Enhancement of Multi-Class Structural Defect Recognition Using Generative Adversarial Network

Hyunkyu Shin, Yonghan Ahn, Sungho Tae, Heungbae Gil, Mihwa Song and Sanghyo Lee
Additional contact information
Hyunkyu Shin: Center for AI Technology in Construction, Hanyang University ERICA, 55, Hanyangdaehak-ro, Sangnok-gu, Ansan 15588, Korea
Yonghan Ahn: School of Architecture and Architectural Engineering, Hanyang University ERICA, 55, Hanyangdaehak-ro, Sangnok-gu, Ansan 15588, Korea
Sungho Tae: School of Architecture and Architectural Engineering, Hanyang University ERICA, 55, Hanyangdaehak-ro, Sangnok-gu, Ansan 15588, Korea
Heungbae Gil: ICT Convergence Research Division, Korea Expressway Corporation Research Institute, 24 Dongtansunhwan-daero 17-gil, Dongtan-myeon, Hwaseong 18489, Korea
Mihwa Song: ICT Convergence Research Division, Korea Expressway Corporation Research Institute, 24 Dongtansunhwan-daero 17-gil, Dongtan-myeon, Hwaseong 18489, Korea
Sanghyo Lee: Division of Smart Convergence Engineering, Hanyang University ERICA, 55, Hanyangdaehak-ro, Sangnok-gu, Ansan 15588, Korea

Sustainability, 2021, vol. 13, issue 22, 1-13

Abstract: Recently, in the building and infrastructure fields, studies on defect detection methods using deep learning have been widely implemented. For robust automatic recognition of defects in buildings, a sufficiently large training dataset is required for the target defects. However, it is challenging to collect sufficient data from degrading building structures. To address the data shortage and imbalance problem, in this study, a data augmentation method was developed using a generative adversarial network (GAN). To confirm the effect of data augmentation in the defect dataset of old structures, two scenarios were compared and experiments were conducted. As a result, in the models that applied the GAN-based data augmentation experimentally, the average performance increased by approximately 0.16 compared to the model trained using a small dataset. Based on the results of the experiments, the GAN-based data augmentation strategy is expected to be a reliable alternative to complement defect datasets with an unbalanced number of objects.

Keywords: generative adversarial network; data augmentation; defect recognition; deep learning; convolutional neural network (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/13/22/12682/pdf (application/pdf)
https://www.mdpi.com/2071-1050/13/22/12682/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:13:y:2021:i:22:p:12682-:d:680541

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().