Take your eyes off the ball

Improving ball-tracking by focusing on team play

Xinchao Wang, Vitaly Ablavsky, Horesh Ben Shitrit, Pascal Fua

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

Accurate video-based ball tracking in team sports is important for automated game analysis, and has proven very difficult because the ball is often occluded by the players. In this paper, we propose a novel approach to addressing this issue by formulating the tracking in terms of deciding which player, if any, is in possession of the ball at any given time. This is very different from standard approaches that first attempt to track the ball and only then to assign possession. We will show that our method substantially increases performance when applied to long basketball and soccer sequences.

Original languageEnglish (US)
Pages (from-to)102-115
Number of pages14
JournalComputer Vision and Image Understanding
Volume119
DOIs
StatePublished - Feb 1 2014
Externally publishedYes

Fingerprint

Sports

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition

Cite this

Wang, Xinchao ; Ablavsky, Vitaly ; Shitrit, Horesh Ben ; Fua, Pascal. / Take your eyes off the ball : Improving ball-tracking by focusing on team play. In: Computer Vision and Image Understanding. 2014 ; Vol. 119. pp. 102-115.
@article{5ed87057c8b24b0c80bb5e3408f54ba3,
title = "Take your eyes off the ball: Improving ball-tracking by focusing on team play",
abstract = "Accurate video-based ball tracking in team sports is important for automated game analysis, and has proven very difficult because the ball is often occluded by the players. In this paper, we propose a novel approach to addressing this issue by formulating the tracking in terms of deciding which player, if any, is in possession of the ball at any given time. This is very different from standard approaches that first attempt to track the ball and only then to assign possession. We will show that our method substantially increases performance when applied to long basketball and soccer sequences.",
author = "Xinchao Wang and Vitaly Ablavsky and Shitrit, {Horesh Ben} and Pascal Fua",
year = "2014",
month = "2",
day = "1",
doi = "https://doi.org/10.1016/j.cviu.2013.11.010",
language = "English (US)",
volume = "119",
pages = "102--115",
journal = "Computer Vision and Image Understanding",
issn = "1077-3142",
publisher = "Academic Press Inc.",

}

Take your eyes off the ball : Improving ball-tracking by focusing on team play. / Wang, Xinchao; Ablavsky, Vitaly; Shitrit, Horesh Ben; Fua, Pascal.

In: Computer Vision and Image Understanding, Vol. 119, 01.02.2014, p. 102-115.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Take your eyes off the ball

T2 - Improving ball-tracking by focusing on team play

AU - Wang, Xinchao

AU - Ablavsky, Vitaly

AU - Shitrit, Horesh Ben

AU - Fua, Pascal

PY - 2014/2/1

Y1 - 2014/2/1

N2 - Accurate video-based ball tracking in team sports is important for automated game analysis, and has proven very difficult because the ball is often occluded by the players. In this paper, we propose a novel approach to addressing this issue by formulating the tracking in terms of deciding which player, if any, is in possession of the ball at any given time. This is very different from standard approaches that first attempt to track the ball and only then to assign possession. We will show that our method substantially increases performance when applied to long basketball and soccer sequences.

AB - Accurate video-based ball tracking in team sports is important for automated game analysis, and has proven very difficult because the ball is often occluded by the players. In this paper, we propose a novel approach to addressing this issue by formulating the tracking in terms of deciding which player, if any, is in possession of the ball at any given time. This is very different from standard approaches that first attempt to track the ball and only then to assign possession. We will show that our method substantially increases performance when applied to long basketball and soccer sequences.

UR - http://www.scopus.com/inward/record.url?scp=84891796090&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84891796090&partnerID=8YFLogxK

U2 - https://doi.org/10.1016/j.cviu.2013.11.010

DO - https://doi.org/10.1016/j.cviu.2013.11.010

M3 - Article

VL - 119

SP - 102

EP - 115

JO - Computer Vision and Image Understanding

JF - Computer Vision and Image Understanding

SN - 1077-3142

ER -