Denoising Ground Penetrating Radar Images Using Generative Adversarial Networks

Ngoc Quy Hoang; Seonghun Kang; Jong Sub Lee

doi:10.1007/978-981-99-9722-0_159

Denoising Ground Penetrating Radar Images Using Generative Adversarial Networks

Ngoc Quy Hoang
, Seonghun Kang
, Jong Sub Lee^*

^*Corresponding author for this work

School of Civil, Environmental and Architectural Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Citations (Scopus)

Abstract

The objective of this study is to improve the visual quality of noisy ground penetrating radar (GPR) images by developing a deep learning network. The dataset includes noisy GPR images that were generated by adding white noise with a coefficient of variation of 1.0, and the original raw GPR images as labels. In addition, a denoising deep learning network was built and trained on the dataset. The experimental results show that the denoising network performs well with high peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) values. Furthermore, the denoised GPR images show as much detail as the ground-truth images. This study shows that the denoising network significantly denoises the GPR images.

Original language	English
Title of host publication	Proceedings of the 5th International Conference on Geotechnics for Sustainable Infrastructure Development - GEOTEC 2023
Editors	Phung Duc Long, Nguyen Tien Dung
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	2343-2349
Number of pages	7
ISBN (Print)	9789819997213
DOIs	https://doi.org/10.1007/978-981-99-9722-0_159
Publication status	Published - 2024
Event	5th International Conference on Geotechnics for Sustainable Infrastructure Development, GEOTEC 2023 - Hanoi, Viet Nam Duration: 2023 Dec 14 → 2023 Dec 15

Publication series

Name	Lecture Notes in Civil Engineering
Volume	395
ISSN (Print)	2366-2557
ISSN (Electronic)	2366-2565

Conference

Conference	5th International Conference on Geotechnics for Sustainable Infrastructure Development, GEOTEC 2023
Country/Territory	Viet Nam
City	Hanoi
Period	23/12/14 → 23/12/15

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

Keywords

Deep learning
Denoise
GPR
Image
Super resolution

ASJC Scopus subject areas

Civil and Structural Engineering

Access to Document

10.1007/978-981-99-9722-0_159

Cite this

Hoang, N. Q., Kang, S., & Lee, J. S. (2024). Denoising Ground Penetrating Radar Images Using Generative Adversarial Networks. In P. Duc Long, & N. T. Dung (Eds.), Proceedings of the 5th International Conference on Geotechnics for Sustainable Infrastructure Development - GEOTEC 2023 (pp. 2343-2349). (Lecture Notes in Civil Engineering; Vol. 395). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-99-9722-0_159

Denoising Ground Penetrating Radar Images Using Generative Adversarial Networks. / Hoang, Ngoc Quy; Kang, Seonghun; Lee, Jong Sub.
Proceedings of the 5th International Conference on Geotechnics for Sustainable Infrastructure Development - GEOTEC 2023. ed. / Phung Duc Long; Nguyen Tien Dung. Springer Science and Business Media Deutschland GmbH, 2024. p. 2343-2349 (Lecture Notes in Civil Engineering; Vol. 395).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Hoang, NQ, Kang, S & Lee, JS 2024, Denoising Ground Penetrating Radar Images Using Generative Adversarial Networks. in P Duc Long & NT Dung (eds), Proceedings of the 5th International Conference on Geotechnics for Sustainable Infrastructure Development - GEOTEC 2023. Lecture Notes in Civil Engineering, vol. 395, Springer Science and Business Media Deutschland GmbH, pp. 2343-2349, 5th International Conference on Geotechnics for Sustainable Infrastructure Development, GEOTEC 2023, Hanoi, Viet Nam, 23/12/14. https://doi.org/10.1007/978-981-99-9722-0_159

Hoang NQ, Kang S, Lee JS. Denoising Ground Penetrating Radar Images Using Generative Adversarial Networks. In Duc Long P, Dung NT, editors, Proceedings of the 5th International Conference on Geotechnics for Sustainable Infrastructure Development - GEOTEC 2023. Springer Science and Business Media Deutschland GmbH. 2024. p. 2343-2349. (Lecture Notes in Civil Engineering). doi: 10.1007/978-981-99-9722-0_159

Hoang, Ngoc Quy ; Kang, Seonghun ; Lee, Jong Sub. / Denoising Ground Penetrating Radar Images Using Generative Adversarial Networks. Proceedings of the 5th International Conference on Geotechnics for Sustainable Infrastructure Development - GEOTEC 2023. editor / Phung Duc Long ; Nguyen Tien Dung. Springer Science and Business Media Deutschland GmbH, 2024. pp. 2343-2349 (Lecture Notes in Civil Engineering).

@inproceedings{d4601117d0cf4daf8f448dd657a30712,

title = "Denoising Ground Penetrating Radar Images Using Generative Adversarial Networks",

abstract = "The objective of this study is to improve the visual quality of noisy ground penetrating radar (GPR) images by developing a deep learning network. The dataset includes noisy GPR images that were generated by adding white noise with a coefficient of variation of 1.0, and the original raw GPR images as labels. In addition, a denoising deep learning network was built and trained on the dataset. The experimental results show that the denoising network performs well with high peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) values. Furthermore, the denoised GPR images show as much detail as the ground-truth images. This study shows that the denoising network significantly denoises the GPR images.",

keywords = "Deep learning, Denoise, GPR, Image, Super resolution",

author = "Hoang, \{Ngoc Quy\} and Seonghun Kang and Lee, \{Jong Sub\}",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.; 5th International Conference on Geotechnics for Sustainable Infrastructure Development, GEOTEC 2023 ; Conference date: 14-12-2023 Through 15-12-2023",

year = "2024",

doi = "10.1007/978-981-99-9722-0\_159",

language = "English",

isbn = "9789819997213",

series = "Lecture Notes in Civil Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "2343--2349",

editor = "\{Duc Long\}, Phung and Dung, \{Nguyen Tien\}",

booktitle = "Proceedings of the 5th International Conference on Geotechnics for Sustainable Infrastructure Development - GEOTEC 2023",

address = "Germany",

}

TY - GEN

T1 - Denoising Ground Penetrating Radar Images Using Generative Adversarial Networks

AU - Hoang, Ngoc Quy

AU - Kang, Seonghun

AU - Lee, Jong Sub

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

PY - 2024

Y1 - 2024

N2 - The objective of this study is to improve the visual quality of noisy ground penetrating radar (GPR) images by developing a deep learning network. The dataset includes noisy GPR images that were generated by adding white noise with a coefficient of variation of 1.0, and the original raw GPR images as labels. In addition, a denoising deep learning network was built and trained on the dataset. The experimental results show that the denoising network performs well with high peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) values. Furthermore, the denoised GPR images show as much detail as the ground-truth images. This study shows that the denoising network significantly denoises the GPR images.

AB - The objective of this study is to improve the visual quality of noisy ground penetrating radar (GPR) images by developing a deep learning network. The dataset includes noisy GPR images that were generated by adding white noise with a coefficient of variation of 1.0, and the original raw GPR images as labels. In addition, a denoising deep learning network was built and trained on the dataset. The experimental results show that the denoising network performs well with high peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) values. Furthermore, the denoised GPR images show as much detail as the ground-truth images. This study shows that the denoising network significantly denoises the GPR images.

KW - Deep learning

KW - Denoise

KW - GPR

KW - Image

KW - Super resolution

UR - https://www.scopus.com/pages/publications/85200781525

U2 - 10.1007/978-981-99-9722-0_159

DO - 10.1007/978-981-99-9722-0_159

M3 - Conference contribution

AN - SCOPUS:85200781525

SN - 9789819997213

T3 - Lecture Notes in Civil Engineering

SP - 2343

EP - 2349

BT - Proceedings of the 5th International Conference on Geotechnics for Sustainable Infrastructure Development - GEOTEC 2023

A2 - Duc Long, Phung

A2 - Dung, Nguyen Tien

PB - Springer Science and Business Media Deutschland GmbH

T2 - 5th International Conference on Geotechnics for Sustainable Infrastructure Development, GEOTEC 2023

Y2 - 14 December 2023 through 15 December 2023

ER -

Denoising Ground Penetrating Radar Images Using Generative Adversarial Networks

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this