCN crack detection via photogrammetric 3D texture mapping of concrete structures
title_sort integrated pixel-level cnn-fcn crack detection via photogrammetric 3d texture mapping of concrete structures
publisher Elsevier B.V.
publishDate 2022
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85131460599&doi=10.1016%2fj.autcon.2022.104388&partnerID=40&md5=314e85acc5fdd91ac70a6289be5d41ce
http://eprints.utp.edu.my/33348/
_version_ 1741197839942287360
score 11.62408