Abstract
Football (soccer) stands as the world’s most popular sport, enthralling millions of fans globally. Within the dynamic sphere of modern football, gaining comprehensive insights into the nuanced technical and physical demands placed on players is pivotal for performance optimization. This paper introduces an innovative deep learning-powered image classification algorithm for recognizing football player activities directly from videos and images. Our pioneering approach harnesses the synergistic capabilities of convolutional neural networks (CNNs) and graph convolutional networks (GCNs) to decipher intricate spatial–temporal patterns in player poses and motions. The methodology employs a hybrid CNN and GCN architecture. The CNN leverages consecutive convolutional and pooling layers to automatically extract discriminative visual features from input frames capturing player poses. The GCN models’ skeletal joints as graph nodes with bones as edges, performing graph convolutions to aggregate spatial and temporal information from neighboring body parts. This enables capturing localized pose dynamics. The complementary CNN and GCN outputs are fused through fully connected layers to classify player activities based on both visual appearances and pose configurations. The model is trained end to end on richly annotated football video data using a multi-class cross-entropy loss. Data augmentation and regularization techniques enhance robustness. Extensive experiments validate the proposed architecture's effectiveness, achieving 97.4% accuracy, 96% precision, 95.5% recall, 95.4% F1-score, 0.90 Matthews correlation, and 93% specificity in classifying 17 complex football activities significantly higher than previous benchmarks. Detailed ablation studies confirm the contributions of the CNN, GCN, and fused model components. The work represents a major advance in leveraging deep neural networks for accurate and granular analysis of sports performances.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00500-023-09321-3/MediaObjects/500_2023_9321_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00500-023-09321-3/MediaObjects/500_2023_9321_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00500-023-09321-3/MediaObjects/500_2023_9321_Fig3_HTML.jpg)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00500-023-09321-3/MediaObjects/500_2023_9321_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00500-023-09321-3/MediaObjects/500_2023_9321_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00500-023-09321-3/MediaObjects/500_2023_9321_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00500-023-09321-3/MediaObjects/500_2023_9321_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00500-023-09321-3/MediaObjects/500_2023_9321_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00500-023-09321-3/MediaObjects/500_2023_9321_Fig9_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00500-023-09321-3/MediaObjects/500_2023_9321_Fig10_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00500-023-09321-3/MediaObjects/500_2023_9321_Fig11_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00500-023-09321-3/MediaObjects/500_2023_9321_Fig12_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00500-023-09321-3/MediaObjects/500_2023_9321_Fig13_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00500-023-09321-3/MediaObjects/500_2023_9321_Fig14_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00500-023-09321-3/MediaObjects/500_2023_9321_Fig15_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00500-023-09321-3/MediaObjects/500_2023_9321_Fig16_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00500-023-09321-3/MediaObjects/500_2023_9321_Fig17_HTML.png)
Similar content being viewed by others
Data availability
The data that support the findings of this study are available from the corresponding author, upon reasonable request.
References
Ali M, Yin B, Kumar A, Sheikh AM et al (2020) Reduction of multiplications in convolutional neural networks. In: 2020 39th Chinese control conference (CCC). IEEE, pp 7406–7411. https://doi.org/10.23919/CCC50068.2020.9188843.
Aslam XD, Hou J, Li Q, Ullah R, Ni Z, Liu Y (2020) Reliable control design for composite-driven scheme based on delay networked T-S fuzzy system. Int J Robust Nonlinear Control 30(4):1622–1642
Cao X, Zhao X, Tang H, Fan N, Zereg F (2023) Football players’ strength training method using image processing based on machine learning. PLoS ONE 18(6):e0287433
Chen Z (2019) Observer-based dissipative output feedback control for network T-S fuzzy systems under time delays with mismatch premise. Nonlinear Dyn 95:2923–2941
Chen W, Yu C, Tu C, Lyu Z, Tang J, Ou S, Fu Y, Xue Z (2020) A survey on hand pose estimation with wearable sensors and computer-vision-based methods. Sensors 20(4):1074
Cuperman R, Jansen KM, Ciszewski MG (2022) An end-to-end deep learning pipeline for football activity recognition based on wearable acceleration sensors. Sensors 22(4):1347
Emam AM, Ali OT, Atia A (2023) Football activities classification. In: 2023 intelligent methods, systems, and applications (IMSA). IEEE, pp 520–525
Feng N, Song Z, Yu J, Chen YPP, Zhao Y, He Y, Guan T (2020) SSET: a dataset for shot segmentation, event detection, player tracking in soccer videos. Multimed Tools Appl 79:28971–28992
Furley P (2019) What modern sports competitions can tell us about human nature. Perspect Psychol Sci 14(2):138–155
García-Aliaga A, Marquina M, Coteron J, Rodriguez-Gonzalez A, Luengo-Sanchez S (2021) In-game behaviour analysis of football players using machine learning techniques based on player statistics. Int J Sports Sci Coach 16(1):148–157
Gupta S, Fahad MS, Deepak A (2020) Pitch-synchronous single frequency filtering spectrogram for speech emotion recognition. Multimed Tools Appl 79:23347–23365
Hazrat B, Yin B, Kumar A, Ali M, Zhang J, Yao J (2023) Jerk-bounded trajectory planning for rotary flexible joint manipulator: an experimental approach. Soft Comput 27(7):4029–4039. https://doi.org/10.1007/s00500-023-07923-5
He K (2021) Prediction model of juvenile football players’ sports injury based on text classification technology of machine learning. Mob Inf Syst 2021:1–10
Host K, Pobar M, Ivasic-Kos M (2023) Analysis of movement and activities of handball players using deep neural networks. J Imaging 9(4):80
Hsu YL, Chang HC, Chiu YJ (2019) Wearable sport activity classification based on deep convolutional neural network. IEEE Access 7:170199–170212
Imran HA (2022) Khail-net: a shallow convolutional neural network for recognizing sports activities using wearable inertial sensors. IEEE Sens Lett 6(9):1–4
** G (2022) Player target tracking and detection in football game video using edge computing and deep learning. J Supercomput 78(7):9475–9491
Kerrigan A, Duarte K, Rawat Y, Shah M (2021) Reformulating zero-shot action recognition for multi-label actions. Adv Neural Inf Process Syst 34:25566–25577
Kumar A, Shaikh AM, Li Y et al (2021) Pruning filters with L1-norm and capped L1-norm for CNN compression. Appl Intell 51:1152–1160. https://doi.org/10.1007/s10489-020-01894-y
Link J, Perst T, Stoeve M, Eskofier BM (2022) Wearable sensors for activity recognition in ultimate frisbee using convolutional neural networks and transfer learning. Sensors 22(7):2560
Liu H, Adreon C, Wagnon N, Bamba AL, Li X, Liu H, MacCall S, Gan Y (2023) Automated player identification and indexing using two-stage deep learning network. Sci Rep 13(1):10036
Mahaseni B, Faizal ERM, Raj RG (2021) Spotting football events using two-stream convolutional neural network and dilated recurrent neural network. IEEE Access 9:61929–61942
Moreira A, Bilsborough JC, Sullivan CJ, Cianciosi M, Aoki MS, Coutts AJ (2015) Training periodization of professional Australian football players during an entire Australian Football League season. Int J Sports Physiol Perform 10(5):566–571
Muhammad IQ, Majid A, Shamrooz S (2023) Adaptive event-triggered robust H∞ control for Takagi–Sugeno fuzzy networked Markov jump systems with time-varying delay. Asian J Control 25(1):213–228
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(1):21–28
Piergiovanni AJ, Ryoo M (2020) Avid dataset: anonymized videos from diverse countries. Adv Neural Inf Process Syst 33:16711–16721
Ranganathan DG (2021) A study to find facts behind preprocessing on deep learning algorithms. J Innov Image Process 3(1):66–74
Rezaei A, Wu LC (2022) Automated soccer head impact exposure tracking using video and deep learning. Sci Rep 12(1):9282
Shamrooz M, Li Q, Hou J (2021) Fault detection for asynchronous T-S fuzzy networked Markov jump systems with new event-triggered scheme. IET Control Theory Appl 15(11):1461–1473
Sharma V, Gupta M, Kumar A, Mishra D (2021) EduNet: a new video dataset for understanding human activity in the classroom environment. Sensors 21(17):5699
Singh R, Sonawane A, Srivastava R (2020) Recent evolution of modern datasets for human activity recognition: a deep survey. Multimed Syst 26(2):83–106
Stoeve M, Schuldhaus D, Gamp A, Zwick C, Eskofier BM (2021) From the laboratory to the field: IMU-based shot and pass detection in football training and game scenarios using deep learning. Sensors 21(9):3071
Ullah R, Dai X, Sheng A (2020) Event-triggered scheme for fault detection and isolation of non-linear system with time-varying delay. IET Control Theory Appl 14(16):2429–2438
Wang L, Zhai Q, Yin B et al (2019) Second-order convolutional network for crowd counting. In: Proc. SPIE 11198, 4th international workshop on pattern recognition, 111980T. https://doi.org/10.1117/12.2540362.
Wang J, Hua Y, Yang Y, Kou H (2023) SPSD: Similarity-preserving self-distillation for video–text retrieval. Int J Multimed Inf Retr 12(2):32
Xu M, Soldan M, Gao J, Liu S, Pérez-Rúa JM, Ghanem B (2023) Boundary-denoising for video activity localization. ar**v:2304.02934
Xu H, Sun Z, Cao Y et al (2023b) A data-driven approach for intrusion and anomaly detection using automated machine learning for the internet of things. Soft Comput. https://doi.org/10.1007/s00500-023-09037-4
Yadav SK, Tiwari K, Pandey HM, Akbar SA (2021) A review of multimodal human activity recognition with special emphasis on classification, applications, challenges and future directions. Knowl Based Syst 223:106970
Yao W, Guo Y, Wu Y, Guo J (2017) Experimental validation of fuzzy PID control of flexible joint system in presence of uncertainties. In: 2017 36th Chinese control conference (CCC). IEEE, pp 4192–4197. https://doi.org/10.23919/ChiCC.2017.8028015
Yin B, Khan J, Wang L, Zhang J, Kumar A (2019) Real-time lane detection and tracking for advanced driver assistance systems. In: 2019 Chinese control conference (CCC). IEEE, pp 6772–6777. https://doi.org/10.23919/ChiCC.2019.8866334
Yin X, Vignesh CC, Vadivel T (2022) Motion capture and evaluation system of football special teaching in colleges and universities based on deep learning. Int J Syst Assur Eng Manag 13(6):3092–3107
Yin B, Aslam MS et al (2023) A practical study of active disturbance rejection control for rotary flexible joint robot manipulator. Soft Comput 27:4987–5001. https://doi.org/10.1007/s00500-023-08026-x
Zhang K, Zuo W, Chen Y, Meng D, Zhang L (2017) Beyond a gaussian denoiser: residual learning of deep cnn for image denoising. IEEE Trans Image Process 26(7):3142–3155
Zhang M, Gao C, Li Q, Wang L, Zhang J (2018) Action detection based on tracklets with the two-stream CNN. Multimed Tools Appl 77:3303–3316
Funding
No funding was provided for the completion of this study.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors have no relevant financial or non-financial interests to disclose. The authors declare that they have no conflict of interest.
Ethical approval
This article does not contain any study with human participants or animals performed by the authors.
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
Li, X., Ullah, R. An image classification algorithm for football players’ activities using deep neural network. Soft Comput 27, 19317–19337 (2023). https://doi.org/10.1007/s00500-023-09321-3
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-023-09321-3