Suppression of Multiple Reflection Interference Signals in GPR Images Caused by Rebar Using VAE-GAN

Due to the rebars layer’s shielding effect on Ground Penetrating Radar (GPR) waves, the hyperbolic clutter generated by the rebars interferes with the echoes from void beneath them. The overlapping waveforms of both signals result in attenuation and distortion of the void signals, making it difficul...

Full description

Saved in:
Bibliographic Details
Main Authors: Chuan Li, Qibing Ma, Yawei Wang, Xi Yang, Hao Liu, Lulu Wang
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/7/3728
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850184658965233664
author Chuan Li
Qibing Ma
Yawei Wang
Xi Yang
Hao Liu
Lulu Wang
author_facet Chuan Li
Qibing Ma
Yawei Wang
Xi Yang
Hao Liu
Lulu Wang
author_sort Chuan Li
collection DOAJ
description Due to the rebars layer’s shielding effect on Ground Penetrating Radar (GPR) waves, the hyperbolic clutter generated by the rebars interferes with the echoes from void beneath them. The overlapping waveforms of both signals result in attenuation and distortion of the void signals, making it difficult to identify void defects under the rebar. This study proposes an unsupervised generative network model based on Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs). Through a shared latent space, mapping is achieved between two image domains, effectively eliminating the multiple reflection interference signals caused by the rebar while accurately reconstructing the void defects, generating GPR B-Scan images without rebar clutter. Additionally, the channel and spatial attention module (CSA) is implemented into the model to help the network to better focus on the essential information in GPR images. The proposed model was validated through ablation and comparative experiments using synthetic data. Finally, real GPR data from the Husa Tunnel were used to verify the model’s effectiveness in practical engineering applications. The results showed that this model is highly effective; it improves the visibility of void defects signals, thereby enhancing the interpretability of GPR data for tunnel lining inspections.
format Article
id doaj-art-44cc000a036045bb9adb2d463555b92d
institution OA Journals
issn 2076-3417
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-44cc000a036045bb9adb2d463555b92d2025-08-20T02:17:00ZengMDPI AGApplied Sciences2076-34172025-03-01157372810.3390/app15073728Suppression of Multiple Reflection Interference Signals in GPR Images Caused by Rebar Using VAE-GANChuan Li0Qibing Ma1Yawei Wang2Xi Yang3Hao Liu4Lulu Wang5Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650051, ChinaFaculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650051, ChinaFaculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650051, ChinaYunnan Aerospace Engineering Geophysical Detecting Co., Ltd., Kunming 650029, ChinaYunnan Aerospace Engineering Geophysical Detecting Co., Ltd., Kunming 650029, ChinaFaculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650051, ChinaDue to the rebars layer’s shielding effect on Ground Penetrating Radar (GPR) waves, the hyperbolic clutter generated by the rebars interferes with the echoes from void beneath them. The overlapping waveforms of both signals result in attenuation and distortion of the void signals, making it difficult to identify void defects under the rebar. This study proposes an unsupervised generative network model based on Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs). Through a shared latent space, mapping is achieved between two image domains, effectively eliminating the multiple reflection interference signals caused by the rebar while accurately reconstructing the void defects, generating GPR B-Scan images without rebar clutter. Additionally, the channel and spatial attention module (CSA) is implemented into the model to help the network to better focus on the essential information in GPR images. The proposed model was validated through ablation and comparative experiments using synthetic data. Finally, real GPR data from the Husa Tunnel were used to verify the model’s effectiveness in practical engineering applications. The results showed that this model is highly effective; it improves the visibility of void defects signals, thereby enhancing the interpretability of GPR data for tunnel lining inspections.https://www.mdpi.com/2076-3417/15/7/3728GPRvoid defectsrebar suppressionVAEGAN
spellingShingle Chuan Li
Qibing Ma
Yawei Wang
Xi Yang
Hao Liu
Lulu Wang
Suppression of Multiple Reflection Interference Signals in GPR Images Caused by Rebar Using VAE-GAN
Applied Sciences
GPR
void defects
rebar suppression
VAE
GAN
title Suppression of Multiple Reflection Interference Signals in GPR Images Caused by Rebar Using VAE-GAN
title_full Suppression of Multiple Reflection Interference Signals in GPR Images Caused by Rebar Using VAE-GAN
title_fullStr Suppression of Multiple Reflection Interference Signals in GPR Images Caused by Rebar Using VAE-GAN
title_full_unstemmed Suppression of Multiple Reflection Interference Signals in GPR Images Caused by Rebar Using VAE-GAN
title_short Suppression of Multiple Reflection Interference Signals in GPR Images Caused by Rebar Using VAE-GAN
title_sort suppression of multiple reflection interference signals in gpr images caused by rebar using vae gan
topic GPR
void defects
rebar suppression
VAE
GAN
url https://www.mdpi.com/2076-3417/15/7/3728
work_keys_str_mv AT chuanli suppressionofmultiplereflectioninterferencesignalsingprimagescausedbyrebarusingvaegan
AT qibingma suppressionofmultiplereflectioninterferencesignalsingprimagescausedbyrebarusingvaegan
AT yaweiwang suppressionofmultiplereflectioninterferencesignalsingprimagescausedbyrebarusingvaegan
AT xiyang suppressionofmultiplereflectioninterferencesignalsingprimagescausedbyrebarusingvaegan
AT haoliu suppressionofmultiplereflectioninterferencesignalsingprimagescausedbyrebarusingvaegan
AT luluwang suppressionofmultiplereflectioninterferencesignalsingprimagescausedbyrebarusingvaegan