Accurate Image Separation Method for Two Closely Spaced Pedestrians Using UWB Doppler Imaging Radar and Supervised Learning

Kenshi SAHO; Hiroaki HOMMA; Takuya SAKAMOTO; Toru SATO; Kenichi INOUE; Takeshi FUKUDA

doi:10.1587/transcom.E97.B.1223

Accurate Image Separation Method for Two Closely Spaced Pedestrians Using UWB Doppler Imaging Radar and Supervised Learning

Kenshi SAHO, Hiroaki HOMMA, Takuya SAKAMOTO, Toru SATO, Kenichi INOUE, Takeshi FUKUDA

Full Text Views

0

Share
Cite this

Summary :

Recent studies have focused on developing security systems using micro-Doppler radars to detect human bodies. However, the resolution of these conventional methods is unsuitable for identifying bodies and moreover, most of these conventional methods were designed for a solitary or sufficiently well-spaced targets. This paper proposes a solution to these problems with an image separation method for two closely spaced pedestrian targets. The proposed method first develops an image of the targets using ultra-wide-band (UWB) Doppler imaging radar. Next, the targets in the image are separated using a supervised learning-based separation method trained on a data set extracted using a range profile. We experimentally evaluated the performance of the image separation using some representative supervised separation methods and selected the most appropriate method. Finally, we reject false points caused by target interference based on the separation result. The experiment, assuming two pedestrians with a body separation of 0.44m, shows that our method accurately separates their images using a UWB Doppler radar with a nominal down-range resolution of 0.3m. We describe applications using various target positions, establish the performance, and derive optimal settings for our method.

Publication: IEICE TRANSACTIONS on Communications Vol.E97-B No.6 pp.1223-1233

Publication Date: 2014/06/01

Publicized

Online ISSN: 1745-1345

DOI: 10.1587/transcom.E97.B.1223

Type of Manuscript: PAPER

Category: Sensing

Authors

Kenshi SAHO
  Kyoto University
Hiroaki HOMMA
  Kyoto University
Takuya SAKAMOTO
  Kyoto University
Toru SATO
  Kyoto University
Kenichi INOUE
  Panasonic Corporation
Takeshi FUKUDA
  Panasonic Corporation

Keyword

human imaging, closely-spaced pedestrians, image separation, UWB Doppler radar, supervised learning, support vector machine (SVM)

Cite this

Copy

Kenshi SAHO, Hiroaki HOMMA, Takuya SAKAMOTO, Toru SATO, Kenichi INOUE, Takeshi FUKUDA, "Accurate Image Separation Method for Two Closely Spaced Pedestrians Using UWB Doppler Imaging Radar and Supervised Learning" in IEICE TRANSACTIONS on Communications, vol. E97-B, no. 6, pp. 1223-1233, June 2014, doi: 10.1587/transcom.E97.B.1223.
Abstract: Recent studies have focused on developing security systems using micro-Doppler radars to detect human bodies. However, the resolution of these conventional methods is unsuitable for identifying bodies and moreover, most of these conventional methods were designed for a solitary or sufficiently well-spaced targets. This paper proposes a solution to these problems with an image separation method for two closely spaced pedestrian targets. The proposed method first develops an image of the targets using ultra-wide-band (UWB) Doppler imaging radar. Next, the targets in the image are separated using a supervised learning-based separation method trained on a data set extracted using a range profile. We experimentally evaluated the performance of the image separation using some representative supervised separation methods and selected the most appropriate method. Finally, we reject false points caused by target interference based on the separation result. The experiment, assuming two pedestrians with a body separation of 0.44m, shows that our method accurately separates their images using a UWB Doppler radar with a nominal down-range resolution of 0.3m. We describe applications using various target positions, establish the performance, and derive optimal settings for our method.
URL: https://globals.ieice.org/en_transactions/communications/10.1587/transcom.E97.B.1223/_p

Copy

@ARTICLE{e97-b_6_1223,
author={Kenshi SAHO, Hiroaki HOMMA, Takuya SAKAMOTO, Toru SATO, Kenichi INOUE, Takeshi FUKUDA, },
journal={IEICE TRANSACTIONS on Communications},
title={Accurate Image Separation Method for Two Closely Spaced Pedestrians Using UWB Doppler Imaging Radar and Supervised Learning},
year={2014},
volume={E97-B},
number={6},
pages={1223-1233},
abstract={Recent studies have focused on developing security systems using micro-Doppler radars to detect human bodies. However, the resolution of these conventional methods is unsuitable for identifying bodies and moreover, most of these conventional methods were designed for a solitary or sufficiently well-spaced targets. This paper proposes a solution to these problems with an image separation method for two closely spaced pedestrian targets. The proposed method first develops an image of the targets using ultra-wide-band (UWB) Doppler imaging radar. Next, the targets in the image are separated using a supervised learning-based separation method trained on a data set extracted using a range profile. We experimentally evaluated the performance of the image separation using some representative supervised separation methods and selected the most appropriate method. Finally, we reject false points caused by target interference based on the separation result. The experiment, assuming two pedestrians with a body separation of 0.44m, shows that our method accurately separates their images using a UWB Doppler radar with a nominal down-range resolution of 0.3m. We describe applications using various target positions, establish the performance, and derive optimal settings for our method.},
keywords={},
doi={10.1587/transcom.E97.B.1223},
ISSN={1745-1345},
month={June},}

Copy

TY - JOUR
TI - Accurate Image Separation Method for Two Closely Spaced Pedestrians Using UWB Doppler Imaging Radar and Supervised Learning
T2 - IEICE TRANSACTIONS on Communications
SP - 1223
EP - 1233
AU - Kenshi SAHO
AU - Hiroaki HOMMA
AU - Takuya SAKAMOTO
AU - Toru SATO
AU - Kenichi INOUE
AU - Takeshi FUKUDA
PY - 2014
DO - 10.1587/transcom.E97.B.1223
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E97-B
IS - 6
JA - IEICE TRANSACTIONS on Communications
Y1 - June 2014
AB - Recent studies have focused on developing security systems using micro-Doppler radars to detect human bodies. However, the resolution of these conventional methods is unsuitable for identifying bodies and moreover, most of these conventional methods were designed for a solitary or sufficiently well-spaced targets. This paper proposes a solution to these problems with an image separation method for two closely spaced pedestrian targets. The proposed method first develops an image of the targets using ultra-wide-band (UWB) Doppler imaging radar. Next, the targets in the image are separated using a supervised learning-based separation method trained on a data set extracted using a range profile. We experimentally evaluated the performance of the image separation using some representative supervised separation methods and selected the most appropriate method. Finally, we reject false points caused by target interference based on the separation result. The experiment, assuming two pedestrians with a body separation of 0.44m, shows that our method accurately separates their images using a UWB Doppler radar with a nominal down-range resolution of 0.3m. We describe applications using various target positions, establish the performance, and derive optimal settings for our method.
ER -