Real-time ball detection and following based on a hybrid vision system with application to robot soccer field

Taher Abbas Shangari, Faraz Shamshirdar, Bita Azari, Mohammadhossein Heydari, Sourosh Sadeghnejad, Jacky Baltes

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

Abstract

Circle detection is one of the most important problems in image processing since circular objects, such as balls, are observed frequently in many natural and artificial environments and problems such as light variations, occlusions, shadows, circle-shaped objects, and real-time processing have to be managed. The previous methods are either edge-based which generally suffer from processing burden or color-based and cannot deal with color variations suitably. This paper presents a real-time ball detection framework that uses both color information and shape information together to detect and track a ball robustly. The results demonstrate superiority of the proposed method over the previous. After classifying the color space, image segmentation, building regions, and extracting objects, to reduce the computation, it is focused on finding the green horizon to eliminate a part of the image, which is beyond the field border. Afterward some filters based on circle-fitting methods, image moments are applied to detect and track the ball. The results show that these filters are real-time, robust against occlusion and are able to track the ball even for distances more than six meters.

Original languageEnglish
Title of host publicationRobot Intelligence Technology and Applications 4 - Results from the 4th International Conference on Robot Intelligence Technology and Applications
EditorsFakhri Karray, Jong-Hwan Kim, Hyun Myung, Jun Jo, Peter Sincak
PublisherSpringer Verlag
Pages521-527
Number of pages7
ISBN (Print)9783319312910
DOIs
Publication statusPublished - 2017 Jan 1
Event4th International Conference on Robot Intelligence Technology and Applications, RiTA 2015 - Bucheon, Korea, Republic of
Duration: 2015 Dec 142015 Dec 16

Publication series

NameAdvances in Intelligent Systems and Computing
Volume447
ISSN (Print)2194-5357

Other

Other4th International Conference on Robot Intelligence Technology and Applications, RiTA 2015
CountryKorea, Republic of
CityBucheon
Period15/12/1415/12/16

Fingerprint

Robots
Color
Processing
Image segmentation
Image processing

Keywords

  • Circle detection
  • Circle-fitting method
  • Color and shape information
  • Real-time ball detection

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science(all)

Cite this

Shangari, T. A., Shamshirdar, F., Azari, B., Heydari, M., Sadeghnejad, S., & Baltes, J. (2017). Real-time ball detection and following based on a hybrid vision system with application to robot soccer field. In F. Karray, J-H. Kim, H. Myung, J. Jo, & P. Sincak (Eds.), Robot Intelligence Technology and Applications 4 - Results from the 4th International Conference on Robot Intelligence Technology and Applications (pp. 521-527). (Advances in Intelligent Systems and Computing; Vol. 447). Springer Verlag. https://doi.org/10.1007/978-3-319-31293-4_42

Real-time ball detection and following based on a hybrid vision system with application to robot soccer field. / Shangari, Taher Abbas; Shamshirdar, Faraz; Azari, Bita; Heydari, Mohammadhossein; Sadeghnejad, Sourosh; Baltes, Jacky.

Robot Intelligence Technology and Applications 4 - Results from the 4th International Conference on Robot Intelligence Technology and Applications. ed. / Fakhri Karray; Jong-Hwan Kim; Hyun Myung; Jun Jo; Peter Sincak. Springer Verlag, 2017. p. 521-527 (Advances in Intelligent Systems and Computing; Vol. 447).

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

Shangari, TA, Shamshirdar, F, Azari, B, Heydari, M, Sadeghnejad, S & Baltes, J 2017, Real-time ball detection and following based on a hybrid vision system with application to robot soccer field. in F Karray, J-H Kim, H Myung, J Jo & P Sincak (eds), Robot Intelligence Technology and Applications 4 - Results from the 4th International Conference on Robot Intelligence Technology and Applications. Advances in Intelligent Systems and Computing, vol. 447, Springer Verlag, pp. 521-527, 4th International Conference on Robot Intelligence Technology and Applications, RiTA 2015, Bucheon, Korea, Republic of, 15/12/14. https://doi.org/10.1007/978-3-319-31293-4_42
Shangari TA, Shamshirdar F, Azari B, Heydari M, Sadeghnejad S, Baltes J. Real-time ball detection and following based on a hybrid vision system with application to robot soccer field. In Karray F, Kim J-H, Myung H, Jo J, Sincak P, editors, Robot Intelligence Technology and Applications 4 - Results from the 4th International Conference on Robot Intelligence Technology and Applications. Springer Verlag. 2017. p. 521-527. (Advances in Intelligent Systems and Computing). https://doi.org/10.1007/978-3-319-31293-4_42
Shangari, Taher Abbas ; Shamshirdar, Faraz ; Azari, Bita ; Heydari, Mohammadhossein ; Sadeghnejad, Sourosh ; Baltes, Jacky. / Real-time ball detection and following based on a hybrid vision system with application to robot soccer field. Robot Intelligence Technology and Applications 4 - Results from the 4th International Conference on Robot Intelligence Technology and Applications. editor / Fakhri Karray ; Jong-Hwan Kim ; Hyun Myung ; Jun Jo ; Peter Sincak. Springer Verlag, 2017. pp. 521-527 (Advances in Intelligent Systems and Computing).
@inproceedings{b4038ad510444c70b6d015d6fc736e80,
title = "Real-time ball detection and following based on a hybrid vision system with application to robot soccer field",
abstract = "Circle detection is one of the most important problems in image processing since circular objects, such as balls, are observed frequently in many natural and artificial environments and problems such as light variations, occlusions, shadows, circle-shaped objects, and real-time processing have to be managed. The previous methods are either edge-based which generally suffer from processing burden or color-based and cannot deal with color variations suitably. This paper presents a real-time ball detection framework that uses both color information and shape information together to detect and track a ball robustly. The results demonstrate superiority of the proposed method over the previous. After classifying the color space, image segmentation, building regions, and extracting objects, to reduce the computation, it is focused on finding the green horizon to eliminate a part of the image, which is beyond the field border. Afterward some filters based on circle-fitting methods, image moments are applied to detect and track the ball. The results show that these filters are real-time, robust against occlusion and are able to track the ball even for distances more than six meters.",
keywords = "Circle detection, Circle-fitting method, Color and shape information, Real-time ball detection",
author = "Shangari, {Taher Abbas} and Faraz Shamshirdar and Bita Azari and Mohammadhossein Heydari and Sourosh Sadeghnejad and Jacky Baltes",
year = "2017",
month = "1",
day = "1",
doi = "10.1007/978-3-319-31293-4_42",
language = "English",
isbn = "9783319312910",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer Verlag",
pages = "521--527",
editor = "Fakhri Karray and Jong-Hwan Kim and Hyun Myung and Jun Jo and Peter Sincak",
booktitle = "Robot Intelligence Technology and Applications 4 - Results from the 4th International Conference on Robot Intelligence Technology and Applications",

}

TY - GEN

T1 - Real-time ball detection and following based on a hybrid vision system with application to robot soccer field

AU - Shangari, Taher Abbas

AU - Shamshirdar, Faraz

AU - Azari, Bita

AU - Heydari, Mohammadhossein

AU - Sadeghnejad, Sourosh

AU - Baltes, Jacky

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Circle detection is one of the most important problems in image processing since circular objects, such as balls, are observed frequently in many natural and artificial environments and problems such as light variations, occlusions, shadows, circle-shaped objects, and real-time processing have to be managed. The previous methods are either edge-based which generally suffer from processing burden or color-based and cannot deal with color variations suitably. This paper presents a real-time ball detection framework that uses both color information and shape information together to detect and track a ball robustly. The results demonstrate superiority of the proposed method over the previous. After classifying the color space, image segmentation, building regions, and extracting objects, to reduce the computation, it is focused on finding the green horizon to eliminate a part of the image, which is beyond the field border. Afterward some filters based on circle-fitting methods, image moments are applied to detect and track the ball. The results show that these filters are real-time, robust against occlusion and are able to track the ball even for distances more than six meters.

AB - Circle detection is one of the most important problems in image processing since circular objects, such as balls, are observed frequently in many natural and artificial environments and problems such as light variations, occlusions, shadows, circle-shaped objects, and real-time processing have to be managed. The previous methods are either edge-based which generally suffer from processing burden or color-based and cannot deal with color variations suitably. This paper presents a real-time ball detection framework that uses both color information and shape information together to detect and track a ball robustly. The results demonstrate superiority of the proposed method over the previous. After classifying the color space, image segmentation, building regions, and extracting objects, to reduce the computation, it is focused on finding the green horizon to eliminate a part of the image, which is beyond the field border. Afterward some filters based on circle-fitting methods, image moments are applied to detect and track the ball. The results show that these filters are real-time, robust against occlusion and are able to track the ball even for distances more than six meters.

KW - Circle detection

KW - Circle-fitting method

KW - Color and shape information

KW - Real-time ball detection

UR - http://www.scopus.com/inward/record.url?scp=84978538772&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84978538772&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-31293-4_42

DO - 10.1007/978-3-319-31293-4_42

M3 - Conference contribution

AN - SCOPUS:84978538772

SN - 9783319312910

T3 - Advances in Intelligent Systems and Computing

SP - 521

EP - 527

BT - Robot Intelligence Technology and Applications 4 - Results from the 4th International Conference on Robot Intelligence Technology and Applications

A2 - Karray, Fakhri

A2 - Kim, Jong-Hwan

A2 - Myung, Hyun

A2 - Jo, Jun

A2 - Sincak, Peter

PB - Springer Verlag

ER -