A general framework for 3D soccer ball estimation and tracking

Jinchang Ren; James Orwell; Graeme A. Jones; Ming Xu

doi:10.1109/ICIP.2004.1421458

A general framework for 3D soccer ball estimation and tracking

Jinchang Ren^*, James Orwell, Graeme A. Jones, Ming Xu

^*Corresponding author for this work

Kingston University

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

36 Citations (Scopus)

Abstract

A general framework for automatic 3D soccer ball estimation and tracking from multiple image sequences is proposed. Firstly, the ball trajectory is modelled as planar-curves in consecutive virtual vertical planes. These planes are then determined by two ball positions with accurately estimated height, namely critical points, which are extracted by curvature thresholding and nearest distance of 3D lines from single or multiple views respectively. Finally, unreliable or missing ball observations are recovered using geometric constraints and polynomial interpolation. Experiments on video sequences from different cameras, with over 5000 frames each, have demonstrated a comprehensive solution for accurate and robust 3D ball estimation and tracking, with over 90% ball estimations within 2.5 metres of manually derived ground truth.

Original language	English
Title of host publication	2004 IEEE International Conference on Image Processing, ICIP 2004
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1935-1938
Number of pages	4
ISBN (Print)	0780385543
DOIs	https://doi.org/10.1109/ICIP.2004.1421458
Publication status	Published - 2004
Externally published	Yes
Event	2004 International Conference on Image Processing, ICIP 2004 - , Singapore Duration: 18 Oct 2004 → 21 Oct 2004

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
Volume	3
ISSN (Print)	1522-4880

Conference

Conference	2004 International Conference on Image Processing, ICIP 2004
Country/Territory	Singapore
Period	18/10/04 → 21/10/04

Access to Document

10.1109/ICIP.2004.1421458

Cite this

Ren, J., Orwell, J., Jones, G. A., & Xu, M. (2004). A general framework for 3D soccer ball estimation and tracking. In 2004 IEEE International Conference on Image Processing, ICIP 2004 (pp. 1935-1938). (Proceedings - International Conference on Image Processing, ICIP; Vol. 3). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIP.2004.1421458

@inproceedings{f4d041f9856f447483324d47e387206c,

title = "A general framework for 3D soccer ball estimation and tracking",

abstract = "A general framework for automatic 3D soccer ball estimation and tracking from multiple image sequences is proposed. Firstly, the ball trajectory is modelled as planar-curves in consecutive virtual vertical planes. These planes are then determined by two ball positions with accurately estimated height, namely critical points, which are extracted by curvature thresholding and nearest distance of 3D lines from single or multiple views respectively. Finally, unreliable or missing ball observations are recovered using geometric constraints and polynomial interpolation. Experiments on video sequences from different cameras, with over 5000 frames each, have demonstrated a comprehensive solution for accurate and robust 3D ball estimation and tracking, with over 90% ball estimations within 2.5 metres of manually derived ground truth.",

author = "Jinchang Ren and James Orwell and Jones, {Graeme A.} and Ming Xu",

year = "2004",

doi = "10.1109/ICIP.2004.1421458",

language = "English",

isbn = "0780385543",

series = "Proceedings - International Conference on Image Processing, ICIP",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1935--1938",

booktitle = "2004 IEEE International Conference on Image Processing, ICIP 2004",

note = "2004 International Conference on Image Processing, ICIP 2004 ; Conference date: 18-10-2004 Through 21-10-2004",

}

Ren, J, Orwell, J, Jones, GA & Xu, M 2004, A general framework for 3D soccer ball estimation and tracking. in 2004 IEEE International Conference on Image Processing, ICIP 2004. Proceedings - International Conference on Image Processing, ICIP, vol. 3, Institute of Electrical and Electronics Engineers Inc., pp. 1935-1938, 2004 International Conference on Image Processing, ICIP 2004, Singapore, 18/10/04. https://doi.org/10.1109/ICIP.2004.1421458

A general framework for 3D soccer ball estimation and tracking. / Ren, Jinchang; Orwell, James; Jones, Graeme A. et al.
2004 IEEE International Conference on Image Processing, ICIP 2004. Institute of Electrical and Electronics Engineers Inc., 2004. p. 1935-1938 (Proceedings - International Conference on Image Processing, ICIP; Vol. 3).

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

TY - GEN

T1 - A general framework for 3D soccer ball estimation and tracking

AU - Ren, Jinchang

AU - Orwell, James

AU - Jones, Graeme A.

AU - Xu, Ming

PY - 2004

Y1 - 2004

N2 - A general framework for automatic 3D soccer ball estimation and tracking from multiple image sequences is proposed. Firstly, the ball trajectory is modelled as planar-curves in consecutive virtual vertical planes. These planes are then determined by two ball positions with accurately estimated height, namely critical points, which are extracted by curvature thresholding and nearest distance of 3D lines from single or multiple views respectively. Finally, unreliable or missing ball observations are recovered using geometric constraints and polynomial interpolation. Experiments on video sequences from different cameras, with over 5000 frames each, have demonstrated a comprehensive solution for accurate and robust 3D ball estimation and tracking, with over 90% ball estimations within 2.5 metres of manually derived ground truth.

AB - A general framework for automatic 3D soccer ball estimation and tracking from multiple image sequences is proposed. Firstly, the ball trajectory is modelled as planar-curves in consecutive virtual vertical planes. These planes are then determined by two ball positions with accurately estimated height, namely critical points, which are extracted by curvature thresholding and nearest distance of 3D lines from single or multiple views respectively. Finally, unreliable or missing ball observations are recovered using geometric constraints and polynomial interpolation. Experiments on video sequences from different cameras, with over 5000 frames each, have demonstrated a comprehensive solution for accurate and robust 3D ball estimation and tracking, with over 90% ball estimations within 2.5 metres of manually derived ground truth.

UR - http://www.scopus.com/inward/record.url?scp=20444439513&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2004.1421458

DO - 10.1109/ICIP.2004.1421458

M3 - Conference Proceeding

AN - SCOPUS:20444439513

SN - 0780385543

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 1935

EP - 1938

BT - 2004 IEEE International Conference on Image Processing, ICIP 2004

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2004 International Conference on Image Processing, ICIP 2004

Y2 - 18 October 2004 through 21 October 2004

ER -

A general framework for 3D soccer ball estimation and tracking

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this