People tracking in dense crowds using optical flow clustering based superpixel

Shota Takayama, Hirokatsu Kataoka, Sho Isobe, Naoki Kurita, Makoto Masuda, Yoshimitsu Aoki

Research output: Contribution to journalArticle

Abstract

People tracking in crowded scenes should be focused since the problem is beneficial and challenging in computer vision field. However, the problem of "crowd tracking" is extremely difficult because hard occlusions, various motions and posture changes. Especially in the crowd tracking, we need to handle occlusion for more robust tracking. This paper tackles a robust crowd tracking based on combination of superpixel and optical flow tracking. The SLIC based superpixel algorithm adaptively estimates a boundary between person and background, therefore the combination of superpixel and optical flow tracking becomes a highly confident tracking for crowd tracking. The tracking experiments show significant results on the UCF crowd dataset in terms of performance rate with comparison.

Original languageEnglish
Pages (from-to)259-265
Number of pages7
JournalSeimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering
Volume82
Issue number3
Publication statusPublished - 2016

Fingerprint

Optical flows
Computer vision
Experiments

Keywords

  • Dense crowd
  • Kmeans clustering
  • Optical flow
  • People tracking
  • Superpixel

ASJC Scopus subject areas

  • Mechanical Engineering

Cite this

People tracking in dense crowds using optical flow clustering based superpixel. / Takayama, Shota; Kataoka, Hirokatsu; Isobe, Sho; Kurita, Naoki; Masuda, Makoto; Aoki, Yoshimitsu.

In: Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering, Vol. 82, No. 3, 2016, p. 259-265.

Research output: Contribution to journalArticle

Takayama, Shota ; Kataoka, Hirokatsu ; Isobe, Sho ; Kurita, Naoki ; Masuda, Makoto ; Aoki, Yoshimitsu. / People tracking in dense crowds using optical flow clustering based superpixel. In: Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering. 2016 ; Vol. 82, No. 3. pp. 259-265.
@article{c4d5092f5501470bb74f04dc8c902819,
title = "People tracking in dense crowds using optical flow clustering based superpixel",
abstract = "People tracking in crowded scenes should be focused since the problem is beneficial and challenging in computer vision field. However, the problem of {"}crowd tracking{"} is extremely difficult because hard occlusions, various motions and posture changes. Especially in the crowd tracking, we need to handle occlusion for more robust tracking. This paper tackles a robust crowd tracking based on combination of superpixel and optical flow tracking. The SLIC based superpixel algorithm adaptively estimates a boundary between person and background, therefore the combination of superpixel and optical flow tracking becomes a highly confident tracking for crowd tracking. The tracking experiments show significant results on the UCF crowd dataset in terms of performance rate with comparison.",
keywords = "Dense crowd, Kmeans clustering, Optical flow, People tracking, Superpixel",
author = "Shota Takayama and Hirokatsu Kataoka and Sho Isobe and Naoki Kurita and Makoto Masuda and Yoshimitsu Aoki",
year = "2016",
language = "English",
volume = "82",
pages = "259--265",
journal = "Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering",
issn = "0912-0289",
publisher = "Japan Society for Precision Engineering",
number = "3",

}

TY - JOUR

T1 - People tracking in dense crowds using optical flow clustering based superpixel

AU - Takayama, Shota

AU - Kataoka, Hirokatsu

AU - Isobe, Sho

AU - Kurita, Naoki

AU - Masuda, Makoto

AU - Aoki, Yoshimitsu

PY - 2016

Y1 - 2016

N2 - People tracking in crowded scenes should be focused since the problem is beneficial and challenging in computer vision field. However, the problem of "crowd tracking" is extremely difficult because hard occlusions, various motions and posture changes. Especially in the crowd tracking, we need to handle occlusion for more robust tracking. This paper tackles a robust crowd tracking based on combination of superpixel and optical flow tracking. The SLIC based superpixel algorithm adaptively estimates a boundary between person and background, therefore the combination of superpixel and optical flow tracking becomes a highly confident tracking for crowd tracking. The tracking experiments show significant results on the UCF crowd dataset in terms of performance rate with comparison.

AB - People tracking in crowded scenes should be focused since the problem is beneficial and challenging in computer vision field. However, the problem of "crowd tracking" is extremely difficult because hard occlusions, various motions and posture changes. Especially in the crowd tracking, we need to handle occlusion for more robust tracking. This paper tackles a robust crowd tracking based on combination of superpixel and optical flow tracking. The SLIC based superpixel algorithm adaptively estimates a boundary between person and background, therefore the combination of superpixel and optical flow tracking becomes a highly confident tracking for crowd tracking. The tracking experiments show significant results on the UCF crowd dataset in terms of performance rate with comparison.

KW - Dense crowd

KW - Kmeans clustering

KW - Optical flow

KW - People tracking

KW - Superpixel

UR - http://www.scopus.com/inward/record.url?scp=84961147661&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961147661&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84961147661

VL - 82

SP - 259

EP - 265

JO - Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering

JF - Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering

SN - 0912-0289

IS - 3

ER -