1932

Abstract

There has been rapid growth in the collection of player tracking data in recent years. These data, providing spatiotemporal locations of players and ball at high resolution, have spurred methodological developments in a range of sports. There have been impacts in the development of player performance measurement (e.g., distance traveled) and in the attribution of value to specific plays (e.g., expected points from a given position) or even specific actions within a play. This review highlights key methodological contributions via statistical and machine learning approaches. The studies and outcomes discussed show how sports can be a playground for extending analytical techniques in a range of areas. The review also describes the ongoing methodological challenges associated with the use of tracking data.

Loading

Article metrics loading...

/content/journals/10.1146/annurev-statistics-033021-110117
2023-03-09
2024-04-21
Loading full text...

Full text loading...

/deliver/fulltext/statistics/10/1/annurev-statistics-033021-110117.html?itemId=/content/journals/10.1146/annurev-statistics-033021-110117&mimeType=html&fmt=ahah

Literature Cited

  1. Albert J, Koning RH. 2007. Statistical Thinking in Sports Boca Raton, FL: CRC
  2. Alcorn MA, Nguyen A. 2021. baller2vec: a multi-entity transformer for multi-agent spatiotemporal modeling. arXiv:2102.03291 [cs.LG]
  3. Amirli A, Alemdar H. 2022. Prediction of the ball location on the 2D plane in football using optical tracking data. Acad. Platf. J. Eng. Smart Syst. 10:11–8
    [Google Scholar]
  4. Andrzejewski M, Chmura J, Pluta B, Konarski JM. 2015. Sprinting activities and distance covered by top level Europa League soccer players. Int. J. Sports Sci. Coach. 10:139–50
    [Google Scholar]
  5. Arbués-Sangüesa A, Martín A, Fernández J, Ballester C, Haro G. 2020. Using player's body-orientation to model pass feasibility in soccer Paper presented at IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, June 16–18
  6. Baca A. 2014. Computer Science in Sport: Research and Practice. London: Taylor & Francis
  7. Bialkowski A, Lucey P, Carr P, Matthews I, Sridharan S, Fookes C. 2016. Discovering team structures in soccer from spatiotemporal data. IEEE Trans. Knowl. Data Eng. 28:102596–605
    [Google Scholar]
  8. Brefeld U, Davis J, Van Haaren J, Zimmermann A, eds. 2019. Proceedings of the 5th International Machine Learning and Data Mining for Sports Analytics Workshop (MLSA 2018), Co-Located with ECML/PKDD 2018 Berlin: Springer
    [Google Scholar]
  9. Bueno MJO, Caetano FG, Pereira TJC, De Souza NM, Moreira GD et al. 2014. Analysis of the distance covered by Brazilian professional futsal players during official matches. Sports Biomech. 13:3230–40
    [Google Scholar]
  10. Burke B. 2019. DeepQB: deep learning with player tracking to quantify quarterback decision-making & performance Paper presented at 13th Annual MIT Sloan Sports Analytics Conference, Boston, March 1–2. https://www.sloansportsconference.com/research-papers/deepqb-deep-learning-with-player-tracking-to-quantify-quarterback-decision-making-performance
  11. Cao Z, Liao T, Song W, Chen Z, Li C 2021. Detecting the shuttlecock for a badminton robot: a YOLO based approach. Exp. Syst. Appl. 164:113833
    [Google Scholar]
  12. Cervone D, Bornn L, Goldsberry K. 2016a. NBA court realty Paper presented at 10th Annual MIT Sloan Sports Analytics Conference, Boston, March 12–13
  13. Cervone D, D'Amour A, Bornn L, Goldsberry K 2016b. A multiresolution stochastic process model for predicting basketball possession outcomes. J. Am. Stat. Assoc. 111:514585–99
    [Google Scholar]
  14. Chan TCY, Fearing DS, Fernandes C, Kovalchik S. 2021. A Markov process approach to untangling intention versus execution in tennis. arXiv:2110.01527 [math.OC]
  15. Cho H, Ryu H, Song M. 2021. Pass2vec: analyzing soccer players' passing style using deep learning. Int. J. Sports Sci. Coach. 17:2355–65
    [Google Scholar]
  16. Colyer SL, Evans M, Cosker DP, Salo AI. 2018. A review of the evolution of vision-based motion analysis and the integration of advanced computer vision methods towards developing a markerless system. Sports Med. Open 4:24
    [Google Scholar]
  17. Delves RI, Aughey RJ, Ball K, Duthie GM. 2021. The quantification of acceleration events in elite team sport: a systematic review. Sports Med 7:45
    [Google Scholar]
  18. Deshpande SK, Evans K. 2020. Expected hypothetical completion probability. J. Quant. Anal. Sports 16:285–94
    [Google Scholar]
  19. Dutta R, Yurko R, Ventura SL. 2020. Unsupervised methods for identifying pass coverage among defensive backs with NFL player tracking data. J. Quant. Anal. Sports 16:2143–61
    [Google Scholar]
  20. Felsen P, Lucey P, Ganguly S. 2018. Where will they go? Predicting fine-grained adversarial multi-agent motion using conditional variational autoencoders. Proceedings of the 15th European Conference on Computer Vision732–47 Berlin: Springer
    [Google Scholar]
  21. Fernández J, Bornn L. 2018. Wide Open Spaces: a statistical technique for measuring space creation in professional soccer Paper presented at 12th Annual MIT Sloan Sports Analytics Conference, Boston, Febr. 23–24
  22. Fernández J, Bornn L, Cervone D. 2019. Decomposing the immeasurable sport: a deep learning expected possession value framework for soccer Paper presented at 13th Annual MIT Sloan Sports Analytics Conference, Boston, March 1–2. https://www.sloansportsconference.com/research-papers/decomposing-the-immeasurable-sport-a-deep-learning-expected-possession-value-framework-for-soccer
  23. Fonseca S, Milho J, Travassos B, Araújo D. 2012. Spatial dynamics of team sports exposed by Voronoi diagrams. Hum. Mov. Sci. 31:61652–59
    [Google Scholar]
  24. Franks A, Miller A, Bornn L, Goldsberry K. 2015. Characterizing the spatial structure of defensive skill in professional basketball. Ann. Appl. Stat. 9:194–121
    [Google Scholar]
  25. Gastin PB, McLean O, Spittle M, Breed RV. 2013. Quantification of tackling demands in professional Australian football using integrated wearable athlete tracking technology. J. Sci. Med. Sport 16:6589–93
    [Google Scholar]
  26. Georgiou T, Liu Y, Chen W, Lew M 2020. A survey of traditional and deep learning–based feature descriptors for high dimensional data in computer vision. Int. J. Multimed. Inf. Retr. 9:3135–70
    [Google Scholar]
  27. Gerrard B 2016. Analytics, technology and high-performance sport. Critical Issues in Global Sport Management S Frawley, N Schulenkorf 227–40 London: Routledge
    [Google Scholar]
  28. Giles B, Kovalchik S, Reid M 2020. A machine learning approach for automatic detection and classification of changes of direction from player tracking data in professional tennis. J. Sports Sci. 38:1106–13
    [Google Scholar]
  29. Goes FR, Brink MS, Elferink-Gemser MT, Kempe M, Lemmink KA. 2021a. The tactics of successful attacks in professional association football: large-scale spatiotemporal analysis of dynamic subgroups using position tracking data. J. Sports Sci. 39:5523–32
    [Google Scholar]
  30. Goes FR, Meerhoff LA, Bueno MJO, Rodrigues DM, Moura FA et al. 2021b. Unlocking the potential of big data to support tactical performance analysis in professional soccer: a systematic review. Eur. J. Sport Sci. 21:4481–96
    [Google Scholar]
  31. Goldsberry K. 2012. CourtVision: new visual and spatial analytics for the NBA Paper presented at 6th Annual MIT Sloan Sports Analytics Conference, Boston, March 2–3
  32. Goldsberry K. 2019. Sprawlball: A Visual Tour of the New Era of the NBA New York: Houghton Mifflin
  33. Gray AJ, Jenkins DG. 2010. Match analysis and the physiological demands of Australian football. Sports Med. 40:4347–60
    [Google Scholar]
  34. Han S, Dunson DB. 2018. Multiresolution tensor decomposition for multiple spatial passing networks. arXiv:1803.01203 [stat.AP]
  35. Harley JA, Lovell RJ, Barnes CA, Portas MD, Weston M. 2011. The interchangeability of global positioning system and semiautomated video-based performance data during elite soccer match play. J. Strength Cond. Res. 25:82334–36
    [Google Scholar]
  36. Hoppe MW, Baumgart C, Polglaze T, Freiwald J. 2018. Validity and reliability of GPS and LPS for measuring distances covered and sprint mechanical properties in team sports. PLOS ONE 13:2e0192708
    [Google Scholar]
  37. Horton M. 2020. Learning feature representations from football tracking Paper presented at 14th Annual MIT Sloan Sports Analytics Conference, Boston, March 6–7. https://www.sloansportsconference.com/research-papers/learning-feature-representations-from-football-tracking
  38. Hughes M, Franks IM, Dancs H. 2019. Essentials of Performance Analysis in Sport London: Taylor & Francis
  39. Johnson N. 2022. Basketball data Data Set, GitHub. https://github.com/neilmj/BasketballData
  40. Jones MR, West DJ, Crewther BT, Cook CJ, Kilduff LP. 2015. Quantifying positional and temporal movement patterns in professional rugby union using global positioning system. Eur. J. Sport Sci. 15:6488–96
    [Google Scholar]
  41. Khatoonabadi SH, Rahmati M. 2009. Automatic soccer players tracking in goal scenes by camera motion elimination. Image Vis. Comput. 27:4469–79
    [Google Scholar]
  42. Kovalchik S. 2021. Why tennis is still not ready to play moneyball. Harvard Data Sci. Rev. 3:1 https://hdsr.mitpress.mit.edu/pub/uy0zl4i1
    [Google Scholar]
  43. Kovalchik S, Albert J 2022. A statistical model of serve return impact patterns in professional tennis. arXiv:2202.00583 [stat.ME]
  44. Kovalchik S, Ingram M, Weeratunga K, Goncu C. 2020. Space-time VON CRAMM: evaluating decision-making in tennis with variational generation of complete resolution arcs via mixture modeling. arXiv:2005.12853 [stat.AP]
  45. Kovalchik S, Reid M. 2018. A shot taxonomy in the era of tracking data in professional tennis. J. Sports Sci. 36:182096–104
    [Google Scholar]
  46. Layden T. 2010. Blood, Sweat and Chalk. The Ultimate Football Playbook: How the Great Coaches Built Today's Game. New York: Time
  47. Le HM, Carr P, Yue Y, Lucey P. 2017a. Data-driven ghosting using deep imitation learning Paper presented at 11th Annual MIT Sloan Sports Analytics Conference, Boston, March 3–4
  48. Le HM, Yue Y, Carr P, Lucey P. 2017b. Coordinated multi-agent imitation learning. Proc. Mach. Learn. Res. 70:1995–2003
    [Google Scholar]
  49. LeCun Y, Kavukcuoglu K, Farabet C. 2010. Convolutional networks and applications in vision. Proceedings of 2010 IEEE International Symposium on Circuits and Systems253–56 Piscataway, NJ: IEEE
    [Google Scholar]
  50. Lemire J. 2020. SOTI reveal: ‘Good eye’ will take on a whole new meaning in Major League Baseball. SportTechie Blog March 26. https://sporttechie.com/mlb-statcast-hawk-eye-baseball
    [Google Scholar]
  51. Link D, Lang S, Seidenschwarz P. 2016. Real time quantification of dangerousity in football using spatiotemporal tracking data. PLOS ONE 11:12e0168768
    [Google Scholar]
  52. Liu G, Luo Y, Schulte O, Kharrat T. 2020. Deep soccer analytics: learning an action-value function for evaluating soccer players. Data Min. Knowl. Discov. 34:51531–59
    [Google Scholar]
  53. Lucey P, Oliver D, Carr P, Roth J, Matthews I 2013. Assessing team strategy using spatiotemporal data. Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining1366–74 New York: ACM
    [Google Scholar]
  54. MarketWatch News Dep 2022. Sports technology market size, share, growth, trends. Report 2022–2030 Press Release, MarketWatch New York: Sept. 30. https://www.marketwatch.com/press-release/sports-technology-market-size-share-growth-trends-report-2022-2030-2022-09-30
  55. Masheswaran R, Chang YH, Su J, Kwok S, Levy T et al. 2014. The three dimensions of rebounding Paper presented at 8th Annual MIT Sloan Sports Analytics Conference, Boston, March 1–2
  56. Mehrasa N, Zhong Y, Tung F, Bornn L, Mori G. 2017. Deep learning of player trajectory representations for team activity analysis Paper presented at 11th Annual MIT Sloan Sports Analytics Conference, Boston, March 3–4
  57. Miller A, Bornn L, Adams R, Goldsberry K 2014. Factorized point process intensities: a spatial analysis of professional basketball. Proceedings of the 31st International Conference on Machine Learning235–43 New York: ACM
    [Google Scholar]
  58. Moeslund T, Thomas G, Hilton A, eds. 2015. Computer Vision in Sports Berlin: Springer
  59. Müller O, Caron M, Döring M, Heuwinkel T, Baumeister J. 2021. PIVOT: a parsimonious end-to-end learning framework for valuing player actions in handball using tracking data Paper presented at 8th Workshop on Machine Learning and Data Mining for Sports Analytics, online, Sept. 13
  60. Naemura M, Fukuda A, Mizutani Y, Izumi Y, Tanaka Y, Enami K. 2000. Morphological segmentation of sport scenes using color information. IEEE Trans. Broadcast. 46:3181–88
    [Google Scholar]
  61. Naik BT, Hashmi MF. 2021. Ball and player detection and tracking in soccer videos using improved YOLOv3 model. Work. Pap., Natl. Inst. Technol. Warangal, Hanamkonda India: https://doi.org/10.21203/rs.3.rs-438886/v1
    [Crossref]
  62. Naik BT, Hashmi MF, Bokde ND. 2022. A comprehensive review of computer vision in sports: open issues, future trends and research directions. arXiv:2203.02281 [cs.CV]
  63. Oliva-Lozano JM, Fortes V, Krustrup P, Muyor JM. 2020. Acceleration and sprint profiles of professional male football players in relation to playing position. PLOS ONE 15:8e0236959
    [Google Scholar]
  64. Oliva-Lozano JM, Fortes V, Muyor JM. 2021. The first, second, and third most demanding passages of play in professional soccer: a longitudinal study. Biol. Sport 38:2165
    [Google Scholar]
  65. Park LA, Scott D, Lovell R. 2019. Velocity zone classification in elite women's football: Where do we draw the lines?. Sci. Med. Footb. 3:121–28
    [Google Scholar]
  66. Pereira TJC, Nakamura FY, de Jesus MT, Vieira CLR, Misuta MS et al. 2017. Analysis of the distances covered and technical actions performed by professional tennis players during official matches. J. Sports Sci. 35:4361–68
    [Google Scholar]
  67. Petway AJ, Freitas TT, Calleja-González J, Medina Leal D, Alcaraz PE 2020. Training load and match-play demands in basketball based on competition level: a systematic review. PLOS ONE 15:3e0229212
    [Google Scholar]
  68. Phillips D. 2014. Tessellation. Wiley Interdiscip. Rev. Comput. Stat. 6:3202–9
    [Google Scholar]
  69. Pileggi H, Stolper CD, Boyle JM, Stasko JT. 2012. Snapshot: visualization to propel ice hockey analytics. IEEE Trans. Vis. Comput. Graph. 18:122819–28
    [Google Scholar]
  70. Power P, Ruiz H, Wei X, Lucey P. 2017. Not all passes are created equal: objectively measuring the risk and reward of passes in soccer from tracking data. Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining1605–13 New York: ACM
    [Google Scholar]
  71. Puterman ML. 2014. Markov Decision Processes: Discrete Stochastic Dynamic Programming New York: Wiley
  72. Redmon J, Divvala S, Girshick R, Farhadi A. 2015. You Only Look Once: unified, real-time object detection. arXiv:1506.02640 [cs.CV]
  73. Rein R, Memmert D 2016. Big data and tactical analysis in elite soccer: future challenges and opportunities for sports science. SpringerPlus 5:1410
    [Google Scholar]
  74. Rein R, Raabe D, Perl J, Memmert D 2016. Evaluation of changes in space control due to passing behavior in elite soccer using Voronoi cells. Proceedings of the 10th International Symposium on Computer Science in Sports179–83 Berlin: Springer
    [Google Scholar]
  75. Sarlis V, Tjortjis C. 2020. Sports analytics—evaluation of basketball players and team performance. Inf. Syst. 93:101562
    [Google Scholar]
  76. Schmid M, Blauberger P, Lames M. 2021. Simulating defensive trajectories in American football for predicting league average defensive movements. Front. Sports Act. Living 3:669845
    [Google Scholar]
  77. Seidl T, Cherukumudi A, Hartnett A, Carr P, Lucey P. 2018. Bhostgusters: real-time interactive play sketching with synthesized NBA defenses Paper presented at 12th Annual MIT Sloan Sports Analytics Conference, Boston, Febr. 23–24
  78. Sicilia A, Pelechrinis K, Goldsberry K. 2019. DeepHoops: evaluating microactions in basketball using deep feature representations of spatio-temporal data. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining2096–104 New York: ACM
    [Google Scholar]
  79. Spearman W, Basye A, Dick G, Hotovy R, Pop P. 2017. Physics-based modeling of pass probabilities in soccer Paper presented at 11th Annual MIT Sloan Sports Analytics Conference, Boston, March 3–4
  80. Taberner M, O'Keefe J, Flower D, Phillips J, Close G et al. 2020. Interchangeability of position tracking technologies; can we merge the data?. Sci. Med. Footb. 4:176–81
    [Google Scholar]
  81. Taki T, Hasegawa J 2000. Visualization of dominant region in team games and its application to teamwork analysis. Proceedings of Computer Graphics International 2000227–35 Piscataway, NJ: IEEE
    [Google Scholar]
  82. Terner Z, Franks A. 2021. Modeling player and team performance in basketball. Annu. Rev. Stat. Appl. 8:1–23
    [Google Scholar]
  83. Tian C, De Silva V, Caine M, Swanson S. 2019. Use of machine learning to automate the identification of basketball strategies using whole team player tracking data. Appl. Sci. 10:124
    [Google Scholar]
  84. Tora MR, Chen J, Little JJ. 2017. Classification of puck possession events in ice hockey. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition147–54 Piscataway, NJ: IEEE
    [Google Scholar]
  85. Torres-Ronda L, Beanland E, Whitehead S, Sweeting A, Clubb J. 2022. Tracking systems in team sports: a narrative review of applications of the data and sport specific analysis. Sports Med 8:15
    [Google Scholar]
  86. Varley MC, Aughey RJ. 2013. Acceleration profiles in elite Australian soccer. Int. J. Sports Med. 34:134–39
    [Google Scholar]
  87. Wei X, Lucey P, Morgan S, Sridharan S. 2016. Forecasting the next shot location in tennis using fine-grained spatiotemporal tracking data. IEEE Trans. Knowl. Data Eng. 28:112988–97
    [Google Scholar]
  88. Wunderlich F, Memmert D. 2021. Forecasting the outcomes of sports events: a review. Eur. J. Sport Sci. 21:7944–57
    [Google Scholar]
  89. Xie J, Gao R, Nijkamp E, Zhu SC, Wu YN. 2020. Representation learning: a statistical perspective. Annu. Rev. Stat. Appl. 7:303–35
    [Google Scholar]
  90. Xu Z, Shi P. 2005. Segmentation of players and team discrimination in soccer videos. Proceedings of the 2005 IEEE International Workshop on VLSI Design and Video Technology369–72 Piscataway, NJ: IEEE
    [Google Scholar]
  91. Yoon Y, Hwang H, Choi Y, Joo M, Oh H et al. 2019. Analyzing basketball movements and pass relationships using realtime object tracking techniques based on deep learning. IEEE Access 7:56564–76
    [Google Scholar]
  92. Yue Y, Lucey P, Carr P, Bialkowski A, Matthews I. 2014. Learning fine-grained spatial models for dynamic sports play prediction. Proceedings of the 2014 IEEE International Conference on Data Mining670–79 Piscataway, NJ: IEEE
    [Google Scholar]
  93. Yurko R, Matano F, Richardson LF, Granered N, Pospisil T et al. 2020. Going deep: models for continuous-time within-play valuation of game outcomes in American football with tracking data. J. Quant. Anal. Sports 16:2163–82
    [Google Scholar]
  94. Zaheer M, Kottur S, Ravanbakhsh S, Poczos B, Salakhutdinov RR, Smola AJ. 2017. Deep sets. Proceedings of the 31st Conference on Neural Information Processing Systems (NeurIPS 2017)3391–401 Red Hook, NY: Curran
    [Google Scholar]
/content/journals/10.1146/annurev-statistics-033021-110117
Loading
/content/journals/10.1146/annurev-statistics-033021-110117
Loading

Data & Media loading...

  • Article Type: Review Article
This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error