Application of computer vision methods in improving the efficiency of training process management for crosscountry skiers

ˑ: 

PhD N.B. Novikova1
A.N. Novikov2
I.G. Ivanova1
A.N. Belyova1
1Saint-Petersburg scientific-research institute for physical culture, St. Petersburg
2ITMO University, St. Petersburg

Objective of the study was to experimentally substantiate the use of the computer vision method in increasing the efficiency of managing the training process of cross-country skiers.
Methods and structure of the study. The analysis of video recordings of athletes skating on roller skis at maximum speed was performed in a specially created computer program, including a system for recognizing athletes' movements based on the Alpha Pose neural network.
Results and conclusions. The developed computer program allows to recognize with sufficient accuracy video recordings of ski racers, made in conditions of training and competitive activity, to visualize the dynamics of angular characteristics and angular velocities of movement in joints, and also to build videograms in automatic mode. The obtained data allow to evaluate the efficiency of skiing technique and to identify technical errors, which are difficult to notice when using traditional methods of technique analysis.

Keywords: highly skilled cross-country skiers, technical training, technique of simultaneous one-step skating, neural network, computer vision methods, scientific and methodological support, video analysis of sports movements.

References

  1. Novikova N.B., Ivanova I.G., Belyova A.N. Informativnost biomekhanicheskikh kriteriyev v otsenke sorevnovatelnoy effektivnosti lyzhnikov-gonshchikov vysokoy kvalifikatsii [Informativeness of biomechanical criteria in assessing the competitive efficiency of highly qualified cross-country skiers]. Teoriya i praktika fizicheskoy kultury. 2024. No. 5. pp. 34-37.
  2. Colyer S.L., Evans M., D.P. Cosker, Salo A. A Review of the Evolution of Vision-Based Motion Analysis and the Integration of Advanced Computer Vision Methods Towards Developing a Markerless System. Sports Med Open. 2018. Vol. 4. No 4 (1). 24 p.
  3. Ludwig K. Lienhart R., Muller S., Kreibich S. Optimierung der voll automatischenzeit kontinuierlichen Erkennung der Korperpose und Skiposition von Skispringern in Videoaufnahmen. BISp-Jahrbuch Forschungs förderung. 2021/22. pp. 361-364.