Abstract
Today, due to the growth of data and the development of receiving and storing technologies, large datasets have been created in various fields, such as soccer video datasets. Since obtaining the information manually from large datasets is very difficult, an automated system to capture important information from soccer videos is strongly needed. Automated analysis of soccer videos includes many applications such as: analyzing team tactics, confirming referees’ decisions, summarizing videos, etc.
In this paper, a forward-backward algorithm is proposed to increase the performance of player detection and tracking. The purpose of this algorithm is to identify and resolve the occlusions among the players and improve the preprocessing steps (playfield extraction and field lines elimination). We also proposed a new method for each preprocessing step to improve the performance of the tracking system. The evaluations show that our tracking algorithm has performed better than previous methods (89% locally and 78% globally).
Similar content being viewed by others
Data availability
In this paper, we used two static datasets for our purpose that the links are as follows:
• VS-PETS 2003: http://www.eecs.qmul.ac.uk/~andrea/spevi.html
• ISSIA (spagnolo): https://pspagnolo.jimdofree.com/download/
In addition, we used four broadcast datasets which their details are as follows:
• Liverpool vs Swansea, 28 Oct 2014 EFL Cup
• Real Madrid vs Atletico Madrid, 15 Jan 2015 Copa del Rey
• Cagliari vs Milan, 28 May 2017 Serie A
• Tottenham Hotspur vs Chelsea, 01 Jan 2015 Premier League
References
Asghar MN, Fiaz H, Rob M (2014) Video indexing: a survey. International Journal of Computer and Information Technology 3, no. 01
Baysal S, Duygulu P (2016) Sentioscope: a soccer player tracking system using model field particles. IEEE Transac Circ Syst Video Technol 26(7):1350–1362
Berclaz J, Fleuret F, Turetken E, Fua P (2011) Multiple object tracking using K-shortest paths optimization. IEEE Trans Pattern Anal Mach Intell 33(9):1806–1819
Choi K, Seo Y (2011) Automatic initialization for 3D soccer player tracking. Pattern Recogn Lett 32(9):1274–1282
Choroś K (2016) Automatic playing field detection and dominant color extraction in sports video shots of different view types. Adv Intel Syst Comput Multimed Netw Inform Syst:39–48
Connolly C, Fleiss T (1997) A study of efficiency and accuracy in the transformation from RGB to CIELAB color space. IEEE Trans Image Process 6(7):1046–1048
D’Orazio T, Leo M (2010) A review of vision-based systems for soccer video analysis. Pattern Recogn 43(8):2911–2926
Ekin AT, Mehrotra R (2003) Automatic soccer video analysis and summarization. IEEE Trans Image Process 12(7):796–807
Herrmann M, Hoernig M, Radig B (2014) Online multi-player tracking in monocular soccer videos. AASRI Proc 8:30–37
Heydari M, Moghadam AME (2012) An MLP-based player detection and tracking in broadcast soccer video. 2012 International Conference of Robotics and Artificial Intelligence
Hu T, Mutlu S, Lanz O (2013) Multicamera People Tracking Using a Locus-based Probabilistic Occupancy Map. Image Analysis and Processing – ICIAP 2013 Lecture Notes in Computer Science. pp 693–702
Kim W, Moon S-W, Lee J, Nam D-W, Jung C (2018) Multiple player tracking in soccer videos: an adaptive multiscale sampling approach. Multimedia Systems
Li H, Flierl M (2012) Sift-based multi-view cooperative tracking for soccer video. 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Lu K, Chen J, Little JJ, He H (2018) Lightweight convolutional neural networks for player detection and classification. Computer Vision and Image Understanding
Maćkowiak S, Konieczny J, Kurc M, Maćkowiak P (2010) Soccer player detection in video broadcast. Comput Vision Grap Lecture Notes Comput Sci:118–125
Manafifard M, Ebadi H, Abrishami Moghaddam H (2015) Discrete particle swarm optimization for player trajectory extraction in soccer broadcast videos. Scientia Iranica 22(3):1031–1044
Manafifard M, Ebadi H, Moghaddam HA (2016) Multi-player detection in soccer broadcast videos using a blob-guided particle swarm optimization method. Multimed Tools Appl 76(10):12251–12280
Manafifard M, Ebadi H, Moghaddam HA (2017) A survey on player tracking in soccer videos. Comput Vis Image Underst 159:19–46
Manafifard M, Ebadi H, Moghaddam HA (2017) Appearance-based multiple hypothesis tracking: application to soccer broadcast videos analysis. Signal Process Image Commun 55:157–170
Mathes T, Piater JH (2006) Robust non-rigid object tracking using point distribution manifolds. Lecture Notes Comput Sci Pattern Recog:515–524
Mentzelopoulos M, Psarrou A, Angelopoulou A, García-Rodríguez J (Dec. 2012) Active foreground region extraction and tracking for sports video annotation. Neural Process Lett 37(1):33–46
Moyyila UR (2015) Detection and Recognition of Soccer Ball and Players. PhD diss.
Najafzadeh N, Fotouhi M, Kasaei S (2015) “Multiple soccer players tracking”, 2015 The International Symposium on Artificial Intelligence and Signal Processing (AISP)
Patil DS, Waykar SB (2012) A Survey on Event Recognition and Summarization in Soccer Videos vol, 3, pp.2365–2367
Sasithradevi A, Roomi SMM (2016) Video shot boundary detection using normalized periodogram distance metric. Circuits Syst 07(10):2875–2883
Schlipsing M, Salmen J, Tschentscher M, Igel C (2014) Adaptive pattern recognition in real-time video-based soccer analysis. J Real-Time Image Proc 13(2):345–361
Shitrit HB, Berclaz J, Fleuret F, Fua P (2014) Multi-commodity network flow for tracking multiple people. IEEE Trans Pattern Anal Mach Intell 36(8):1614–1627
Yang Y, Li D (2017) Robust player detection and tracking in broadcast soccer video based on enhanced particle filter. J Vis Commun Image Represent 46:81–94
Zhang S (2015) Research on effective field lines detection and tracking algorithm in soccer videos. Int Multimed Ubiqui Engin 10(7):75–84
Zhang P, Zheng L, Jiang Y, Mao L, Li Z, Sheng B (Feb. 2017) Tracking soccer players using spatio-temporal context learning under multiple views. Multimed Tools Appl 77(15):18935–18955
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Competing interests
The author declares that he has no known competing financial interests or personal relationships that influence the work reported in this paper.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Sani, M.R. Multi object tracking in soccer video focusing on occlusion detection and resolving. Multimed Tools Appl 82, 35913–35947 (2023). https://doi.org/10.1007/s11042-023-14798-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-14798-z