| Presentation | 2019-01-18 Super-resolution for GPR Images by Deep Learning Using Generative Adversarial Networks 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 recognize the underground objects from the GPR images, we have developed a super-resolution method for 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 / super-resolution / FDTD method / GPU |
| Paper # | PN2018-75,EMT2018-109,OPE2018-184,LQE2018-194,EST2018-122,MWP2018-93 |
| Date of Issue | 2019-01-10 (PN, EMT, OPE, LQE, EST, MWP) |
| Conference Information | |
| Committee | PN / EMT / OPE / EST / MWP / LQE / IEE-EMT |
|---|---|
| Conference Date | 2019/1/17(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Osaka University Nakanoshima Center |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Hiroshi Hasegawa(Nagoya Univ.) / Akira Hirose(Univ. of Tokyo) / Kouki Sato(Furukawa Electric Industries) / Akimasa Hirata(Nagoya Inst. of Tech.) / Tetsuya Kawanishi(Waseda Univ.) / Kiichi Hamamoto(Kyusyu Univ.) / Keiji Goto(National Defense Academy) |
| Vice Chair | Haruki Ogoshi(Furukawa Electric) / Takehiro Tsuritani(KDDI Research) / Hideaki Furukawa(NICT) / Koichi Hirayama(Kitami Inst. of Tech.) / Hiroshi Takahashi(Sophia Univ.) / Shinichiro Ohnuki(Nihon Univ.) / Masayuki Kimishima(Advantest) / Jun Shibayama(Hosei Univ.) / Naoto Yoshimoto(Chitose Inst. of Science and Tech.) / Hiroshi Aruga(Mitsubishi Electric) |
| Secretary | Haruki Ogoshi(NICT) / Takehiro Tsuritani(Univ. of Fukui) / Hideaki Furukawa(NTT) / Koichi Hirayama(Tokyo Metro. Coll. of Tech) / Hiroshi Takahashi(Fukuoka Inst.of Tech.) / Shinichiro Ohnuki(Univ. of Tokyo) / Masayuki Kimishima(NICT) / Jun Shibayama(CIST) / Naoto Yoshimoto(National Inst. of Tech.,Sendai College) / Hiroshi Aruga(NICT) / (Chiba Inst. of Tech.) |
| Assistant | Keijiro Suzuki(AIST) / Junichiro Sugisaka(Kitami Inst. of Tech.) / Yuya Shoji(Tokyo Inst. of Tech.) / Kazunori Seno(NTT) / Takahiro Ito(Nagoya Inst. of Tech.) / Kazuhiro Fujita(Fujitsu) / Kensuke Ikeda(CRIEPI) / Kosuke Nishimura(KDDI Research) / Masaya Nagai(Osaka Univ.) / Yoshihiro Naka(Kyushu Univ. of Health and Welfare) |
| Paper Information | |
| Registration To | Technical Committee on Photonic Network / Technical Committee on Electromagnetic Theory / Technical Committee on OptoElectronics / Technical Committee on Electronics Simulation Technology / Technical Committee on Microwave and Millimeter-wave Photonics / Technical Committee on Lasers and Quantum Electronics / Technical Meeting on Electromagnetic Theory |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Super-resolution for GPR Images by Deep Learning Using Generative Adversarial Networks |
| Sub Title (in English) | |
| Keyword(1) | generative adversarial networks |
| Keyword(2) | deep learning |
| Keyword(3) | ground penetrating radar |
| Keyword(4) | super-resolution |
| 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) |
| 2nd Author's Name | Tomoyuki Kimoto |
| 2nd Author's Affiliation | National Institute of Technology, Oita College(NIT, Oita) |
| Date | 2019-01-18 |
| Paper # | PN2018-75,EMT2018-109,OPE2018-184,LQE2018-194,EST2018-122,MWP2018-93 |
| Volume (vol) | vol.118 |
| Number (no) | PN-396,EMT-397,OPE-398,LQE-399,EST-400,MWP-401 |
| Page | pp.pp.237-242(PN), pp.237-242(EMT), pp.237-242(OPE), pp.237-242(LQE), pp.237-242(EST), pp.237-242(MWP), |
| #Pages | 6 |
| Date of Issue | 2019-01-10 (PN, EMT, OPE, LQE, EST, MWP) |