Presentation 2017-07-21
Characteristics of Object Identification by Ground Penetrating Radar Images using Deep Learning
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 adequately 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. In this study, to objectively and quantitatively inspect 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 have learned the underground object using the generated GPR images by a deep convolutional neural network (CNN). It is shown that we have obtained multilayer layers CNN can identify six materials and size with roughly 80 % accuracy in in-homogeneous underground media.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Deep learning / convolutional neural network / ground penetrating radar / FDTD method / GPU / object identification
Paper # EMT2017-23,MW2017-48,OPE2017-28,EST2017-25,MWP2017-25
Date of Issue 2017-07-13 (EMT, MW, OPE, EST, MWP)

Conference Information
Committee MWP / OPE / EMT / MW / EST / IEE-EMT
Conference Date 2017/7/20(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Obihiro Chamber of Commerce and Industry
Topics (in Japanese) (See Japanese page)
Topics (in English) Light wave & Electromagnetic Wave Workshop
Chair Tetsuya Kawanishi(Waseda Univ.) / Kazutoshi Kato(Kyushu Univ.) / Akira Hirose(Univ. of Tokyo) / Masahiro Muraguchi(TUC) / Hideaki Kimura(NTT) / Keiji Goto(National Defense Academy)
Vice Chair Naoto Yoshimoto(Chitose Inst. of Science and Tech.) / Kouki Sato(Furukawa Electric Industries) / Koichi Hirayama(Kitami Inst. of Tech.) / Yoshinori Kogami(Utsunomiya Univ.) / Hiroshi Okazaki(NTTdocomo) / Kenichi Tajima(Mitsubishi Electric) / Akimasa Hirata(Nagoya Inst. of Tech.) / Shinichiro Ohnuki(Nihon Univ.)
Secretary Naoto Yoshimoto(NICT) / Kouki Sato(Chiba Inst. of Tech.) / Koichi Hirayama(NTT) / Yoshinori Kogami(Kanagawa Inst. of Tech.) / Hiroshi Okazaki(Univ. of Hyogo) / Kenichi Tajima(Tokyo Metro. Coll. of Tech) / Akimasa Hirata(Tokyo Inst. of Tech.) / Shinichiro Ohnuki(HITACHI) / (Tohoku Univ.)
Assistant Kosuke Nishimura(KDDI) / Kensuke Ikeda(CRIEPI) / Takuo Tanemura(Univ. of Tokyo) / Tsuyoshi Matsuoka(Kyushu Sangyo Univ.) / Satoshi Ono(Univ. of Electro-Comm.) / Mizuki Motoyoshi(Tohoku Univ.) / Takahiro Ito(Nagoya Inst. of Tech.) / Kazuhiro Fujita(Fujitsu) / Yoshihiro Naka(KUHW)

Paper Information
Registration To Technical Committee on Microwave and Millimeter-wave Photonics / Technical Committee on OptoElectronics / Technical Committee on Electromagnetic Theory / Technical Committee on Microwaves / Technical Committee on Electronics Simulation Technology / Technical Meeting on Electromagnetic Theory
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Characteristics of Object Identification by Ground Penetrating Radar Images using Deep Learning
Sub Title (in English)
Keyword(1) Deep learning
Keyword(2) convolutional neural network
Keyword(3) ground penetrating radar
Keyword(4) FDTD method
Keyword(5) GPU
Keyword(6) object identification
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 2017-07-21
Paper # EMT2017-23,MW2017-48,OPE2017-28,EST2017-25,MWP2017-25
Volume (vol) vol.117
Number (no) EMT-139,MW-140,OPE-141,EST-142,MWP-143
Page pp.pp.89-94(EMT), pp.89-94(MW), pp.89-94(OPE), pp.89-94(EST), pp.89-94(MWP),
#Pages 6
Date of Issue 2017-07-13 (EMT, MW, OPE, EST, MWP)