Person searching through an omnidirectional camera using CNN in the tsukuba challenge

Shingo Nakamura, Tadahiro Hasegawa, Tsubasa Hiraoka, Yoshinori Ochiai, Shinichi Yuta

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The Tsukuba Challenge is a competition, in which autonomous mobile robots run on a route set on a public road under a real environment. Their task includes not only simple running but also finding multiple specific persons at the same time. This study proposes a method that would realize person searching. While many person-searching algorithms use a laser sensor and a camera in combination, our method only uses an omnidirectional camera. The search target is detected using a convolutional neural network (CNN) that performs a classification of the search target. Training a CNN requires a great amount of data for which pseudo images created by composition are used. Our method is implemented in an autonomous mobile robot, and its performance has been verified in the Tsukuba Challenge 2017.

Original languageEnglish
Pages (from-to)540-551
Number of pages12
JournalJournal of Robotics and Mechatronics
Volume30
Issue number4
DOIs
Publication statusPublished - 2018 Aug 1

Fingerprint

Mobile robots
Cameras
Neural networks
Lasers
Sensors
Chemical analysis

Keywords

  • Convolutional neural networks
  • Omnidirectional camera
  • Person searching
  • Tsukuba challenge

ASJC Scopus subject areas

  • Computer Science(all)
  • Electrical and Electronic Engineering

Cite this

Person searching through an omnidirectional camera using CNN in the tsukuba challenge. / Nakamura, Shingo; Hasegawa, Tadahiro; Hiraoka, Tsubasa; Ochiai, Yoshinori; Yuta, Shinichi.

In: Journal of Robotics and Mechatronics, Vol. 30, No. 4, 01.08.2018, p. 540-551.

Research output: Contribution to journalArticle

@article{b2cf83566add4e39876e615e0729ad86,
title = "Person searching through an omnidirectional camera using CNN in the tsukuba challenge",
abstract = "The Tsukuba Challenge is a competition, in which autonomous mobile robots run on a route set on a public road under a real environment. Their task includes not only simple running but also finding multiple specific persons at the same time. This study proposes a method that would realize person searching. While many person-searching algorithms use a laser sensor and a camera in combination, our method only uses an omnidirectional camera. The search target is detected using a convolutional neural network (CNN) that performs a classification of the search target. Training a CNN requires a great amount of data for which pseudo images created by composition are used. Our method is implemented in an autonomous mobile robot, and its performance has been verified in the Tsukuba Challenge 2017.",
keywords = "Convolutional neural networks, Omnidirectional camera, Person searching, Tsukuba challenge",
author = "Shingo Nakamura and Tadahiro Hasegawa and Tsubasa Hiraoka and Yoshinori Ochiai and Shinichi Yuta",
year = "2018",
month = "8",
day = "1",
doi = "10.20965/jrm.2018.p0540",
language = "English",
volume = "30",
pages = "540--551",
journal = "Journal of Robotics and Mechatronics",
issn = "0915-3942",
publisher = "Fuji Technology Press",
number = "4",

}

TY - JOUR

T1 - Person searching through an omnidirectional camera using CNN in the tsukuba challenge

AU - Nakamura, Shingo

AU - Hasegawa, Tadahiro

AU - Hiraoka, Tsubasa

AU - Ochiai, Yoshinori

AU - Yuta, Shinichi

PY - 2018/8/1

Y1 - 2018/8/1

N2 - The Tsukuba Challenge is a competition, in which autonomous mobile robots run on a route set on a public road under a real environment. Their task includes not only simple running but also finding multiple specific persons at the same time. This study proposes a method that would realize person searching. While many person-searching algorithms use a laser sensor and a camera in combination, our method only uses an omnidirectional camera. The search target is detected using a convolutional neural network (CNN) that performs a classification of the search target. Training a CNN requires a great amount of data for which pseudo images created by composition are used. Our method is implemented in an autonomous mobile robot, and its performance has been verified in the Tsukuba Challenge 2017.

AB - The Tsukuba Challenge is a competition, in which autonomous mobile robots run on a route set on a public road under a real environment. Their task includes not only simple running but also finding multiple specific persons at the same time. This study proposes a method that would realize person searching. While many person-searching algorithms use a laser sensor and a camera in combination, our method only uses an omnidirectional camera. The search target is detected using a convolutional neural network (CNN) that performs a classification of the search target. Training a CNN requires a great amount of data for which pseudo images created by composition are used. Our method is implemented in an autonomous mobile robot, and its performance has been verified in the Tsukuba Challenge 2017.

KW - Convolutional neural networks

KW - Omnidirectional camera

KW - Person searching

KW - Tsukuba challenge

UR - http://www.scopus.com/inward/record.url?scp=85052198459&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85052198459&partnerID=8YFLogxK

U2 - 10.20965/jrm.2018.p0540

DO - 10.20965/jrm.2018.p0540

M3 - Article

AN - SCOPUS:85052198459

VL - 30

SP - 540

EP - 551

JO - Journal of Robotics and Mechatronics

JF - Journal of Robotics and Mechatronics

SN - 0915-3942

IS - 4

ER -