Multiple players tracking and identification using group detection and player number recognition in sports video

Taiki Yamamoto, Hirokatsu Kataoka, Masaki Hayashi, Yoshimitsu Aoki, Kyoko Oshima, Masamoto Tanabiki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

We are interested in the problem of automatically tracking and identifying players in sports video. While there are many automatic multi-target tracking methods, in sports video, it is difficult to track multiple players due to frequent occlusions, quick motion of players and camera, and camera position. We propose tracking method that associates tracklets of a same player using results of player number recognition. To deal with frequent occlusions, we detect human region by level set method and then estimates if it is occluded group region or unoccluded individual one. Moreover, we associate tracklets using the results of player number recognition at each frame by keypoints-based matching with templates from multiple viewpoints, so that final tracklets include occluded region.

Original languageEnglish
Title of host publicationIECON Proceedings (Industrial Electronics Conference)
Pages2442-2446
Number of pages5
DOIs
Publication statusPublished - 2013
Event39th Annual Conference of the IEEE Industrial Electronics Society, IECON 2013 - Vienna, Austria
Duration: 2013 Nov 102013 Nov 14

Other

Other39th Annual Conference of the IEEE Industrial Electronics Society, IECON 2013
CountryAustria
CityVienna
Period13/11/1013/11/14

Fingerprint

Sports
Cameras
Target tracking

Keywords

  • Affin Warp
  • data association
  • level set method
  • multiple target tracking
  • SIFT

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Yamamoto, T., Kataoka, H., Hayashi, M., Aoki, Y., Oshima, K., & Tanabiki, M. (2013). Multiple players tracking and identification using group detection and player number recognition in sports video. In IECON Proceedings (Industrial Electronics Conference) (pp. 2442-2446). [6699514] https://doi.org/10.1109/IECON.2013.6699514

Multiple players tracking and identification using group detection and player number recognition in sports video. / Yamamoto, Taiki; Kataoka, Hirokatsu; Hayashi, Masaki; Aoki, Yoshimitsu; Oshima, Kyoko; Tanabiki, Masamoto.

IECON Proceedings (Industrial Electronics Conference). 2013. p. 2442-2446 6699514.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yamamoto, T, Kataoka, H, Hayashi, M, Aoki, Y, Oshima, K & Tanabiki, M 2013, Multiple players tracking and identification using group detection and player number recognition in sports video. in IECON Proceedings (Industrial Electronics Conference)., 6699514, pp. 2442-2446, 39th Annual Conference of the IEEE Industrial Electronics Society, IECON 2013, Vienna, Austria, 13/11/10. https://doi.org/10.1109/IECON.2013.6699514
Yamamoto T, Kataoka H, Hayashi M, Aoki Y, Oshima K, Tanabiki M. Multiple players tracking and identification using group detection and player number recognition in sports video. In IECON Proceedings (Industrial Electronics Conference). 2013. p. 2442-2446. 6699514 https://doi.org/10.1109/IECON.2013.6699514
Yamamoto, Taiki ; Kataoka, Hirokatsu ; Hayashi, Masaki ; Aoki, Yoshimitsu ; Oshima, Kyoko ; Tanabiki, Masamoto. / Multiple players tracking and identification using group detection and player number recognition in sports video. IECON Proceedings (Industrial Electronics Conference). 2013. pp. 2442-2446
@inproceedings{a703480e3ec24da2af70c9cab1992cd0,
title = "Multiple players tracking and identification using group detection and player number recognition in sports video",
abstract = "We are interested in the problem of automatically tracking and identifying players in sports video. While there are many automatic multi-target tracking methods, in sports video, it is difficult to track multiple players due to frequent occlusions, quick motion of players and camera, and camera position. We propose tracking method that associates tracklets of a same player using results of player number recognition. To deal with frequent occlusions, we detect human region by level set method and then estimates if it is occluded group region or unoccluded individual one. Moreover, we associate tracklets using the results of player number recognition at each frame by keypoints-based matching with templates from multiple viewpoints, so that final tracklets include occluded region.",
keywords = "Affin Warp, data association, level set method, multiple target tracking, SIFT",
author = "Taiki Yamamoto and Hirokatsu Kataoka and Masaki Hayashi and Yoshimitsu Aoki and Kyoko Oshima and Masamoto Tanabiki",
year = "2013",
doi = "10.1109/IECON.2013.6699514",
language = "English",
isbn = "9781479902248",
pages = "2442--2446",
booktitle = "IECON Proceedings (Industrial Electronics Conference)",

}

TY - GEN

T1 - Multiple players tracking and identification using group detection and player number recognition in sports video

AU - Yamamoto, Taiki

AU - Kataoka, Hirokatsu

AU - Hayashi, Masaki

AU - Aoki, Yoshimitsu

AU - Oshima, Kyoko

AU - Tanabiki, Masamoto

PY - 2013

Y1 - 2013

N2 - We are interested in the problem of automatically tracking and identifying players in sports video. While there are many automatic multi-target tracking methods, in sports video, it is difficult to track multiple players due to frequent occlusions, quick motion of players and camera, and camera position. We propose tracking method that associates tracklets of a same player using results of player number recognition. To deal with frequent occlusions, we detect human region by level set method and then estimates if it is occluded group region or unoccluded individual one. Moreover, we associate tracklets using the results of player number recognition at each frame by keypoints-based matching with templates from multiple viewpoints, so that final tracklets include occluded region.

AB - We are interested in the problem of automatically tracking and identifying players in sports video. While there are many automatic multi-target tracking methods, in sports video, it is difficult to track multiple players due to frequent occlusions, quick motion of players and camera, and camera position. We propose tracking method that associates tracklets of a same player using results of player number recognition. To deal with frequent occlusions, we detect human region by level set method and then estimates if it is occluded group region or unoccluded individual one. Moreover, we associate tracklets using the results of player number recognition at each frame by keypoints-based matching with templates from multiple viewpoints, so that final tracklets include occluded region.

KW - Affin Warp

KW - data association

KW - level set method

KW - multiple target tracking

KW - SIFT

UR - http://www.scopus.com/inward/record.url?scp=84893633394&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893633394&partnerID=8YFLogxK

U2 - 10.1109/IECON.2013.6699514

DO - 10.1109/IECON.2013.6699514

M3 - Conference contribution

SN - 9781479902248

SP - 2442

EP - 2446

BT - IECON Proceedings (Industrial Electronics Conference)

ER -