Innovative Approaches in Organizing Physical Education Classes Using Computer Technologies

Original article

DOI: 10.15293/1812-9463.2304.06


Boris A. Shriner

Novosibirsk State Pedagogical University, Novosibirsk, Russia

Konstantin M. Zhomin

Novosibirsk State Pedagogical University, Novosibirsk, Russia


AbstractThe article examines the prospects for using computer vision technologies in the process of physical education of schoolchildren. Modern methods of pattern recognition, detection and tracking of objects are analyzed, which can be used for automated control over the performance of physical exercises. Particular attention is paid to the capabilities of the MediaPipe library, which allows you to track the position and movement of human body parts in real time. We considered specific algorithms and software solutions based on MediaPipe, OpenCV, TensorFlow, Keras, which allow you to analyze the correctness of movement, assess physical activity, and recognize errors. The possibility of using neural network algorithms to assess posture and build an optimal trajectory of movements is shown. The CV-Trainer program was developed and tested for automated assessment of constitutional features (body type), determination of body proportions, calculation of angles and lengths of body segments, which allows you to quantify the amplitude and trajectory of motion of motor action on video. The prospects of integrating computer vision technologies into the educational process to increase the efficiency and individualization of physical education of schoolchildren are discussed.

Keywordscomputer technology, computer vision, computer program, physical education, physical exercise, automation, schoolchildren.

For Citation: Shriner B. A., Zhomin K. M. Innovative Approaches in Organizing Physical Education Classes Using Computer Technologies. Journal of Pedagogical Innovations, 2023, no. 4 (72), pp. 77–85. (In Russ.) DOI:

FundingThe study was carried out within the framework of the project “Research and development of methods for classes on recreational physical educationˮ, which is being implemented with the financial support of the Ministry of Education of the Russian Federation within the framework of state task no. 073-03-2023-027 of 27.01.2023.



1. Boyko G. M., Purygina M. G. Application of artificial intelligence and its assistance to players and coaches in sports. Young scientist, 2021, no. 50 (392), pp. 28–32. (In Russian)

2. Ermakov A. V. Analysis of the movement in martial arts using the OpenCV “computer vision” libraries and the MediaPipe artificial intelligence framework. Martial arts and combat sports: science, practice, education: materials of the VI All-Russian scientific and practical conference with international participation (Moscow, October 14, 2021) / edited by Yu. L. Orlova, L. G. Ryzhkova. Moscow: Publishing house of the Russian University of Sports, 2021, pp. 106–111. (In Russian)

3. Ermakov A. V., Goretskaya N. N. Analysis of the amplitude of movement during throwing a knife at a distance of 3 meters using the framework of artificial intelligence. Integration of science and sports practice in combat sports: collection of conference proceedings (Moscow, November 16, 2021). Moscow: Publishing house of the Russian University of Sports, 2021, pp. 167–173. (In Russian)

4. Ermakov A. V., Myakinchenko P. E. Forecasting using methods of mathematical modeling in sports of higher achievements on the example of winter sports. Theory and practice of physical culture, 2021, no. 2, pp. 52–54. (In Russian)

5. Zinkevich A. V., Zaluskaya E. E., Tur A. A. Application of human posture and gesture assessment in the buildingʼs digital twin. Perspectives of science, 2023, no. 7 (166),
pp. 38–41. (In Russian)

6. Kaznacheev D. G. Tracking hand movement using computer vision. Best research work 2021: a collection of articles of the XXXII International Research Competition (Penza, August 15, 2021) / edited by G. Yu. Gulyaeva. Penza: Nauka i Prosveshchenie Publ., 2021, pp. 29–32. (In Russian)

7. Kiselev Yu. V., Bogomolov I. A., Rozaliev V. L., Baklan V. A. Analysis of approaches, methods and solutions for detecting human posture. Choosing a tool for the task of determining a personʼs emotional state by his pose. Modern science-intensive technologies, 2023, no. 6, pp. 41–47. (In Russian) DOI:

8. Lapaeva A. G., Tabakov S. E., Ermakov A. V. Verification of the methodology for measuring the V-factor when making throws with a turn in sambo. Bulletin of Sports Science, 2023, no. 3, pp. 82–87. (In Russian)

9. Medvedev A. A., Laptev A. A. Algorithm for identifying non-verbal markers of human behavior on video. Scientific result. Information technology, 2022, vol. 7, issue 2, pp. 58–64. (In Russian) DOI:

10. Obukhov A. D., Dedov D. L., Surkova E. O., Korobova I. L. The method of three-dimensional capture of human movements based on computer vision. Advanced Engineering Research (Rostov-on-Don), 2023, vol. 23, issue 3, pp. 317–328. (In Russian) DOI:

11. Obukhov A. D., Volkov A. A., Vekhteva N. A. [et al.] Method of forming a digital shadow of the human movement process based on the combination of motion capture systems. Informatics and automation, 2023, vol. 22, issue 1, pp. 168–189. DOI: (In Russian)

12. Solovyova A. Artificial intelligence — the prospects of application in the sports industry [Electronic resource]. URL: =2 (date of access: 11.08.2023). (In Russian)

13. Surkova E. O., Arkhipov A. E., Vekhteva N. A. Development of an algorithm of occupation of movements of the person on the basis of computer sight. Formation of Russia and topical issues of modern science: the collection of articles VI of the All-Russian academic and research conference (Penza, May 22–23, 2023) / edited by P. A. Gagayev,
E. P. Belozertseva. Penza: Publishing house of the Penza State Agricultural University, 2023, pp. 464–468. (In Russian)

14. Terekhin A. D., Ilyalov O. R., Stepanov A. V. The system of estimation of sports exercises according to the neural network analysis of a video series. Applied mathematics and issues of management, 2022, no. 1, pp. 75–86. (In Russian) DOI:

15. Irshad M. T., Nisar M. A., Gouverneur P., Rapp M., Grzegorzek M. AI Approaches towards Prechtl’s Assessment of General Movements: A Systematic Literature Review. Sensors, 2020, vol. 20, issue 18. DOI:

16. Sers R., Forrester S., Moss E., Ward S., Ma J., Zecca M. Validity of the Perception Neuron Inertial Motion Capture System for Upper Body Motion Analysis. Measurement, 2020, vol. 149. DOI:


Information about the Authors

Boris А. Schreiner – Candidate of Psychological Sciences, Associate Professor of the Department of Information Systems, Novosibirsk State Pedagogical University, Novosibirsk, Russia,,

Konstantin M. Zhomin – Candidate of Biological Sciences, Associate Professor, Associate Professor of the Department of Sports Disciplines, Novosibirsk State Pedagogical University, Novosibirsk, Russia,,


Authorsʼ contribution: Authors have all made an equivalent contribution to preparing the article for publication.

The authors declare no conflict of interest.

Received: 18.08.2023; approved after peer review: 18.10.2023; accepted for publication: 02.11.2023.