Accurate ball tracking in volleyball actions to support referees

• Autorzy: Kurowski P. , Szelag K. , Zaluski W. , Sitnik R.

Identyfikatory

DOI

10.1016/j.opelre.2018.10.004

• Języki publikacji: EN

Abstrakty

EN

This paper proposes a method for offline accurate ball tracking for short volleyball actions in sport halls. Our aim is to detect block touches on the ball and to determinate accurate trajectory and impact positions of the ball to support referees. The proposed method is divided into two stages, namely training and ball tracking, and is based on background subtraction. Application of the Gaussian mixture model has been used to estimate a background, and a high-speed camera with a capture rate of 180 frames per second and a resolution of 1920 × 1080 are used for motion capture. In sport halls significant differences in light intensity occur between each sequence frame. To minimize the influence of these light changes, an additional model is created and template matching is used for accurate determination of ball positions when the ball contour in the foreground image is distorted. We show that this algorithm is more accurate than other methods used in similar systems. Our light intensity change model eliminates almost all pixels added to images of moving objects owing to sudden changes in intensity. The average accuracy achieved in the validation process is of 0.57 pixel. Our algorithm accurately determined 99.8% of all ball positions from 2000 test frames, with 25.4 ms being the average time for a single frame analysis. The algorithm presented in this paper is the first stage of referee support using a system of many cameras and 3D trajectories.

Słowa kluczowe

EN

object recognition; object tracking; object trajectory; light intensity changes; volleyball

• Wydawca: Stowarzyszenie Elektryków Polskich ; Polska Akademia Nauk ; Wojskowa Akademia Techniczna im. Jarosława Dąbrowskiego
• Czasopismo: Opto-Electronics Review
• Rocznik: 2018
• Tom: Vol. 26, No. 4
• Strony: 296--306
• Opis fizyczny: Bibliogr. 27 poz., rys., wykr.

Twórcy

autor

Kurowski P.

• Warsaw University of Technology, Faculty of Mechatronics, 8 Św. Andrzeja Boboli St. 02-525, Warsaw, Poland

autor

Szelag K.

• Warsaw University of Technology, Faculty of Mechatronics, 8 Św. Andrzeja Boboli St. 02-525, Warsaw, Poland

autor

Zaluski W.

• Warsaw University of Technology, Faculty of Mechatronics, 8 Św. Andrzeja Boboli St. 02-525, Warsaw, Poland

autor

Sitnik R.

• Warsaw University of Technology, Faculty of Mechatronics, 8 Św. Andrzeja Boboli St. 02-525, Warsaw, Poland

Bibliografia

• [1] X. Tong, T. Wang, W. Li, Y. Zhang, A novel algorithm for effective ball tracking, Intern. J. Pattern Recognit. Artif. Intell. 24 (03) (2010) 359–379.
• [2] X. Yu, H.W. Leong, C. Xu, Q. Tian, Trajectory-based ball detection and tracking in Broadcast Soccer Video, IEEE Ttans. Multimedia 8 (6) (2006) 1164–1178.
• [3] X. Yu, C. Xu, Q. Tian, K.W. Wan, A novel ball detection framework for real soccer video, IEEE Int. Con. Multimedia. 2 (2003) 265–268.
• [4] R.E. Kalman, A new approach to linear filtering and prediction problems, J. Basic Eng.-Ttans. Asme 80 (1960) 35–45.
• [5] Y. Seo, S. Choi, H. Kim, K.S. Hong, Where are the ball and players? Soccer game analysis with color-based tracking and image mosaic, Lect. Notes Comput. Sci. 1311 (1997) 196–203.
• [6] Y. Ji, J. Zhang, Z. Shi, M.H. Liu, J. Ren, Research on real time tracking of table tennis ball based on machine learning with low-speed camera, Syst. Sci. Control. Eng. 6 (1) (2018) 71–79, http://dx.doi.org/10.1080/21642583.2018.1450167.
• [7] D. Speck, P. Barros, C. Weber, S. Wermter, Ball localization for robocup soccer using convolutional neural networks, Lect. Notes Artif. Int. 9776 (2017) 19–30, http://dx.doi.org/10.1007/978-3-319-68792-6 2.
• [8] D. Liang, Y. Liu, Q. Huang, W. Gao, A scheme for ball detection and tracking in broadcast soccer video”, Lect. Notes Comput. Sci. 3767 (2005) 864–875.
• [9] T. D’Orazio, N. Ancona, G. Cicirelli, M. Nitti, A ball detection algorithm for real soccer image sequences, Proc. IAPR Int. Conf. Pattern Recogn. 1 (2002) 210–213.
• [10] H. Chen, W. Tsai, S. Lee, J. Yu, Ball tracking and 3D trajectory approximation with applications to tactics analysis from single- camera volleyball sequences, Multimed. Tools Appl. 60 (3) (2012) 641–667.
• [11] H. Chen, M. Tien, Y. Chen, W. Tsai, S. Lee, Physics-based ball tracking and 3D trajectory reconstruction with applications to shooting location estimation in basketball video, J. Vis. Commun. Image R 20 (3) (2009) 204–216.
• [12] H. Chen, H. Chen, M. Hsiao, W. Tsai, S. Lee, A trajectory-based ball tracking framework with visual enrichment for broadcast baseball videos, J. Inf. Sci. Eng. 24 (1) (2008) 143–157.
• [13] B. Chakraborty, S. Meher, A real time trajectory based ball detection and tracking framework for basketball video, J. Opt.-UK 42 (2) (2013) 156–170.
• [14] M. Labayen, I. Olaizola, N. Aginako, J. Florez, Accurate ball trajectory tracking and 3D visualization for computer-assisted sports broadcast, Multimed. Tools Appl. 73 (3) (2014) 1819–1842.
• [15] B. Sugandi, K. Hyoungseop, J.K. Tan, S. Ishikawa, Tracking of moving objects by using a Resolution image, in: Second International Conference on Innovative Computing, Information and Control, 2007, 408.
• [16] Y. Ohno, J. Miura, Y. Shirai, Tracking players and estimation of the 3D position of a ball in soccer games, Proc. IAPR Int. Conf. Pattern Recogn. 1 (2000) 145–148.
• [17] G. Gomez, P.H. Lopez, D. Link, B. Eskofier, Tracking of ball and players in beach volleyball videos, PLoS One 9 (11) (2014).
• [18] Z. Zivkovic, F. van der Heijden, Efficient adaptive density estimation per image pixel for the task of background subtraction, Pattern Recogn. Lett. 27 (7) (2006) 773–780.
• [19] B.D. Ekinci, M. Gokmen, A ball tracking system for offline tennis videos, in: 1st WSEAS International Conference on Visualization, Imaging and Simulation, 2008, pp. 45–48.
• [20] Y. Ariki, T. Takiguchi, K. Yano, Digital camera work for soccer video production with event recognition and accurate ball tracking by switching search method, in: 2008 IEEE Int Con Multi, 2008, pp. 889–892.
• [21] X. Cheng, X. Zhuang, Y. Wang, M. Honda, T. Ikenaga, Particle filter with ball size adaptive tracking window and ball feature likelihood model for ball’s 3D position tracking in volleyball analysis, Lect. Notes Comput. SC –PCM 9314 (2015) 203–211.
• [22] P.R. Kamble, A.G. Keskar, K.M. Bhurchandi, Ball tracking in sports: a survey, Artif. Intell. Rev. (2017) 1–51, http://dx.doi.org/10.1007/s10462-017-9582-2.
• [23] X. Wang, V. Ablavsky, H. Shitrit, P. Fua, Take your eyes off the ball: improving ball tracking by focusing on team play, Comput. Vis. Image Underst. 119 (2014) 102–115.
• [24] N.M. Oliver, B. Rosario, A.P. Pentland, A Bayesian computer vision system for modelling human interactions, IEEE Trans. Pattern Anal. Mach. Intell. 22 (8) (2000) 831–843.
• [25] A. Maksai, X. Wang, P. Fua, What players do with the ball: a physically constrained interaction modeling, Proc CVPR IEEE (2016) 972–981.
• [26] M. Hearst, S. Dumais, E. Osuna, et al., Support vector machines, IEEE Intell. Syst. Appl. 13 (4) (1998) 18–28.
• [27] “FIVB Official Volleyball Rules 2017-2020” https://www.fivb.org/EN/Refereeing-Rules/documents/FIVB-Volleyball Rules 2017-2020-EN-v06.pdf. (Accessed 06 June 2018).

Uwagi

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2018).