Analisis Kerapatan Pertahanan Sepak Bola Berbasis Computer Vision dan Transformasi Homografi

Savio Hendriko Palendeng; Oktavian Abraham Lantang; Muhamad Dwisnanto Putro

doi:10.30606/rjti.v5i3.4772

Authors

Savio Hendriko Palendeng Universitas Sam Ratulangi
Oktavian Abraham Lantang Universitas Sam Ratulangi
Muhamad Dwisnanto Putro Universitas Sam Ratulangi

DOI:

https://doi.org/10.30606/rjti.v5i3.4772

Keywords:

Computer Vision, Deep Learning, Object Tracking, Sports Analytics, Transformasi Homografi

Abstract

Defensive compactness and inter-player distance are crucial tactical aspects in football. However, their evaluation has traditionally relied on subjective visual observation, which is highly susceptible to bias caused by perspective distortion from television broadcast cameras. This research aims to develop an automated data-driven spatiotemporal analytics system to quantitatively extract tactical metrics from single broadcast camera videos. This system provides an objective solution for coaching staff to precisely evaluate the effectiveness of defensive strategies, replacing manual observation methods. The proposed method integrates Computer Vision and Deep Learning, utilizing the YOLOv11m model for player detection, the BoTSORT tracking algorithm, and a color space filter for team differentiation. The 2D pixel coordinates are then converted into real-world pitch distance metrics using Homographic Transformation supported by Global Motion Estimation (GME) to overcome camera movement. Testing on static (Indonesia National Team) and dynamic (Bayern Munich) defensive scenarios showed that the detection model achieved an mAP50 precision of 0.986, with a tracking accuracy (MOTA) of 89.78%. Field distance projection validation recorded a very low error rate (MAPE) of 7.93% in the static calibration area. This computational system is proven reliable as a Sports Analytics instrument to reduce tactical interpretation bias, map Convex Hull and dyadic distances, and objectively support coaches strategic decision-making.

Downloads

Download data is not yet available.

References

L. Forcher, L. Forcher, S. Altmann, D. Jekauc, and M. Kempe, "Is a compact organization important for defensive success in elite soccer? – Analysis based on player tracking data," Int. J. Sports Sci. Coach., vol. 19, no. 2, pp. 757–768, Apr. 2024, doi: 10.1177/17479541231172695.

H. F. Wibowo and D. Nugroho, "JOSSAE (Journal of Sport Science and Education) Analisis Momen Pola Menyerang, Bertahan dan Transisi pada Timnas Indonesia U-19 Vs Bulgaria," Journal of Sport Science and Education), vol. 6, no. 1, p. 57, 2021, doi: 10.26740/j.

F. G. Caetano, V. P. Da Silva, R. D. S. Torres, R. D. O. Anido, S. A. Cunha, and F. A. Moura, "Analysis of Match Dynamics of Different Soccer Competition Levels Based on the Player Dyads," J. Hum. Kinet., vol. 70, no. 1, pp. 173–182, Nov. 2019, doi: 10.2478/hukin-2019-0030.

B. Jin, "Video analysis and data-driven tactical optimization of sports football matches: Visual recognition and strategy analysis algorithm," Journal of Autonomous Intelligence, vol. 7, no. 5, p. 1581, Mar. 2024, doi: 10.32629/jai.v7i5.1581.

F. Denis and A. Steinmaier, "Real-Time Offside Detection in Football Using Computer Vision and Artificial Intelligence Techniques," 2024.

F. Öberg, "Football analysis using machine learning and computer vision," Master's Thesis, Linköping University, 2021.

P. P. Dharnamoni, K. N. Sri, K. Pradnya, and Dr. D. Shravani, "Real-Time Football Match Analysis Using Deep Learning," International Journal of Multidisciplinary Research and Growth Evaluation, vol. 6, no. 2, pp. 710–715, 2025, doi: 10.54660/.ijmrge.2025.6.2.710-715.

P. S. S. Markappa, C. Oleary, and C. Lynch, "A Review of YOLO Models for Soccer-Based Object Detection," in 6th International Conference on Intelligent Computing in Data Sciences, ICDS 2024, Institute of Electrical and Electronics Engineers Inc., 2024. doi: 10.1109/ICDS62089.2024.10756443.

K. Rangasamy, M. A. As'ari, N. A. Rahmad, N. F. Ghazali, and S. Ismail, "Deep learning in sport video analysis: A review," Telkomnika (Telecommunication Computing Electronics and Control), vol. 18, no. 4, pp. 1926–1933, 2020, doi: 10.12928/TELKOMNIKA.V18I4.14730.

R. Khanam and M. Hussain, "YOLOv11: An Overview of the Key Architectural Enhancements," Oct. 2024, [Online]. Available: http://arxiv.org/abs/2410.17725

J. Agrawal, R. Maheshwari, S. Nalode, Y. Prabhat, P. Sonsare, and K. Khurana, "Football Player Detection and Tracking Using Deep Learning Approach," in 2024 International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Applications, ICAIQSA 2024 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 2024. doi: 10.1109/ICAIQSA64000.2024.10882213.

M. R. Hartono, C. A. Sari, and R. R. Ali, "FOOTBALL PLAYER TRACKING, TEAM ASSIGNMENT, AND SPEED ESTIMATION USING YOLOV5 AND OPTICAL FLOW," Jurnal Teknik Informatika (Jutif), vol. 6, no. 1, pp. 51–62, Feb. 2025, doi: 10.52436/1.jutif.2025.6.1.4165.

J. Joshan Athanesious and S. Kiruthika, "Perspective Transform Based YOLO With Weighted Intersect Fusion for Forecasting the Possession Sequence of the Live Football Game," IEEE Access, vol. 12, pp. 75542–75558, 2024, doi: 10.1109/ACCESS.2024.3402370.

K. Kausalya, K. S. Raja S, and S. Sudha, "An optimized deep learning approach for detection and classification of player actions in football game," Entertain. Comput., vol. 55, Sep. 2025, doi: 10.1016/j.entcom.2025.101003.

B. Low, D. Coutinho, B. Gonçalves, R. Rein, D. Memmert, and J. Sampaio, "A Systematic Review of Collective Tactical Behaviours in Football Using Positional Data," Feb. 01, 2020, Springer. doi: 10.1007/s40279-019-01194-7.

V. R. Chaganti, M. Mann, R. P. Badoni, and S. B. Mandyam, "Advanced Computer Vision Techniques for Football Match Analysis: Detection, Team Assignment, and Player Tracking," in International Conference on Artificial Intelligence and Emerging Technologies, ICAIET 2025, Institute of Electrical and Electronics Engineers Inc., 2025. doi: 10.1109/ICAIET65052.2025.11211437.

S. Raschka, J. Patterson, and C. Nolet, "Machine learning in python: Main developments and technology trends in data science, machine learning, and artificial intelligence," Apr. 01, 2020, MDPI AG. doi: 10.3390/info11040193.

F. Zhuang et al., "A Comprehensive Survey on Transfer Learning," Jan. 01, 2021, Institute of Electrical and Electronics Engineers Inc. doi: 10.1109/JPROC.2020.3004555.

soccer players, "soccer players Dataset," Roboflow Universe, 2024. [Online].

M. Adžemović, "Deep Learning-Based Multi-Object Tracking: A Comprehensive Survey from Foundations to State-of-the-Art," Jun. 2025, [Online]. Available: http://arxiv.org/abs/2506.13457

N. Aharon, R. Orfaig, and B.-Z. Bobrovsky, "BoT-SORT: Robust Associations Multi-Pedestrian Tracking," Jul. 2022, [Online]. Available: http://arxiv.org/abs/2206.14651

O. Lantang, G. Terdik, A. Hajdu, and A. Tiba, "Investigation of the efficiency of an interconnected convolutional neural network by classifying medical images," Annales Mathematicae et Informaticae, vol. 53, pp. 219–234, 2021, doi: 10.33039/ami.2021.04.001.

Q. Cheng, Z. Zhifeng, Y. Ke, T. Zhang, and J. I. Guotai, "Homography matrix estimation method based on adaptive genetic algorithm," vol. 16, 2025, [Online]. Available: http://jmsi.publish.founderss.cn

M. J. de O. Bueno, M. Silva, S. A. Cunha, R. da S. Torres, and F. A. Moura, "Multiscale fractal dimension applied to tactical analysis in football: A novel approach to evaluate the shapes of team organization on the pitch," PLoS One, vol. 16, no. 9 September, Sep. 2021, doi: 10.1371/journal.pone.0256771.

J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection," May 2016, [Online]. Available: http://arxiv.org/abs/1506.02640

A. A. Murat and M. S. Kiran, "A comprehensive review on YOLO versions for object detection," Oct. 01, 2025, Elsevier B.V. doi: 10.1016/j.jestch.2025.102161.

Y. Zhang et al., "ByteTrack: Multi-Object Tracking by Associating Every Detection Box." [Online]. Available: https://github.com/ifzhang/ByteTrack.

H.-Q. Chen, C.-C. Liao, Y.-H. Sun, C.-K. Lin, and Y.-C. Tseng, "FieldMOT: A Field-Registered Multi-Object Tracking for Sports Videos." [Online]. Available: https://github.com/maomao726/FieldTrack.

M. Rico-González, J. Pino-Ortega, J. Castellano, J. M. Oliva-Lozano, and A. L. Arcos, "Reference values for collective tactical behaviours based on positional data in professional football matches: A systematic review," 2022, Institute of Sport. doi: 10.5114/biolsport.2021.102921.

Z. Cao, G. Hidalgo, T. Simon, S. E. Wei, and Y. Sheikh, "OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields," IEEE Trans. Pattern Anal. Mach. Intell., vol. 43, no. 1, pp. 172–186, Jan. 2021, doi: 10.1109/TPAMI.2019.2929257.