Tracking the soccer ball using multiple fixed cameras

Jinchang Ren, J. Orwell, G. Jones, M. Xu

Research output: Contribution to journalArticle

47 Citations (Scopus)

Abstract

This paper demonstrates innovative techniques for estimating the trajectory of a soccer ball from multiple fixed cameras. Since the ball is nearly always moving and frequently occluded, its size and shape appearance varies over time and between cameras. Knowledge about the soccer domain is utilized and expressed in terms of field, object and motion models to distinguish the ball from other movements in the tracking and matching processes. Using ground plane velocity, longevity, normalized size and color features, each of the tracks obtained from a Kalman filter is assigned with a likelihood measure that represents the ball. This measure is further refined by reasoning through occlusions and back-tracking in the track history. This can be demonstrated to improve the accuracy and continuity of the results. Finally, a simple 3D trajectory model is presented, and the estimated 3D ball positions are fed back to constrain the 2D processing for more efficient and robust detection and tracking. Experimental results with quantitative evaluations from several long sequences are reported.
LanguageEnglish
Pages633-642
Number of pages10
JournalComputer Vision and Image Understanding
Volume113
Issue number5
DOIs
Publication statusPublished - 2009

Fingerprint

Cameras
Trajectories
Kalman filters
Color
Processing

Keywords

  • motion analysis
  • domain knowledge modeling
  • video signal processing
  • 3D vision
  • trajectory modeling
  • sports analysis

Cite this

Ren, Jinchang ; Orwell, J. ; Jones, G. ; Xu, M. / Tracking the soccer ball using multiple fixed cameras. In: Computer Vision and Image Understanding. 2009 ; Vol. 113, No. 5. pp. 633-642.
@article{330ccdbaa7134518b69301c09b6972c9,
title = "Tracking the soccer ball using multiple fixed cameras",
abstract = "This paper demonstrates innovative techniques for estimating the trajectory of a soccer ball from multiple fixed cameras. Since the ball is nearly always moving and frequently occluded, its size and shape appearance varies over time and between cameras. Knowledge about the soccer domain is utilized and expressed in terms of field, object and motion models to distinguish the ball from other movements in the tracking and matching processes. Using ground plane velocity, longevity, normalized size and color features, each of the tracks obtained from a Kalman filter is assigned with a likelihood measure that represents the ball. This measure is further refined by reasoning through occlusions and back-tracking in the track history. This can be demonstrated to improve the accuracy and continuity of the results. Finally, a simple 3D trajectory model is presented, and the estimated 3D ball positions are fed back to constrain the 2D processing for more efficient and robust detection and tracking. Experimental results with quantitative evaluations from several long sequences are reported.",
keywords = "motion analysis, domain knowledge modeling, video signal processing, 3D vision, trajectory modeling, sports analysis",
author = "Jinchang Ren and J. Orwell and G. Jones and M. Xu",
year = "2009",
doi = "10.1016/j.cviu.2008.01.007",
language = "English",
volume = "113",
pages = "633--642",
journal = "Computer Vision and Image Understanding",
issn = "1077-3142",
number = "5",

}

Tracking the soccer ball using multiple fixed cameras. / Ren, Jinchang; Orwell, J.; Jones, G.; Xu, M.

In: Computer Vision and Image Understanding, Vol. 113, No. 5, 2009, p. 633-642.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Tracking the soccer ball using multiple fixed cameras

AU - Ren, Jinchang

AU - Orwell, J.

AU - Jones, G.

AU - Xu, M.

PY - 2009

Y1 - 2009

N2 - This paper demonstrates innovative techniques for estimating the trajectory of a soccer ball from multiple fixed cameras. Since the ball is nearly always moving and frequently occluded, its size and shape appearance varies over time and between cameras. Knowledge about the soccer domain is utilized and expressed in terms of field, object and motion models to distinguish the ball from other movements in the tracking and matching processes. Using ground plane velocity, longevity, normalized size and color features, each of the tracks obtained from a Kalman filter is assigned with a likelihood measure that represents the ball. This measure is further refined by reasoning through occlusions and back-tracking in the track history. This can be demonstrated to improve the accuracy and continuity of the results. Finally, a simple 3D trajectory model is presented, and the estimated 3D ball positions are fed back to constrain the 2D processing for more efficient and robust detection and tracking. Experimental results with quantitative evaluations from several long sequences are reported.

AB - This paper demonstrates innovative techniques for estimating the trajectory of a soccer ball from multiple fixed cameras. Since the ball is nearly always moving and frequently occluded, its size and shape appearance varies over time and between cameras. Knowledge about the soccer domain is utilized and expressed in terms of field, object and motion models to distinguish the ball from other movements in the tracking and matching processes. Using ground plane velocity, longevity, normalized size and color features, each of the tracks obtained from a Kalman filter is assigned with a likelihood measure that represents the ball. This measure is further refined by reasoning through occlusions and back-tracking in the track history. This can be demonstrated to improve the accuracy and continuity of the results. Finally, a simple 3D trajectory model is presented, and the estimated 3D ball positions are fed back to constrain the 2D processing for more efficient and robust detection and tracking. Experimental results with quantitative evaluations from several long sequences are reported.

KW - motion analysis

KW - domain knowledge modeling

KW - video signal processing

KW - 3D vision

KW - trajectory modeling

KW - sports analysis

UR - http://www.journals.elsevier.com/computer-vision-and-image-understanding

U2 - 10.1016/j.cviu.2008.01.007

DO - 10.1016/j.cviu.2008.01.007

M3 - Article

VL - 113

SP - 633

EP - 642

JO - Computer Vision and Image Understanding

T2 - Computer Vision and Image Understanding

JF - Computer Vision and Image Understanding

SN - 1077-3142

IS - 5

ER -