Skip to main content

Advertisement

SpringerLink
Log in

Data driven intelligent action recognition and correction in sports training and teaching

  • Special Issue
  • Published:
Evolutionary Intelligence Aims and scope Submit manuscript

Abstract

With the development of world economy, sports development has also become a symbol of national strength. Nowadays, sports competition has become an important activity for all countries to show their strength, and also an important bridge to connect all countries and build friendship. In the process of challenging the limit, human beings gradually master the action essentials of various sports, and the action difference of athletes directly affects the grades of the competition. Therefore, in the process of sports training, athletes of various countries will focus on the standard of action of each athlete. In traditional sports training, veteran athletes with rich experience are usually used as coaches to guide athletes empirically. However, the difference of coaches will also lead to the difference of sports effects. At the same time, coaches’ grasp of athletes’ action standards is more based on subjective observation, which cannot be accurately measured, so there may be large differences and errors in their grasp of action standards. In this paper, we propose an intelligent action recognition and correction system to assist coaches to measure and evaluate athletes’ actions more accurately, and give correction suggestions according to standard actions. Our system uses RGB-D sensors to analyze athletes’ skeleton key points in real time. The different between the athlete’s action and the standard action is calculated through the connection between the joint key points. In this paper, we also use the timing tracking algorithm to comprehensively evaluate the consistency of the action with the standard. We verified the feasibility of the recognition correction system through the actual movement and measurement of athletes. The experiment shows that our system can accurately measure the movements of athletes, and has more accurate measurement results and correction suggestions than the traditional coach naked eye measurement.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Data availability

All data used to support the findings of the study is included within this paper.

References

  1. Wang Z, Qin R, Yan J, Guo C (2019) Vision sensor based action recognition for improving efficiency and quality under the environment of industry 4.0. Procedia CIRP 80:711–716

    Article  Google Scholar 

  2. Yin J, Han J, Wang C, Zhang B, Zeng X (2019) A skeleton-based action recognition system for medical condition detection. In: 2019 IEEE biomedical circuits and systems conference (BioCAS), IEEE, pp 1–4 

  3. Lee J, Ahn B (2020) Real-time human action recognition with a low-cost RGB camera and mobile robot platform. Sensors 20(10):2886

    Article  Google Scholar 

  4. Cheng Y, Liang X, Xu Y, Kuang X (2022) Artificial intelligence technology in basketball training action recognition. Front Neurorobotics 16

  5. Martin PE, Benois-Pineau J, Péteri R, Morlier J (2020) Fine grained sport action recognition with twin spatio-temporal convolutional neural networks. Multimed Tools Appl 79(27):20429–20447

    Article  Google Scholar 

  6. Xiong W, Bertoni L, Mordan T, Alahi A (2022) Simple yet effective action recognition for autonomous driving. In: 11th triennial symposium on transportation analysis conference (TRISTAN XI) (No. CONF)

  7. Kerboua A, Batouche M (2019) 3D skeleton action recognition for security improvement. Int J Intell Syst Appl 11(3):42

    Google Scholar 

  8. Yang C, Chen D, Xu Z (2021) Action recognition system for security monitoring. In: International conference on artificial intelligence, virtual reality, and visualization (AIVRV 2021), SPIE, vol 12153, pp 62–67

  9. Fangbemi AS, Liu B, Yu NH, Zhang Y (2018) Efficient human action recognition interface for augmented and virtual reality applications based on binary descriptor. In: International conference on augmented reality, virtual reality and computer graphics, Springer, Cham, pp 252–260

  10. Sheng B, Xiao F, Sha L, Sun L (2020) Deep spatial–temporal model based cross-scene action recognition using commodity WiFi. IEEE Internet Things J 7(4):3592–3601

    Article  Google Scholar 

  11. Zheng T, Yang W, Sun J, Liu Z, Wang K, Zou X (2022) Processing IMU action recognition based on brain-inspired computing with microfabricated MEMS resonators. Neuromorph Comput Eng 2(2):024004

    Article  Google Scholar 

  12. Shaikh MB, Chai D (2021) RGB-D data-based action recognition: a review. Sensors 21(12):4246

    Article  Google Scholar 

  13. Yang L, Zhang L, Dong H, Alelaiwi A, Saddik E (2015) Evaluating and improving the depth accuracy of Kinect for Windows v2. IEEE Sens J 15(8):4275–4285

    Article  Google Scholar 

  14. Carfagni M, Furferi R, Governi L, Santarelli C, Servi M, Uccheddu F, Volpe Y (2019) Metrological and critical characterization of the Intel D415 stereo depth camera. Sensors 19(3):489

    Article  Google Scholar 

  15. Yang X, Tian Y (2014) Super normal vector for activity recognition using depth sequences. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 804–811

  16. Oreifej O, Liu Z (2013) Hon4d: histogram of oriented 4d normals for activity recognition from depth sequences. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 716–723

  17. Rahmani H, Mahmood A, Huynh DQ, Mian A (2014) Real time action recognition using histograms of depth gradients and random decision forests. In: IEEE winter conference on applications of computer vision, IEEE, pp 626–633

  18. Sun J (2022) A digital feature recognition technology used in ballet training action correction. Comput Intell Neurosci 2022

  19. Ding Z (2018) Research on human behavior recognition technology based on smart phone sensor Dissertation of Master. Hunan University

  20. Crochiere RE (1981) Digital signal processor: sub-band coding. Bell Syst Tech J 60(7):1633–1653

    Article  Google Scholar 

  21. Tang J. Research on moving human body recognition system based on DSP. Dissertation of Master. Huazhong University of science and technology

  22. Li B, Wang L, Feng H (2022) Intelligent Correction Method of Shooting Action Based on Computer Vision. Comput Intell Neurosci 2022

  23. Shapiro LG, Stockman GC (2001) Computer vision, vol 3. Prentice Hall, New Jersey

    Google Scholar 

  24. Szeliski R (2010) Computer vision: algorithms and applications. Springer, Cham

    MATH  Google Scholar 

  25. Ahad MAR (2011) Computer vision and action recognition: a guide for image processing and computer vision community for action understanding, vol 5. Springer, Cham

    Google Scholar 

  26. Ke L, Li X, Bisk Y, Holtzman A, Gan Z, Liu J, Srinivasa S (2019) Tactical rewind: self-correction via backtracking in vision-and-language navigation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 6741–6749

  27. Jia B (2020) Recognition model of sports athletes’ wrong actions based on computer vision

  28. Zhang S (2022) An intelligent and fast dance action recognition model using two-dimensional convolution network method. J Environ Public Health 2022

  29. Zhao C (2021) Application of virtual reality and artificial intelligence technology in fitness clubs. Math Probl Eng 2021

  30. Miao J et al (2022) Practical and secure multifactor authentication protocol for autonomous vehicles in 5G. Software. Practice and Experience

  31. Ionescu C, Papava D, Olaru V et al (2013) Human3.6m: large scale datasets and predictive methods for 3d human sensing in natural environments. IEEE Trans Pattern Anal Mach Intell 36(7):1325–1339

    Article  Google Scholar 

Download references

Funding

This paper has not received any funding support yet.

Author information

Authors and Affiliations

  1. Jilin Engineering Vocational College, Siping, 136001, People’s Republic of China

    Sicong Shan & Shuang Sun

  2. Dalian Maritime University, Dalian, 116026, People’s Republic of China

    Peng Dong

Authors
  1. Sicong Shan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shuang Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Peng Dong
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sicong Shan.

Ethics declarations

Conflict of interest

The authors declare that there is no conflict of interest in this paper.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Shan, S., Sun, S. & Dong, P. Data driven intelligent action recognition and correction in sports training and teaching. Evol. Intel. 16, 1679–1687 (2023). https://doi.org/10.1007/s12065-023-00827-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12065-023-00827-1

Keywords

Search

Navigation