Skip to main content
SpringerLink
Log in

Real-time segmentation methods for monocular soccer videos

  • Applied Problems
  • Published:
Pattern Recognition and Image Analysis Aims and scope Submit manuscript

Abstract

The analysis of video records of soccer games is a topic of extensive and challenging research in image sequence processing, particularly that of player and field tracking. In this paper, we propose a new approach for detecting players and field lines in monocular TV video data that involves determining the convex field area and grass colors. This is carried out by considering contextual knowledge, together with a new method for color segmentation that selects polyhedrons in a frame-wise manner within the RGB cube. In summary, for every input image, a binary mask of the field area and a background mask are determined. Both mask creation algorithms achieve per pixel F1 scores of about 98% within our representative test set and are real-time capable. Applications like line detection and player tracking are presented.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. A. Bigontina, M. Hermann, M. Hoernig, and B. Radig, “Human body part classification in monocular soccer images,” in Proc. 9th Open German-Russian Workshop on Pattern Recognition and Image Understanding (Koblenz, 2014).

    Google Scholar 

  2. F. I. de Football Association et al., Laws of the Game (FIFA, 2013/14).

    Google Scholar 

  3. T. De Marco, M. Leo, and C. Distante, “Soccer ball detection with isophotoes curvature analysis,” in Image Analysis and Processing ICIAP-2013 (Springer, 2013), pp. 793–802.

    Chapter  Google Scholar 

  4. M. Dimopoulos and T. Winkler, “Image warmnessa new perceptual feature for images and videos,” in Proc. 22nd IEEE Eur. Signal Processing Conf. (EUSIPCO) (Lisbon, 2014), pp. 1662–1666.

    Google Scholar 

  5. A. Ekin, A. M. Tekalp, and R. Mehrotra, “Automatic soccer video analysis and summarization,” IEEE Trans. Image Processing 12 (7), 796–807 (2003).

    Article  Google Scholar 

  6. P. J. Figueroa, N. J. Leite, and R. M. Barros, “Background recovering in outdoor image sequences: an example of soccer players segmentation,” Image Vision Comput. 24 (4), 363–374 (2006).

    Article  Google Scholar 

  7. S. Gedikli, “Continual and robust estimation of camera parameters in broadcasted sports games,” PhD Thesis (Munchen Techn. Univ., 2009).

    Google Scholar 

  8. R. C. Gonzalez and R. E. Woods, Digital Image Processing (2002).

    Google Scholar 

  9. R. L. Graham, “An efficient algorithm for determining the convex hull of a finite planar set,” Inf. Processing Lett. 1 (94), 132–133 (1972).

    Article  MATH  Google Scholar 

  10. R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision (Cambridge Univ. Press, 2003).

    Google Scholar 

  11. M. Herrmann, M. Hoerng, and B. Radig, “Online multi-player tracking in monocular soccer videos,” in Proc. AASRI Conf. on Sports Engineering and Computer Science (SECS 2014) (London, 2014), vol. 8, pp. 30–37.

    Google Scholar 

  12. M. Hoernig, M. Herrmann, and B. Radig, “Multi temporal distance images for short detection in soccer games,” in Proc. 22nd Europ. Signal Processing Conf. EUSIPCO 2014 (Lisbon, Sept. 2014).

    Google Scholar 

  13. N. V. Hoyningen-Huene and M. Beetz, “Rao-black-wellized resampling particle filter for real-time player tracking in sports,” in Proc. VISAPP, INSTICC (Lisboa, Funchal, 2009), pp. 464–471.

    Google Scholar 

  14. R. E. Kalman, “A new approach to linear filtering and prediction problems,” J. Fluids Eng. 82 (1), 35–45 (1960).

    Google Scholar 

  15. D.-H. Lee, S.-G. Lee, and J.-H. Choi, “Region-based corner detection by radial projection,” J. Opt. Soc. Korea 15 (2), 152–154 (2011).

    Article  Google Scholar 

  16. W.-L. Lu, J.-A. Ting, J. J. Little, and K. P. Murphy, “Learning to track and identify players from broadcast sports videos,” Trans. Pattern. Anal. Mach. Intellig. 35 (7), 1704–1716 (2013).

    Article  Google Scholar 

  17. A. A. Mustafa, “Boundary signature matching for object recognition,” in Proc. 6th Vision Interface Annu. Conf. (Ottawa, 2001), pp. 72–79.

    Google Scholar 

  18. Y. Seo, S. Choi, H. Kim, and K.-S. Hing, “Where are the ball and players? Soccer game analysis with color-based tracking and image mosaic,” in Image Analysis and Processing (Springer, 1997), pp. 196–203.

    Chapter  Google Scholar 

  19. I. W. Sutherland and G. W. Hodgman, “Reentrant polygon clipping,” Commun. ACM 17 (1), 32–42 (1974).

    Article  MATH  Google Scholar 

  20. X.-F. Tong, H.-Q. Lu, and Q.-S. Liu, “An effective and fast soccer ball detection and tracking method,” in Proc. 17th Int. IEEE Conf. on Pattern Recognition ICPR 2004 (Cambridge, 2004), vol. 4, pp. 795–798.

    Google Scholar 

  21. O. Utsumi, K. Miura, I. Ide, S. Sakai, and H. Tanaka, “An object detection method for describing soccer games from video,” in Proc. IEEE Conf. on Multimedia and Expo ICME’02 (Lauzanne, 2002), vol. 1, pp. 45–48.

    Google Scholar 

  22. R. G. Von Gioi, J. Jakubowicz, J.-M. Morel, and G. Randall, “Lsd: a fast line segment detector with a false detection control,” IEEE Trans. Pattern Anal. Mach. Intellig. 32 (4), 722–732 (2010).

    Article  Google Scholar 

  23. X. Yu, Q. Tian, and K. W. Wan, “A novel ball detection framework for real soccer video,” in Proc. IEEE Int. Conf. Multimedia and Expo ICME’03 (2003), Vol. 2, p. II-265.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Image Understanding and Knowledge-Based Systems, Boltzmannstrasse 3, 85748, Garching, Germany

    M. Hoernig, M. Herrmann & B. Radig

Authors
  1. M. Hoernig
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. M. Herrmann
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. B. Radig
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to M. Hoernig.

Additional information

This paper uses the materials of the report submitted at the 11th International Conference “Pattern Recognition and Image Analysis: New Information Technologies,” Samara, Russia, September 23–28, 2013.

The article is published in the original.

Martin Hoernig studied Mathematics at the Leipzig University of Applied Sciences. He received his master’s degree in 2011. In the same year he worked as a scientist at the Max Planck Institute for Human Cognitive and Brain Sciences Leipzig. Today, he is a research assistant in the TU Munich Image Understanding and Knowledge-Based Systems Group headed by Bernd Radig. His primary areas of research are: image analysis and understanding, learning and decision making, as well as web technologies.

Michael Herrmann, born 1980, received his diploma degree in computer science from the Julius-Maxi- milians-Universität Würzburg in 2007. From 2007 to 2012 he was a software engineer for industrial computer vision systems in private industry. Additionally, he was a research assistant at the Hochschule Rosenheim from 2010 to 2012. Since 2012 he is part of the research group Image Understanding and Knowledge Based System at the Technische Universität München headed by Bernd Radig. His research interests include computer vision, machine learning, and especially the detection and tracking of objects in videos.

Bernd Radig received his diploma degree in Physics in 1972 from the University of Bonn and the doctor degree in Computer Science in 1978 from the University of Hamburg. There he got his venia legendi and finished his habilitation dissertation in 1982. He was Assistant and Associate Professor in Hamburg (1982–1986) and full professor, chair of Image Understanding and Knowledge Based Systems, Fakultät für Informatik, Technische Universität München (1986–2010). He is a member of the Emeriti of Excellence programme. He was chairman and founder of the Association of Bavarian Research Cooperations (1993–2007), a unique network of scientists, specialising in challenging disciplines in accordance with Bavarian enterprises. 1988 he founded the Bavarian Research Centre for Knowledge Based Systems (FORWISS), an institute common to the three universities TU München, Erlangen and Passau. He was general chairman of the annual symposium of the German Association for Pattern Recognition in 1981, 1991, 2001 as well as of the European Conference on Artificial Intelligence (ECAI), 1988. He is active as organizer and programme committee member of the German-Russian Workshop on Pattern Recognition. He holds the German Order of Merit (1992) and the award Pro Meritis Scientiae et Litterarum of the State of Bavaria for outstanding contributions to science and art (2002). His current research activities are in real-time image sequence understanding for applications in robotics, sports or driver assistance systems.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hoernig, M., Herrmann, M. & Radig, B. Real-time segmentation methods for monocular soccer videos. Pattern Recognit. Image Anal. 25, 327–337 (2015). https://doi.org/10.1134/S105466181502011X

Download citation

  • Received:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S105466181502011X

Keywords

Search

Navigation