Presentation | 2018-09-06 Clutter Reduction from GPR Image by Deep Learning Using Generative Adversarial Network Jun Sonoda, Tomoyuki Kimoto, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Recently, deterioration of social infrastructures such as tunnels and bridges become a serious social problem. It is required to rapidly and accurately detect for abnormal parts of the social infrastructures. The ground penetrating radar (GPR) is efficient for the social infrastructure inspection. However, it is difficult to identify the material and size of the underground object from the radar image obtained the GPR. To objectively and quantitatively investigate from the GPR images by the deep learning, we have automatically and massively generated the GPR images by a fast finite-difference time-domain (FDTD) simulation with graphics processing units (GPUs), and it has been learned the underground object using a deep convolutional neural network (CNN), with the generated GPR images. As the results, we have obtained multilayer layers CNN can identify six materials and size with roughly more than 80% accuracy in some inhomogeneous underground. In this study, to increase the accuracy of object identification for the GPR images with many clutters in some inhomogeneous underground, we try to reduce clutters from the GPR images by the deep learning using the generative adversarial networks (GAN). |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | generative adversarial networks / deep learning / ground penetrating radar / clutter reducing / FDTD method / GPU |
Paper # | EST2018-51 |
Date of Issue | 2018-08-30 (EST) |
Conference Information | |
Committee | EST |
---|---|
Conference Date | 2018/9/6(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Kumejima-machi, Okinawa |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Simulation techniques, etc. |
Chair | Akimasa Hirata(Nagoya Inst. of Tech.) |
Vice Chair | Shinichiro Ohnuki(Nihon Univ.) / Masayuki Kimishima(Advantest) / Jun Shibayama(Hosei Univ.) |
Secretary | Shinichiro Ohnuki(CIST) / Masayuki Kimishima(National Inst. of Tech.,Sendai College) / Jun Shibayama |
Assistant | Takahiro Ito(Nagoya Inst. of Tech.) / Kazuhiro Fujita(Fujitsu) |
Paper Information | |
Registration To | Technical Committee on Electronics Simulation Technology |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Clutter Reduction from GPR Image by Deep Learning Using Generative Adversarial Network |
Sub Title (in English) | |
Keyword(1) | generative adversarial networks |
Keyword(2) | deep learning |
Keyword(3) | ground penetrating radar |
Keyword(4) | clutter reducing |
Keyword(5) | FDTD method |
Keyword(6) | GPU |
1st Author's Name | Jun Sonoda |
1st Author's Affiliation | National Institute of Technology, Sendai College(NIT, Sendai College) |
2nd Author's Name | Tomoyuki Kimoto |
2nd Author's Affiliation | National Institute of Technology, Oita College(NIT, Oita College) |
Date | 2018-09-06 |
Paper # | EST2018-51 |
Volume (vol) | vol.118 |
Number (no) | EST-209 |
Page | pp.pp.47-51(EST), |
#Pages | 5 |
Date of Issue | 2018-08-30 (EST) |