Research on Real-Time Recognition and Posture Assessment of Tai Chi Cloud Hands Movement Based on Improved YOLOv7
Main Article Content
Abstract
Traditional Tai Chi Cloud Hands teaching is facing the challenges of frequent arm-crossing and large rhythmic variations, which make it hard for traditional methods to stably track joints and assess posture in real time. In this paper, we design an improved YOLOv7 dual task framework with spatiotemporal attention and human prior knowledge. Firstly, a lightweight coordinate attention mechanism is introduced to improve the perception of occlusion on joint. Secondly, a temporally aligned neck design is implemented. Optical flow is used to fuse inter-frame features and suppress jitter. Then, template geometric constraints are introduced. Sag and arc deviation angles are introduced into loss function for quantitative scoring. Finally, reparameterization and simplification of detection head guarantee real-time application. The experimental results show that our model can achieve an average recall rate of 91.7% for occluded joints, the improvement of 19.6% over the baseline in fully occluded situation, parameter amount of 38.3M, running time of 14. 2ms and correlation coefficient between score and judge of 0.882. This model effectively balances computational efficiency, joint localization accuracy, and professional biomechanical evaluation, providing a robust and feasible framework for the digitized instruction of traditional martial arts. The real-time posture framework can be combined with wearable motion sensors in traditional martial arts training.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
Huang Qiong, “Application Research of Visualization Based on Attitude Estimation in 24 Style Tai Chi Teaching,” Journal of Guangzhou Sport University, vol. 44, no. 1, pp. 1-9, 2024, doi: 10.3969/j.issn.1007-323X.2024.01.001.
X. Feng, X. Lu, and L. Si X, “Taijiquan auxiliary training and scoring based on motion capture technology and DTW algorithm,” International Journal of Ambient Computing and Intelligence, vol. 14, no. 1, pp. 1-15, 2023, doi: 10.4018/IJACI.330539.
Z. Fan and F. Huang, “Tai Chi movement segmentation and recognition on the grounds of multi-sensor data fusion and the DBSCAN algorithm,” Nonlinear Engineering, vol. 14, no. 1, Art. no. 20250151, 2025, doi: 10.1515/NLENG-2025-0151.
N. Yang Q, D. Ji X, and H. Yang X, “Multi-scale feature refined network for human pose estimation,” International Journal of Pattern Recognition and Artificial Intelligence, vol. 37, no. 13, Art. no. 2356022, 2023, doi: 10.1142/S0218001423560220.
H. Jiang J, N. Xia, and Y. Zhou S, “A multi-type feature fusion network based on importance weighting for occluded human pose estimation,” IEEE/CAA Journal of Automatica Sinica, vol. 12, no. 4, pp. 789-805, 2025, doi: 10.1109/JAS.2024.124953.
C. Fu H, W. Gao J, and B. Liu H, “Human pose estimation and action recognition for fitness movements,” Computers & Graphics, vol. 116, pp. 418-426, 2023, doi: 10.1016/j.cag.2023.09.008.
Niu Yue, Wang Annan, and Wu Shengxi, “Attitude estimation based on attention mechanism and cascaded pyramid network,” Journal of East China University of Science and Technology (Natural Science Edition), vol. 49, no. 5, pp. 724-734, 2023, doi: 10.14135/j.cnki.1006-30800.20220715003.
Hou Xiangjun and Chen Yajun, “Human pose estimation algorithm based on improved YOLOv7 Pose,” Journal of Chengdu University of Information Science and Technology, vol. 40, no. 4, pp. 441-445, 2025, doi: 10.16836/j.cnki.jcuit.2022.04.005.
G. Xu and C. Wu X, “Human pose estimation method based on LSA-HRnet and its application in Taijiquan,” Journal of South-Central Minzu University (Natural Science Edition), vol. 42, no. 6, pp. 839-845, 2023, doi: 10.12130/znmdzk.20230608.
Y. Gai D, Y. Feng R, D. Min W, X. Yang, P. Su, Q. Wang, and Q. Han, “Spatiotemporal learning transformer for video-based human pose estimation,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 33, no. 9, pp. 4564-4576, 2023, doi: 10.1109/TCSVT.2023.3269666.
J. Ding, W. Niu S, G. Nie Z, and Y. Zhu W, “Research on human posture estimation algorithm based on YOLO-Pose,” Sensors, vol. 24, no. 10, pp. 3036, 2024, doi: 10.3390/s24103036.
H. Ni Y, H. Wang, X. Mao J, et al., “Quantitative detection of typical bridge surface damages based on global attention mechanism and YOLOv7 network,” Structural Health Monitoring, vol. 24, no. 2, pp. 941-962, 2025, doi: 10.1177/14759217241246953.
F. Xu J, S. Komorita, and K. Kawamura, “FSPose: A heterogeneous framework with fast and slow networks for human pose estimation in videos,” IEICE Transactions on Information and Systems, vol. E106-D, no. 6, pp. 1165-1174, 2023, doi: 10.1587/transinf.2022EDP7182.