Automatic Player Detection and Labeling in Broadcast Soccer Video Using Genetic Algorithm

Document Type : Research Paper


1 Computer Engineering, Islamic Azad Mobarake Branch, Mobarakeh, Isfahan, Iran.

2 Faculty of Electrical and Computer Engineering, Semnan University, Semnan, Iran.

3 Faculty of Human Sciences, Semnan University, Semnan, Iran.


Due to the increasing amount of video data, a lot of research has been done in the field of retrieving and categorizing this type of data. On the other hand, with the growing popularity of football and the increasing number of its audiences, the importance of automatic and real-time extraction of statistics and information about soccer matches has increased. One of the critical and challenging tasks in soccer video analysis is the detection of players’ blobs and regions, along with identifying the teams related to the players. This task encounters many challenges, including grass loss in the playfield, the presence of playfield lines and players' shadows, the overlapping of players with objects and other players, and different shapes of players in different situations. This paper proposes a framework for detecting players and their related teams. For this purpose, an object-sieve-based method is used to detect players’ blobs, and a genetic algorithm is used to identify their related teams. Each chromosome of the genetic algorithm is a window that lies on one blob whose fitness function shows how much its color and shape characteristics fit with the uniforms of each of the two teams. The proposed method was evaluated by 50 different frames of broadcast soccer videos, including 563 players, and 40 different sub-images, including 84 players. The results show 98% and 91.6% precision for player detection and labeling, respectively.


Main Subjects

[1] C. Cuevas, D. Quilón, and N. García, “Techniques and applications for soccer video analysis: A survey,” Multimed. Tools Appl., vol. 79, no. 39–40, pp. 29685–29721, 2020, doi: 10.1007/s11042-020-09409-0.
[2] N. Alijanpour, H. Nobari, L. Bolboli, R. Afroundeh, and A. Garcia-Ramos, “Using Global Positioning System to Compare Training Monotony and Training Strain of Starters and Non-Starters across of Full-Season in Professional Soccer Players,” Sustain., vol. 14, no. 6, 2022, doi: 10.3390/su14063560.
[3] L. Morra, F. Manigrasso, and F. Lamberti, “SoccER: Computer graphics meets sports analytics for soccer event recognition,” SoftwareX, vol. 12, 2020, doi: 10.1016/j.softx.2020.100612.
[4] R. Gholizadeh, H. Nobari, L. Bolboli, M. Siahkouhian, and J. P. Brito, “Comparison of Measurements of External Load between Professional Soccer Players,” Healthcare, vol. 10, no. 6, p. 1116, 2022, doi: 10.3390/healthcare10061116.
[5] M. Kaushal, B. S. Khehra, and A. Sharma, “Soft Computing based object detection and tracking approaches: State-of-the-Art survey,” Appl. Soft Comput. J., vol. 70, pp. 423–464, 2018, doi: 10.1016/j.asoc.2018.05.023.
[6] R. Singh, A. Kumar Singh Kushwaha, Chandni, and R. Srivastava, “Recent Trends in Human Activity Recognition- A Comparative Study,” Cogn. Syst. Res., Oct. 2022, doi: 10.1016/j.cogsys.2022.10.003.
[7] M. Gholizade, H. Soltanizadeh, and M. Rahmanimanesh, “A Survey of Transfer Learning and Categories,” Model. Simul. Electr. Electron. Eng., vol. 1, no. 3, pp. 17–25, 2021, doi: 10.22075/mseee.2021.23310.1062.
[8] U. M. Rao and U. C. Pati, “A novel algorithm for detection of soccer ball and player,” 2015 Int. Conf. Commun. Signal Process. ICCSP 2015, pp. 344–348, 2015, doi: 10.1109/ICCSP.2015.7322903.
[9] M. Heydari and A. M. E. Moghadam, “An MLP-based player detection and tracking in broadcast soccer video,” 2012 Int. Conf. Robot. Artif. Intell. ICRAI 2012, pp. 195–199, 2012, doi: 10.1109/ICRAI.2012.6413398.
[10] K. Zhang, J. Wu, X. Tong, and Y. Wang, “An automatic multi-camera-based event extraction system for real soccer videos,” Pattern Anal. Appl., vol. 23, no. 2, pp. 953–965, 2020, doi: 10.1007/s10044-019-00830-2.
[11] J. Liu et al., “Automatic player detection, labeling and tracking in broadcast soccer video,” BMVC 2007 - Proc. Br. Mach. Vis. Conf. 2007, 2007, doi: 10.5244/C.21.3.
[12] S. Nag, P. Shivakumara, U. Pal, T. Lu, and M. Blumenstein, “A new unified method for detecting text from marathon runners and sports players in video (PR-D-19-01078R2),” Pattern Recognit., vol. 107, 2020, doi: 10.1016/j.patcog.2020.107476.
[13] S. Gerke, S. Singh, A. Linnemann, and P. Ndjiki-Nya, “Unsupervised color classifier training for soccer player detection,” IEEE VCIP 2013 - 2013 IEEE Int. Conf. Vis. Commun. Image Process., 2013, doi: 10.1109/VCIP.2013.6706424.
[14]  M. Manafifard, H. Ebadi, and H. A. Moghaddam, “Multi-player detection in soccer broadcast videos using a blob-guided particle swarm optimization method,” Multimed. Tools Appl., vol. 76, no. 10, pp. 12251–12280, 2017, doi: 10.1007/s11042-016-3625-6.
[15] Y. Yang and D. Li, “Robust player detection and tracking in broadcast soccer video based on enhanced particle filter,” J. Vis. Commun. Image Represent., vol. 46, pp. 81–94, 2017, doi: 10.1016/j.jvcir.2017.03.008.
[16] K. Lu, J. Chen, J. J. Little, and H. He, “Lightweight convolutional neural networks for player detection and classification,” Comput. Vis. Image Underst., vol. 172, pp. 77–87, 2018, doi: 10.1016/j.cviu.2018.02.008.
[17] W. Kim, S. W. Moon, J. Lee, D. W. Nam, and C. Jung, “Multiple player tracking in soccer videos: an adaptive multiscale sampling approach,” Multimed. Syst., vol. 24, no. 6, pp. 611–623, 2018, doi: 10.1007/s00530-018-0586-9.
[18] Q. Tran, A. Tran, T. B. Dinh, and D. Duong, “Long-view player detection framework algorithm in broadcast soccer videos,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 6839 LNAI, pp. 557–564, 2011, doi: 10.1007/978-3-642-25944-9_72.
[19] M. A. Montañés Laborda, E. F. Torres Moreno, J. Martínez del Rincón, and J. E. Herrero Jaraba, “Real-time GPU color-based segmentation of football players,” J. Real-Time Image Process., vol. 7, no. 4, pp. 267–279, 2012, doi: 10.1007/s11554-011-0194-9.
[20] W. L. Lu, J. A. Ting, J. J. Little, and K. P. Murphy, “Learning to track and identify players from broadcast sports videos,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 35, no. 7, pp. 1704–1716, 2013, doi: 10.1109/TPAMI.2012.242.
[21] L. H. Chen, C. W. Su, and H. A. Hsiao, “Player trajectory reconstruction for tactical analysis,” Multimed. Tools Appl., vol. 77, no. 23, pp. 30475–30486, 2018, doi: 10.1007/s11042-018-6164-5.