Abstract
In the process of sports movements, relevant actions occur at a fast pace. In the field of artificial intelligence, recognizing such action features poses significant challenges, thereby affecting the accuracy of motion training correction. This paper proposes a correction method for sports training based on a support vector machine classification model. The method involves constructing a skeletal model of the athlete's body, reading keyframes of motion training data, and creating a three-dimensional virtual image model of the motion training using spherical linear interpolation and spatiotemporal deformation methods. This model enables the extraction of motion training action images. The obtained motion training action images are preprocessed using wavelet transformation to extract temporal and frequency domain features, which are then used as inputs to the support vector machine classification model. The model classifies and recognizes correct actions from incorrect actions. Additionally, by decomposing the incorrect motion training actions using RGB plane separation, the information features of motion training images are extracted, and a correction is achieved through comparison. The proposed method has a structural similarity of over 0.923 and an image information entropy of over 0.917 for basketball training action image processing. The recognition rate of dribbling training actions is 97.4%, and the peak signal-to-noise ratio of basketball training action images is 7.2 dB. After correcting the shooting actions using the proposed method, the shooting accuracy reaches 94%.
Similar content being viewed by others
Data availability
Data will be made available on reasonable request.
References
Liu S, Zhang Y, Srivastava G (2023) Point-supervised temporal action localization based on multi-branch attention. Enterp Inform Syst. https://doi.org/10.1080/17517575.2023.2197318
Ye H, Li H, Chen C (2021) Adaptive Deep Cascade Broad Learning System and Its Application in Image Denoising. IEEE Trans Cybern 51(9):4450–4463
Lv X, Xu X, Feng Q, Zhang B, Ding C, Liu Q (2020) High-contrast Imaging based on Wavefront Shaping to Improve Low Signal-to-noise Ratio Photoacoustic Signals using Superpixel Method. Chin Phys B 29(3):251–258
Zhang Y, Zhai X, Wang J (2022) Activity Recognition Approach Using a Low-Resolution Infrared Sensor. Infrared Technol 44(01):47–53
Gao M, Ding Y, Xin H (2022) 3D Skeleton Point Motion Recognition Based on Convolution of Spatiotemporal Multi-residual Image. J Chin Comput Syst 43(12):2570–2574
Sun Q, He N, Zhang C (2022) Human Skeleton Action Recognition Method Based on Lightweight Graph Convolution. Comput Eng 48(5):306–313
Zhang W, Gu L (2022) Motion Comparison and Correction Model Based on Relative Position of Bone Points. Comput Digital Eng 50(07):1552–1556+1619
Ren L (2021) Research on Correction Method of Shooting Angle in Basketball Training based on Visual Perception. J Anyang Normal Univ 133(05):96–100
Kokaram A, Singh D, Robinson S, Kelly D, Collis B, Libreri K (2020) Motion-based Frame Interpolation for Film and Television Effects. IET Comput Vision 14(6):323–338
Yang W, Hui H, Zhang X (2022) Precise Couple Selection and Fitting Method Based on 3D Point Cloud. Comput Simul 39(12):64–68
Liu S, Huang S, Wang S, Khan M, Paolo B, Ser JD (2023) Visual Tracking in Complex Scenes: A Location Fusion Mechanism Based on the Combination of Multiple Visual Cognition Flows. Inform Fusion 96:281–296
Chen X, Zou M, Yang B, Wang Z, Qi L (2021) A Visually Secure Image Encryption Method based on Integer Wavelet Transform and Rhombus Prediction. Math Biosci Eng 18(2):1722–1739
Feigenbaum AS, Grabner PJ, Hardin DP (2021) Eigenfunctions of the Fourier Transform with Specified Zeros. Math Proc Cambridge Philos Soc 171(2):329–367
Liu S, Li Y, Fu W (2022) Human-centered Attention-aware Networks for Action Recognition. Int J Intell Syst 37(12):10968–10987
Davy A, Ehret T, Morel JM, Arias P, Facciolo G (2021) Video Denoising by Combining Patch Search and CNNs. J Math Imaging Vision 63(1):73–88
Li J, Gu D (2021) Research on Basketball Players’ Action Recognition based on Interactive System and machine learning. J Intell Fuzzy Syst 40(2):2029–2039
Song H, Li W, Shen P, Vasilakos A (2017) Gradient-driven parking navigation using a continuous information potential field based on wireless sensor network. Inf Sci 408:100–114
Fan X, Song HB, Fan XF, Yang JC (2018) Imperfect information dynamic stackelberg game based resource allocation using hidden Markov for cloud computing. IEEE Trans Serv Comput 11(1):78–89
Acknowledgements
This work is supported by National Key R&D Program of China (No. 2022YFE0138600). This job is also supported by Supported by Natural Science Foundation of Shaanxi Province of China (2021JM-344) and Open Fund for Chongqing Key Laboratory of Computational Intelligence (No. 2020FF02) and Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data (No. IPBED7).
Author information
Authors and Affiliations
Contributions
Yan Zhang contributed to Writing—Original Draft, Methodology, and Conceptualization; Wei Wei contributed to Conceptualization and Writing—Review and Editing.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
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.
About this article
Cite this article
Zhang, Y., Wei, W. Sports Training Correction based on 3D Virtual Image Model. Mobile Netw Appl (2023). https://doi.org/10.1007/s11036-023-02252-1
Accepted:
Published:
DOI: https://doi.org/10.1007/s11036-023-02252-1