Research on RDE-pose football player foul recognition and pose estimation based on the improved model of YOLOv8

Abstract

Aiming at the problems of large amount of calculation and slow detection speed of the existing soccer pose estimation model, this paper proposes a lightweight improved algorithm based on YOLOv8-Pose model and applies it to the recognition task of soccer player’s foul behavior. Firstly, RepConv and DBB reparameterization modules are introduced to enhance the ability of multi-scale feature fusion and solve the problem of large scale difference of visual objects. A centralized intra-layer adjustment feature pyramid network is designed, which combines the deformable attention mechanism and CASPPF in a parallel way. The pyramid network is globally centralized adjusted in a top–down manner, and the spatial weight of the global representation in the network is increased, so that the improved algorithm can obtain comprehensive and discriminative feature representation. The cross-entropy loss function is replaced by the exponential sliding sample weighting function (EMA‐SlideLoss) to enhance the classification ability of the model and improve the stability of training. Using these methods, we propose an improved model RDE-YOLOv8-Pose model. The experimental results show that compared with the YOLOv8-Pose model, this research method improves mAP@0.5 by 0.142 and achieves a detection speed of 47.4 frames/s. This study can effectively improve the motion capture ability of artificial intelligence methods for soccer players, and provide more efficient and accurate technical support for intelligent monitoring of sports events and auxiliary referee decision-making.

Keywords

pose detection action foul YOLOv8-pose reparameterization module CASPPF EMA-SlideLoss

Get full access to this article

View all access options for this article.

References

Najjar

M-C

. Legal and ethical issues arising from the application of data analytics and artificial intelligence to traditional sports. Albany Law J Sci Technol 2023; 33: 51. DOI: 10.1016/j.socimp.2024.100040.

Zhou

Chen

. Application of deep learning technology in strength training of football players and field line detection of football robots. Front Neurorob 2022; 16: 867028. DOI: 10.3389/fnbot.2022.867028.

Wang

Liu

. Analyzing the feature extraction of football player’s offense action using machine vision, big data, and internet of things. Soft Comput 2023; 27(15): 10905–10920. DOI: 10.1007/s00500-023-08735-3.

Zhang

Yan

. AI-driven image recognition system for automated offside and foul detection in football matches using computer vision. Int J Adv Comput Sci Appl 2025; 16(1): 2025. DOI: 10.14569/IJACSA.2025.01601114.

Wang

Tan

Zhen

, et al. Deep 3D human pose estimation: a review. Comput Vis Image Understand 2021; 210: 103225. DOI: 10.1007/s00500-023-08735-3.

Host

Ivašić-Kos

. An overview of human action recognition in sports based on computer vision. Heliyon 2022; 8(6): e09633. DOI: 10.1016/j.heliyon.2022.e09633.

Liu

Bao

Sun

, et al. Recent advances of monocular 2D and 3D human pose estimation: a deep learning perspective. ACM Comput Surv 2022; 55(4): 1–41. DOI: 10.1145/3524497.

Yan

Xiong

, et al. Boosting integral-based human pose estimation through implicit heatmap learning. Neural Netw 2024; 179: 106524. DOI: 10.1016/j.neunet.2024.106524.

Ewers

J-H

Anderson

Thomson

. Deep reinforcement learning for time-critical wilderness search and rescue using drones. Front Robot AI 2025; 11: 1527095. DOI: 10.3389/frobt.2024.1527095.

10.

Sun

Zhang

Luo

, et al. Human action recognition using a convolutional neural network based on skeleton heatmaps from two-stage pose estimation. Biom Intel Rob 2022; 2(3): 100062. DOI: 10.1016/j.birob.2022.100062.

11.

Kappan

Sandoval

Meijering

, et al. Attention-enhanced lightweight hourglass network for human pose estimation. arXiv preprint, 2024. DOI: 10.48550/arXiv.2412.06227.

12.

Sun

Wang

Huang

, et al. Fast semantic segmentation of ultra-high-resolution remote sensing images via score map and fast transformer-based fusion. Remote Sens 2024; 16(17): 3248. DOI: 10.3390/rs16173248.

13.

Zhang

, et al. Student network learning via evolutionary knowledge distillation. IEEE Trans Circ Syst Video Technol 2021; 32(4): 2251–2263. DOI: 10.1109/TCSVT.2021.3090902.

14.

Cheng

Wang

Yang

, et al. Monocular 3D multi-person pose estimation by integrating top-down and bottom-up networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 7649–7659. IEEE. DOI: 10.1109/CVPR46437.2021.00756.

15.

El Kaid

Brazey

Barra

, et al. Top-down system for multi-person 3D absolute pose estimation from monocular videos. Sensors 2022; 22(11): 4109. DOI: 10.3390/s22114109.

16.

Chen

Guo

Yang

, et al. Fast vehicle detection algorithm in traffic scene based on improved SSD. Measurement 2022; 201: 111655. DOI: 10.1016/j.measurement.2022.111655.

17.

Jin

Zhou

, et al. Focus on local: detecting lane marker from bottom up via key point. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 14122–14130. IEEE. DOI: 10.1109/CVPR46437.2021.01390.

18.

Nguyen

H-C

Nguyen

T-H

Nowak

, et al. Combined YOLOv5 and HRNet for high accuracy 2D keypoint and human pose estimation. J Artif Intell Soft Comput Res 2022; 12(4): 281–298. DOI: 10.2478/jaiscr-2022-0019.

19.

Sun

Brockhauser

Hegedűs

. Comparing end-to-end machine learning methods for spectra classification. Appl Sci 2021; 11(23): 11520. DOI: 10.3390/app112311520.

20.

Knap

. Human modelling and pose estimation overview. arXiv preprint, 2024. DOI: 10.48550/arXiv.241219290.

21.

Liu

, et al. Human skeleton behavior recognition model based on multi-object pose estimation with spatiotemporal semantics. Mach Vis Appl 2023; 34(3): 44. DOI: 10.1007/s00138-023-01396-0.

22.

Papaioannidis

Mademlis

Pitas

. Fast CNN-based single-person 2D human pose estimation for autonomous systems. IEEE Trans Circ Syst Video Technol 2022; 33(3): 1262–1275. DOI: 10.1109/TCSVT.2022.3209160.

23.

Toshpulatov

Lee

, et al. Human pose, hand and mesh estimation using deep learning: a survey. J Supercomput 2022; 78(6): 7616–7654. DOI: 10.1007/s11227-021-04184-7.

24.

Xiao

, et al. An automatic assessment model of adenoid hypertrophy in MRI images based on deep convolutional neural networks. IEEE Access 2023; 11: 106516–106527. DOI: 10.1109/ACCESS.2023.3316689.

25.

Liu

Chen

Feng

, et al. Deep dual consecutive network for human pose estimation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 525–534. IEEE. DOI: 10.1109/CVPR46437.2021.00059.

26.

Liu

Wang

Lang

, et al. An accurate deep key-point prediction model with low-level texture refinement and high-level semantic enhancement for bolt vertex detection in industrial machine systems. IEEE Access 2025; 13: 48226–48238. DOI: 10.1109/ACCESS.2025.3547332.

27.

Muzammul

Algarni

Ghadi

, et al. Enhancing UAV aerial image analysis: integrating advanced SAHI techniques with real-time detection models on the VisDrone dataset. IEEE Access 2024; 12: 21621–21633. DOI: 10.1109/ACCESS.2024.3363413.

28.

Wei

Cao

, et al. NN-Stretch: automatic neural network branching for parallel inference on heterogeneous multi-processors. In: Proceedings of the 21st Annual International Conference on Mobile Systems, Applications and Services, 2023, pp. 70–83. IEEE. DOI: 10.1145/3581791.3596870.

29.

Hamaguchi

. Multi-branch network for addressing intra-class variation in remote sensing building detection. IEEE J Sel Top Appl Earth Obs Rem Sens 2024; 17: 16710–16726. DOI: 10.1109/JSTARS.2024.3454110.

30.

Jiang

Gao

. Interact-pose datasets for 2D human pose estimation in multi-person interaction scene. In: International Symposium on Artificial Intelligence and Robotics, 2022, pp. 211–223. Springer. DOI: 10.1007/978-981-19-7943-9_18.