Posture recognition and correction of five step fist based on OpenPose

Abstract

The network video training mode of five step fist has become the mainstream training mode at present, because it is not limited by time and region. However, there are also some problems, such as irregular movements of practitioners, due to the influence of subjective human eyes, which will damage their health. Therefore, this paper proposes a pose recognition and correction method of the five step fist based on OpenPose. By identifying the standard movements and the movements of the practitioners, the key points are extracted, the deviation and similarity between the practitioners and the standards are calculated, and the corresponding correct and effective correction suggestions are given. These works can provide strong technical support for the training and cultural dissemination of the five step fist.

Keywords

A

References

[1] Chen G. An interpretable composite CNN and GRU for fine-grained martial arts motion modeling using big data analytics and machine learning. Soft computing. 2024, 28(3): 2223-2243. J]

[2] Pang Y, Zhang K, Li F. Explainable quality assessment of effective aligned skeletal representations for martial arts movements by multi-machine learning decisions. Scientific reports. 2025, 15(1): 323. J]

[3] Zhang Z. Basic theory of Chinese Wushu. 2008, Beijing, People’s Sports Press[M]

[4] Liu H. Research on teaching strategy of Wushu five step fist in elementary school under the perspective of teaching content with learning and practicing method. Youth sports. 2022, 7: 106-107[J]

[5] Li Y. Research on the construction of micro-specialized Wushu curriculum in Shanghai universities-taking Shanghai Normal University as an example. 2023, Shanghai, Shanghai Normal University000610[D]

[6] Zhang J, Gu F M, Ding J L. Research on the design and application of SPOC-based martial arts teaching-taking five step fist as an example. Journal of Tongling College. 2020, 1903120-123[J]

[7] Zhao Z. The current situation of the development of five step fist teaching in some secondary schools in Hengyang city and a survey study. Boxing and fighting. 2019, 2: 32[J]

[8] Nani G V, Sibanda L. Online home schooling: are parents ready? lessons from the corona virus disease induced lock down. Randwick international research and analysis institute. 2020, 1(2): 140-151[J]

[9] Ni L. Optimizing online learning resources to empower cloud-based physical education learning and practicing taking the fourth grade “movement combination (I): five step fist” learning unit as an example. Shanghai education. 2022, Z2: 131-132[J]

[10] Liu Y M, Guo L, Guo Q. Retracted article: dynamic light collection system based on human posture estimation application in martial arts action teaching simulation. Optical and quantum electronics. 2024, 563376. J]

[11] Liu L, Dai Y, Liu Z. Real-time pose estimation and motion tracking for motion performance using deep learning models. Journal of intelligent systems. 2024, 33120230288. J]

[12] Chen Y. A Wushu leg gesture recognition algorithm based on random forest and bone feature extraction (RF-SFE). International journal of high speed electronics and systems. 2024, 6: 2540066[J]

[13] Le V H. 3-D human pose estimation in traditional martial art videos. International journal of machine learning and computing. 2020, 102358-367[J]

[14] XIANG H. Lightweight open pose based body posture estimation for badminton players[J]. Forest chemicals review, 2022: 339–350.

[15] Fukushima T, Haggenmueller K, Lames M. Validity of OpenPose key point recognition and performance analysis in taekwondo. International Symposium on Computer Science in Sport, September 27–30, 2023, Hangzhou, China. 2023, Singapore, Springer68-76[C]

[16] Lu F. Aishifu: AI karate pose trainer using human pose estimation. Journal of student research. 2023, 12(3): 1-11. J]

[17] Li Z. A method for recognizing wrong actions of martial arts athletes based on keyframe extraction. International journal of biometrics. 2024, 16(3–4): 256-271. J]

[18] Chen W, Jiang Z, Guo Het al. . Fall detection based on key points of human-skeleton using OpenPose. Symmetry. 2020, 12(5): 744. J]

[19] Wu Y, Zhang T, Niu Jet al. . YOLO-based lightweight traffic sign detection algorithm and mobile deployment. Optoelectronics letters. 2025, 214249-256. J]

[20] Yan P L, Zhang Y H. Retracted article: application of light sensors based on reinforcement learning in martial arts action optimization and image defect detection. Optical and quantum electronics. 2024, 564498. J]

RIGHTS & PERMISSIONS

Tianjin University of Technology