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

Hyunkyu Shin,Sanghyo Lee,Mihwa Song,Sungho Tae,Yonghan Ahn,Heungbae Gil

doi:10.3390/su132212682

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.

Highlights

Gao [30] applied a generative adversarial network (GAN) for infrastructural image data augmentation, and the results demonstrated the effectiveness and robustness of the proposed methods
With geometric data augmentation and to demonstrate experimentally that GAN-based data augmentation contributes to the improvement of the structural damage recognition model
In contrast to previous studies, this study presented selective GAN-based data augmentation approaches to solve the imbalance of specific defects such as leakage and rebar exposure, which are relatively low in frequency

Summary

Introduction

The demand for the development of efficient inspection methods of old building structures using automatic technology has increased, because the traditional inspection approach is time-consuming and costly. For this reason, in the building and infrastructure fields, many studies have explored vision-based approaches to detect damage in structures for more efficient diagnosis and maintenance [1,2]. Previous studies have demonstrated that structural defects can be automatically recognized by analyzing visual data. These studies have only focused on single damage identification and detection; they have limitations for application in multi-damage recognition. The degrading buildings and infrastructures expose diverse defects on the superficial structures

Objectives

Methods

Conclusion