Presentation 2008-07-24
GPR signal processing and feature extraction for landmine discrimination
Masahiko NISHIMOTO, Takaaki TANAKA, Yusuke KIMURA, Vakhtang JANDIERI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Ground penetrating radar is one of the sensors applicable to landmine detection. However, for practical application of GPR sensors to detection of buried landmines, it is required to reduce high incidence of false alarms caused by a strong ground clutter and returns from other confusing objects such as stones, tree roots, or metal fragments underground. In order to reduce the false alarms, development of identification techniques for GPR sensor to discriminate desired landmines between confusing objects becomes important. In this study, we propose three kinds of features for landmine discrimination and demonstrate the effectiveness and limitations of them through Monte Carlo simulations. As the landmine model, we employ a landmine-shape object with a small air gap in it and generate data samples by using a two-dimensional FDTD method. Effects of soil condition and inclination of the landmine on discrimination performance are checked, and applicability of the features to actual problems is also checked through simple laboratory experiments.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) landmine / ground penetrating radar / feature extraction
Paper # MW2008-68,OPE2008-51
Date of Issue

Conference Information
Committee OPE
Conference Date 2008/7/17(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Optoelectronics (OPE)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) GPR signal processing and feature extraction for landmine discrimination
Sub Title (in English)
Keyword(1) landmine
Keyword(2) ground penetrating radar
Keyword(3) feature extraction
1st Author's Name Masahiko NISHIMOTO
1st Author's Affiliation Graduate School of Science and Technology, Kumamoto University()
2nd Author's Name Takaaki TANAKA
2nd Author's Affiliation Graduate School of Science and Technology, Kumamoto University
3rd Author's Name Yusuke KIMURA
3rd Author's Affiliation Graduate School of Science and Technology, Kumamoto University
4th Author's Name Vakhtang JANDIERI
4th Author's Affiliation Graduate School of Science and Technology, Kumamoto University
Date 2008-07-24
Paper # MW2008-68,OPE2008-51
Volume (vol) vol.108
Number (no) 155
Page pp.pp.-
#Pages 6
Date of Issue