Dr. Hab., Associate Professor A.A. Polozov¹
Dr. Phys.-Math., Professor D.B. Berg¹
Postgraduate student N.A. Maltseva¹
Postgraduate student B.B.A. Almomani^1
1Ural Federal University named after the First President of Russia B.N. Yeltsin, Yekaterinburg

Objective of the study was to development of a system for dynamic management of a professional team's game in real time («Computer Trainer»).
Methods and structure of the study. As part of the experimental part of the study, a comparative analysis of the effectiveness of computer vision algorithms used to analyze video recordings of basketball games of the ASB Division Sverdlovsk Region championship was conducted. Based on the data obtained, an assessment of the accuracy and performance of mathematical models developed to solve control system problems was carried out.
Results and conclusions. The tasks of calculating three-dimensional coordinates of players with an error of 0,4 m, detecting players, the ball, tracking players, classifying teams of players, recognizing numbers on T-shirts were solved. Without the participation of neural networks, it was possible to identify 30 types of technical and tactical martial arts (TTMA), a method for generating voice commands in real time, elements of communication with players were implemented. The estimated effect of implementation is estimated by us at 22-28% of additional points scored, however, due to a number of technical limitations, it is not yet possible to use the full potential of the project. The authors are open to cooperation with professional clubs to complete the project.

Keywords: game management system, sport, coach, information technology, big data, machine learning, optimization, team efficiency.

References

1. Polozov, A. A., Kudryavtsev, I. V., Karmanov, A. A., & Maltseva, N. A. (2022). Golosovoye upravleniye komandoy kompyuternym trenerom v basketbole (PIRS online) [Voice control of a team with a computer coach in basketball (PIRS online)]. Teoriya i praktika fizicheskoy kultury, 11, 54–56.
2. Polozov, A. A., Golshteyn, S. L., Maltseva, N. A., et al. (2024). Kachestvo metodov trekinga s reindefikatsiyey obyektov [Quality of tracking methods with object reindexation]. Vestnik DGU, Tekhnicheskiye nauki, 51(3), 103–109.