Fusion-Net50-Based Soccer Player Re-Identification and Team Clustering for Speed and Movement Analysis
DOI:
https://doi.org/10.29207/resti.v10i4.7457Keywords:
ByteTrack, football, K-means Clustering, Re-ID-ColorEmbedding ResNet-50, YOLOv8nAbstract
Comprehensive analysis of soccer matches requires substantial human resources as well as specialized equipment with relatively high costs. The development of Computer Vision (CV) technology, particularly the Multi-Object Tracking (MOT) approach, enables contactless and efficient analysis of player performance. However, the main challenges in MOT for soccer, namely player re-identification, tracking ID switches, as well as inter-frame identity consistency, especially under occlusion conditions and low-confidence detections, can cause the analysis data to become invalid. This research aims to improve object identity consistency (Tracking ID) in video-based soccer match analysis by integrating detection, tracking, re-identification, and team identification methods. This research proposes the integration of YOLOv8n- and ByteTrack-based tracking methods with a Re-ID embedding mechanism, low-confidence detection handling, as well as ResNet-50-based Feature–Position Fusion to maintain identity consistency (Track ID) throughout the video sequence. Furthermore, team identification is consistently performed using a Color Embedding approach with a ResNet-50 backbone and the K-Means clustering algorithm. The experimental results show that the integration of all these methods successfully maintains consistent Track ID with a total of 25 Track IDs (Players 21 Track IDs, Goalkeeper 1 Track ID, Referee 2 Track IDs, Ball 1 Track ID). This performance is supported by evaluation metrics indicating strong performance, namely HOTA of 91.9%, MOTA of 89.8%, and MOTP of 81.0%. The effectiveness of the Re-ID module in maintaining object identity consistency is reflected in the IDF1 score of 94.9%. Supported by association metrics (AssA 93.5%, AssRe 94.8%, AssPr 96.3%), these results indicate that trajectories are formed with a relatively low level of association errors, thereby supporting subsequent analyses such as speed estimation and player movement visualization in a more stable manner.
Downloads
References
UEFA, “UEFA EURO 2024: Record Attendance and Fan Engagement Figures,” Jul. 2024. [Online]. Available: https://www.sportspro.com/insights/analysis/euro-2024-stats-tv-ratings-viewership-attendance-social-media-sales/
S. Plakias, “Review Articles on Soccer Performance Analysis: A Bibliometric Analysis of Current Trends and Emerging Themes,” Sports, vol. 13, no. 5, p. 131, 2025, doi: 10.3390/sports13050131.
C. Huang, M. Zhang, and C. Li, “Tactical Analysis and Performance Metrics,” Psychol. Sport Exerc., vol. 73, p. 102695, 2024, [Online]. Available: https://ssrn.com/abstract=4758324
S. Plakias, T. Tsatalas, V. Armatas, D. Tsaopoulos, and G. Giakas, “Tactical Situations and Playing Styles as Key Performance Indicators in Soccer,” JFMK, vol. 9, no. 2, p. 88, May 2024, doi: 10.3390/jfmk9020088.
B. Mahaseni, E. R. M. Faizal, and R. G. Raj, “Spotting football events using two-stream convolutional neural network and dilated recurrent neural network,” IEEE Access, vol. 9, pp. 61929–61942, 2021. doi: 10.1109/ACCESS.2021.3074831.
F. Zheng, D. Z. Al-Hamid, P. H. J. Chong, C. Yang, and X. J. Li, “A Review of Computer Vision Technology for Football Videos,” Information, vol. 16, no. 5, p. 355, Apr. 2025, doi: 10.3390/info16050355.
Y. Sun, Z. Sun, and W. Chen, “The evolution of object detection methods,” Jul. 01, 2024, Elsevier Ltd. doi: 10.1016/j.engappai.2024.108458.
E. Edozie, A. N. Shuaibu, U. K. John, and B. O. Sadiq, “Comprehensive review of recent developments in visual object detection based on deep learning,” Artif. Intell. Rev., vol. 58, no. 9, Sep. 2025, doi: 10.1007/s10462-025-11284-w.
Y.-L. Chen, K.-C. Hung, J.-Y. Zhang, and L.-W. Lin, “Improved YOLOv8n Models for Object Detection in Remote Sensing Images,” IEEE Access, vol. 13, pp. 97889–97900, 2025, doi: 10.1109/ACCESS.2025.3574856.
E. S. d. Santos Júnior, T. Paixão, and A. B. Alvarez, “Comparative Performance of YOLOv8, YOLOv9, YOLOv10, and YOLOv11 for Layout Analysis of Historical Documents Images,” Applied Sciences, vol. 15, no. 6, p. 3164, 2025, doi: 10.3390/app15063164.
Y. Wang and V. Y. Mariano, “A Multi Object Tracking Framework Based on YOLOv8s and Bytetrack Algorithm,” IEEE Access, vol. 12, pp. 120711–120719, 2024, doi: 10.1109/ACCESS.2024.3450370.
L. You, Y. Chen, C. Xiao, C. Sun, and R. Li, “Multi-Object Vehicle Detection and Tracking Algorithm Based on Improved YOLOv8 and ByteTrack,” Electronics (Switzerland), vol. 13, no. 15, Aug. 2024, doi: 10.3390/electronics13153033.
J. Cao, J. Pang, X. Weng, R. Khirodkar, and K. Kitani, “Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking,” Mar. 2023, [Online]. Available: http://arxiv.org/abs/2203.14360
V. Stanojević and B. Todorović, “BoostTrack++: using tracklet information to detect more objects in multiple object tracking,” Aug. 2025, [Online]. Available: http://arxiv.org/abs/2408.13003
J. Sun, H. W. Huang, C. Y. Yang, Z. Jiang, and J. N. Hwang, “GTA: Global Tracklet Association for Multi-Object Tracking in Sports,” in Proceedings of the Asian Conference on Computer Vision, 2024, pp. 421–434. doi: 10.1007/978-981-96-2644-1_6.
B. T. Naik, M. F. Hashmi, Z. W. Geem, and N. D. Bokde, “DeepPlayer-Track: Player and Referee Tracking With Jersey Color Recognition in Soccer,” IEEE Access, vol. 10, pp. 32494–32509, 2022, doi: 10.1109/ACCESS.2022.3161441.
B. Thulasya Naik, M. F. Hashmi, and A. Gupta, “EIoU-distance loss: an automated team-wise player detection and tracking with jersey colour recognition in soccer,” 2024, Taylor and Francis Ltd. doi: 10.1080/09540091.2023.2291991.
K. Zhou, Y. Yang, A. Cavallaro, and T. Xiang, “Learning Generalisable Omni-Scale Representations for Person Re-Identification,” Apr. 2021, [Online]. Available: http://arxiv.org/abs/1910.06827
H. J. Mohammed et al., “ReID-DeePNet: A Hybrid Deep Learning System for Person Re-Identification,” Mathematics, vol. 10, no. 19, Oct. 2022, doi: 10.3390/math10193530.
A. Tanapatpiboon, W. Kusakunniran, and W. Limroongreungrat, “Deep learning-based detection of players and teams in soccer videos with positioning heatmap generation,” ACI, 2025, doi: 10.1108/ACI-07-2024-0257.
S. Chen, X. Ouyang, and F. Luo, “Ensemble One-Class Support Vector Machine for Sea Surface Target Detection Based on k-Means Clustering,” Remote Sens. (Basel)., vol. 16, no. 13, p. 2401, 2024, doi: 10.3390/rs16132401.
S. Jardim, J. António, and C. Mora, “Graphical Image Region Extraction with K-Means Clustering and Watershed,” J. Imaging, vol. 8, no. 6, Jun. 2022, doi: 10.3390/jimaging8060163.
A. Cioppa and others, “SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videos,” in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2022, pp. 3490–3501. doi: 10.1109/cvprw56347.2022.00393.
Ultralytics, “Ultralytics YOLOv8 Docs: Models,” 2023. [Online]. Available: https://docs.ultralytics.com/models/yolov8/
Roboflow, “Supervision 0.27.0 – Trackers Documentation,” 2025. [Online]. Available: https://supervision.roboflow.com/0.27.0/trackers/
A. Alfarano, L. Maiano, L. Papa, and I. Amerini, “Estimating Optical Flow: A Comprehensive Review of the State of the Art,” Computer Vision and Image Understanding, vol. 249, p. 104160, 2024, doi: 10.1016/j.cviu.2024.104160.
H. Yin, R. O. Sinnott, and G. T. Jayaputera, “A survey of video-based human action recognition in team sports,” Artif. Intell. Rev., vol. 57, no. 11, Nov. 2024, doi: 10.1007/s10462-024-10934-9.
T. Brox, A. Bruhn, N. Papenberg, and J. Weickert, “High Accuracy Optical Flow Estimation Based on a Theory for Warping,” in Computer Vision - ECCV 2004, vol. 3024, T. Pajdla and J. Matas, Eds., in Lecture Notes in Computer Science, vol. 3024. , Berlin, Heidelberg: Springer, 2004. doi: 10.1007/978-3-540-24673-2_3.
Bureau International des Poids et Mesures, “The International System of Units (SI), 9th ed.,” 2019, Sèvres, France. Available: https://www.bipm.org/en/publications/si-brochure
Downloads
Published
Issue
Section
License
Copyright in each article belongs to the author
- The author acknowledges that the RESTI Journal (System Engineering and Information Technology) is the first publisher to publish with a license Creative Commons Attribution 4.0 International License.
- Authors can enter writing separately, arrange the non-exclusive distribution of manuscripts that have been published in this journal into other versions (eg sent to the author's institutional repository, publication in a book, etc.), by acknowledging that the manuscript has been published for the first time in the RESTI (Rekayasa Sistem dan Teknologi Informasi) journal ;
