Real-time modeling of 3-D soccer ball trajectories from multiple fixed cameras

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

Research output: Contribution to journalArticle

36 Citations (Scopus)

Abstract

In this paper, model-based approaches for real-time 3-D soccer ball tracking are proposed, using image sequences from multiple fixed cameras as input. The main challenges include filtering false alarms, tracking through missing observations, and estimating 3-D positions from single or multiple cameras. The key innovations are: 1. incorporating motion cues and temporal hysteresis thresholding in ball detection; 2. modeling each ball trajectory as curve segments in successive virtual vertical planes so that the 3-D position of the ball can be determined from a single camera view; and 3. introducing four motion phases (rolling, flying, in possession, and out of play) and employing phase-specific models to estimate ball trajectories which enables high-level semantics applied in low-level tracking. In addition, unreliable or missing ball observations are recovered using spatio-temporal constraints and temporal filtering. The system accuracy and robustness are evaluated by comparing the estimated ball positions and phases with manual ground-truth data of real soccer sequences.
LanguageEnglish
Pages350-362
Number of pages13
JournalIEEE Transactions on Circuits and Systems for Video Technology
Volume18
Issue number3
DOIs
Publication statusPublished - Mar 2008

Fingerprint

Cameras
Trajectories
Hysteresis
Innovation
Semantics

Keywords

  • ball trajectory
  • modelling
  • estimation theory
  • image motion analysis

Cite this

@article{ca27a2a720fe4dbea7f80adccadaab01,
title = "Real-time modeling of 3-D soccer ball trajectories from multiple fixed cameras",
abstract = "In this paper, model-based approaches for real-time 3-D soccer ball tracking are proposed, using image sequences from multiple fixed cameras as input. The main challenges include filtering false alarms, tracking through missing observations, and estimating 3-D positions from single or multiple cameras. The key innovations are: 1. incorporating motion cues and temporal hysteresis thresholding in ball detection; 2. modeling each ball trajectory as curve segments in successive virtual vertical planes so that the 3-D position of the ball can be determined from a single camera view; and 3. introducing four motion phases (rolling, flying, in possession, and out of play) and employing phase-specific models to estimate ball trajectories which enables high-level semantics applied in low-level tracking. In addition, unreliable or missing ball observations are recovered using spatio-temporal constraints and temporal filtering. The system accuracy and robustness are evaluated by comparing the estimated ball positions and phases with manual ground-truth data of real soccer sequences.",
keywords = "ball trajectory, modelling, estimation theory, image motion analysis",
author = "Jinchang Ren and M. Xu and J. Orwell and G. Jones",
year = "2008",
month = "3",
doi = "10.1109/TCSVT.2008.918276",
language = "English",
volume = "18",
pages = "350--362",
journal = "IEEE Transactions on Circuits and Systems for Video Technology",
issn = "1051-8215",
number = "3",

}

Real-time modeling of 3-D soccer ball trajectories from multiple fixed cameras. / Ren, Jinchang; Xu, M.; Orwell, J.; Jones, G.

In: IEEE Transactions on Circuits and Systems for Video Technology, Vol. 18, No. 3, 03.2008, p. 350-362.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Real-time modeling of 3-D soccer ball trajectories from multiple fixed cameras

AU - Ren, Jinchang

AU - Xu, M.

AU - Orwell, J.

AU - Jones, G.

PY - 2008/3

Y1 - 2008/3

N2 - In this paper, model-based approaches for real-time 3-D soccer ball tracking are proposed, using image sequences from multiple fixed cameras as input. The main challenges include filtering false alarms, tracking through missing observations, and estimating 3-D positions from single or multiple cameras. The key innovations are: 1. incorporating motion cues and temporal hysteresis thresholding in ball detection; 2. modeling each ball trajectory as curve segments in successive virtual vertical planes so that the 3-D position of the ball can be determined from a single camera view; and 3. introducing four motion phases (rolling, flying, in possession, and out of play) and employing phase-specific models to estimate ball trajectories which enables high-level semantics applied in low-level tracking. In addition, unreliable or missing ball observations are recovered using spatio-temporal constraints and temporal filtering. The system accuracy and robustness are evaluated by comparing the estimated ball positions and phases with manual ground-truth data of real soccer sequences.

AB - In this paper, model-based approaches for real-time 3-D soccer ball tracking are proposed, using image sequences from multiple fixed cameras as input. The main challenges include filtering false alarms, tracking through missing observations, and estimating 3-D positions from single or multiple cameras. The key innovations are: 1. incorporating motion cues and temporal hysteresis thresholding in ball detection; 2. modeling each ball trajectory as curve segments in successive virtual vertical planes so that the 3-D position of the ball can be determined from a single camera view; and 3. introducing four motion phases (rolling, flying, in possession, and out of play) and employing phase-specific models to estimate ball trajectories which enables high-level semantics applied in low-level tracking. In addition, unreliable or missing ball observations are recovered using spatio-temporal constraints and temporal filtering. The system accuracy and robustness are evaluated by comparing the estimated ball positions and phases with manual ground-truth data of real soccer sequences.

KW - ball trajectory

KW - modelling

KW - estimation theory

KW - image motion analysis

UR - http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=76

U2 - 10.1109/TCSVT.2008.918276

DO - 10.1109/TCSVT.2008.918276

M3 - Article

VL - 18

SP - 350

EP - 362

JO - IEEE Transactions on Circuits and Systems for Video Technology

T2 - IEEE Transactions on Circuits and Systems for Video Technology

JF - IEEE Transactions on Circuits and Systems for Video Technology

SN - 1051-8215

IS - 3

ER -