Item request has been placed! ×
Item request cannot be made. ×
loading  Processing Request

Human swimming posture recognition combining improved 3D convolutional network and attention residual network.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
Read Online Read More Add to Saved list
  • Author(s): Li M;Li M; Ning C; Ning C
  • Source:
    PloS one [PLoS One] 2025 Dec 02; Vol. 20 (12), pp. e0337577. Date of Electronic Publication: 2025 Dec 02 (Print Publication: 2025).
  • Publication Type:
    Journal Article
  • Language:
    English
  • Additional Information
    • Source:
      Publisher: Public Library of Science Country of Publication: United States NLM ID: 101285081 Publication Model: eCollection Cited Medium: Internet ISSN: 1932-6203 (Electronic) Linking ISSN: 19326203 NLM ISO Abbreviation: PLoS One Subsets: MEDLINE
    • Publication Information:
      Original Publication: San Francisco, CA : Public Library of Science
    • Subject Terms:
      Swimming*/physiology ; Posture*/physiology ; Neural Networks, Computer*; Humans ; Algorithms
    • Abstract:
      Human swimming posture recognition is a key technology to improve training effect and reduce sports injury by analyzing and recognizing swimmer's movement posture. However, the existing technical means cannot accomplish the accurate recognition of human swimming posture in underwater environment with high standard. For this reason, the study takes the 3D convolutional neural network as the model basis, and introduces the global average pooling and batch normalization to optimize its network structure and data processing, respectively. Meanwhile, full pre-activation residual network and three-branch structure convolutional attention mechanism are added to improve the feature extraction and recognition. Finally, a novel human swimming posture recognition model is proposed. The outcomes revealed that this model had the highest recognition accuracy of 95%, the highest recall of 93.26% and the highest F1 value of 92.87%. The lowest pose recognition errors were up to 4.7%, 4.9%, 2.1% and 6.6% for freestyle, breaststroke, butterfly and backstroke, respectively. The shortest recognition time was 6.78 s for the freestyle item, which minimized the recognition time and reduced the recognition error compared with the same type of recognition model. The new model proposed by the research shows significant advantages in recognition accuracy and computational efficiency. It can provide more effective support for recognizing athletes' swimming posture for future swimming endeavors.
      (Copyright: © 2025 Li, Ning. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)
    • Abstract:
      The authors have declared that no competing interests exist.
    • References:
      Sensors (Basel). 2023 Feb 15;23(4):. (PMID: 36850778)
      Sensors (Basel). 2023 Nov 08;23(22):. (PMID: 38005436)
      Sensors (Basel). 2023 Feb 20;23(4):. (PMID: 36850962)
      Sci Rep. 2024 Jan 2;14(1):55. (PMID: 38167475)
      Diagnostics (Basel). 2023 May 26;13(11):. (PMID: 37296713)
      IEEE Trans Neural Netw Learn Syst. 2023 Dec;34(12):9874-9886. (PMID: 35439141)
      Sensors (Basel). 2022 Dec 08;22(24):. (PMID: 36559983)
      Micromachines (Basel). 2023 Oct 31;14(11):. (PMID: 38004907)
    • Publication Date:
      Date Created: 20251202 Date Completed: 20251202 Latest Revision: 20251205
    • Publication Date:
      20260130
    • Accession Number:
      PMC12671778
    • Accession Number:
      10.1371/journal.pone.0337577
    • Accession Number:
      41329706