Presentation 2012-01-27
Accurate image separation of pedestrians with UWB Doppler imaging radars
Hiroaki HOMMA, Kenshi SAHO, Takuya SAKAMOTO, Toru SATO, Kenichi INOUE, Takashi FUKUDA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A numerous studies have been devoted to developing security systems using ultra-wideband Doppler imaging radars to detect human bodies. Most of these conventional methods have been designed for a single target, whereas it is needed to develop alternative methods applicable to multiple targets. One such method based on hierarchical clustering was developed to separate images of multiple targets, but its accuracy is not satisfactory in practice. This paper proposes another method using the support vector machine algorithm to achieve better accuracy. Numerical simulations establish that the proposed method is able to separate images of two targets with root-mean-square error of 5.24 cm.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) UWB Doppler imaging rader / support vector machine / pedestrian identification
Paper # SANE2011-153
Date of Issue

Conference Information
Committee SANE
Conference Date 2012/1/19(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 Space, Aeronautical and Navigational Electronics (SANE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Accurate image separation of pedestrians with UWB Doppler imaging radars
Sub Title (in English)
Keyword(1) UWB Doppler imaging rader
Keyword(2) support vector machine
Keyword(3) pedestrian identification
1st Author's Name Hiroaki HOMMA
1st Author's Affiliation Graduate School of Informatics, Kyoto University()
2nd Author's Name Kenshi SAHO
2nd Author's Affiliation Graduate School of Informatics, Kyoto University
3rd Author's Name Takuya SAKAMOTO
3rd Author's Affiliation Graduate School of Informatics, Kyoto University
4th Author's Name Toru SATO
4th Author's Affiliation Graduate School of Informatics, Kyoto University
5th Author's Name Kenichi INOUE
5th Author's Affiliation Advanced Technology Research Laboratories, Panasonic Co., Ltd.
6th Author's Name Takashi FUKUDA
6th Author's Affiliation Advanced Technology Research Laboratories, Panasonic Co., Ltd.
Date 2012-01-27
Paper # SANE2011-153
Volume (vol) vol.111
Number (no) 407
Page pp.pp.-
#Pages 6
Date of Issue