Application of Deep Learning and Unmanned Aerial Vehicle on Building Maintenance

Several natural and human factors are responsible for the defacement of the external walls and tiles of buildings, and the related deterioration can be a public safety hazard. Therefore, active building maintenance and repair processes are essential for ensuring building sustainability. However, con...

Full description

Saved in:
Bibliographic Details
Main Authors: Ren-Yi Kung, Nai-Hsin Pan, Charles C.N. Wang, Pin-Chan Lee
Format: Article
Language:English
Published: Wiley 2021-01-01
Series:Advances in Civil Engineering
Online Access:http://dx.doi.org/10.1155/2021/5598690
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849683423212339200
author Ren-Yi Kung
Nai-Hsin Pan
Charles C.N. Wang
Pin-Chan Lee
author_facet Ren-Yi Kung
Nai-Hsin Pan
Charles C.N. Wang
Pin-Chan Lee
author_sort Ren-Yi Kung
collection DOAJ
description Several natural and human factors are responsible for the defacement of the external walls and tiles of buildings, and the related deterioration can be a public safety hazard. Therefore, active building maintenance and repair processes are essential for ensuring building sustainability. However, conventional inspection methods are time-, cost-, and labor-intensive processes. Therefore, herein, this study proposes a convolutional neural network (CNN) model for image-based automated detection and localization of key building defects (efflorescence, spalling, cracking, and defacement). Based on a pretrained CNN VGG-16 classifier, this model applies class activation mapping for object localization. After identifying its limitations in real-life applications, this study determined the model’s robustness and ability to accurately detect and localize defects in the external wall tiles of buildings. For real-time detection and localization, this study applied this model by using mobile devices and drones. The results show that the application of deep learning with UAV can effectively detect various kinds of external wall defects and improve the detection efficiency.
format Article
id doaj-art-d7efc566ae1841bdb54f65ec105c76e4
institution DOAJ
issn 1687-8086
1687-8094
language English
publishDate 2021-01-01
publisher Wiley
record_format Article
series Advances in Civil Engineering
spelling doaj-art-d7efc566ae1841bdb54f65ec105c76e42025-08-20T03:23:52ZengWileyAdvances in Civil Engineering1687-80861687-80942021-01-01202110.1155/2021/55986905598690Application of Deep Learning and Unmanned Aerial Vehicle on Building MaintenanceRen-Yi Kung0Nai-Hsin Pan1Charles C.N. Wang2Pin-Chan Lee3Graduate School of Engineering Science and Technology, National Yunlin University of Science and Technology, Douliu, TaiwanDepartment of Construction Engineering, National Yunlin University of Science and Technology, Douliu, TaiwanDepartment of Bioinformatics and Medical Engineering, Asia University / Center for Artificial Intelligence and Precision Medicine Research, Asia University, Wufeng, TaiwanYuejin Technology, Ltd., New Taipei City, TaiwanSeveral natural and human factors are responsible for the defacement of the external walls and tiles of buildings, and the related deterioration can be a public safety hazard. Therefore, active building maintenance and repair processes are essential for ensuring building sustainability. However, conventional inspection methods are time-, cost-, and labor-intensive processes. Therefore, herein, this study proposes a convolutional neural network (CNN) model for image-based automated detection and localization of key building defects (efflorescence, spalling, cracking, and defacement). Based on a pretrained CNN VGG-16 classifier, this model applies class activation mapping for object localization. After identifying its limitations in real-life applications, this study determined the model’s robustness and ability to accurately detect and localize defects in the external wall tiles of buildings. For real-time detection and localization, this study applied this model by using mobile devices and drones. The results show that the application of deep learning with UAV can effectively detect various kinds of external wall defects and improve the detection efficiency.http://dx.doi.org/10.1155/2021/5598690
spellingShingle Ren-Yi Kung
Nai-Hsin Pan
Charles C.N. Wang
Pin-Chan Lee
Application of Deep Learning and Unmanned Aerial Vehicle on Building Maintenance
Advances in Civil Engineering
title Application of Deep Learning and Unmanned Aerial Vehicle on Building Maintenance
title_full Application of Deep Learning and Unmanned Aerial Vehicle on Building Maintenance
title_fullStr Application of Deep Learning and Unmanned Aerial Vehicle on Building Maintenance
title_full_unstemmed Application of Deep Learning and Unmanned Aerial Vehicle on Building Maintenance
title_short Application of Deep Learning and Unmanned Aerial Vehicle on Building Maintenance
title_sort application of deep learning and unmanned aerial vehicle on building maintenance
url http://dx.doi.org/10.1155/2021/5598690
work_keys_str_mv AT renyikung applicationofdeeplearningandunmannedaerialvehicleonbuildingmaintenance
AT naihsinpan applicationofdeeplearningandunmannedaerialvehicleonbuildingmaintenance
AT charlescnwang applicationofdeeplearningandunmannedaerialvehicleonbuildingmaintenance
AT pinchanlee applicationofdeeplearningandunmannedaerialvehicleonbuildingmaintenance