DOI QR코드

DOI QR Code

An Evaluation Method of Taekwondo Poomsae Performance

  • Thi Thuy Hoang (Department of Electrical and Information Engineering, SeoulTech) ;
  • Heejune Ahn (Department of Electrical and Information Engineering, SeoulTech)
  • Received : 2023.04.27
  • Accepted : 2023.09.26
  • Published : 2023.12.31

Abstract

In this study, we formulated a method that evaluates Taekwondo Poomsae performance using a series of choreographed training movements. Despite recent achievements in 3D human pose estimation (HPE) performance, the analysis of human actions remains challenging. In particular, Taekwondo Poomsae action analysis is challenging owing to the absence of time synchronization data and necessity to compare postures, rather than directly relying on joint locations owing to differences in human shapes. To address these challenges, we first decomposed human joint representation into joint rotation (posture) and limb length (body shape), then synchronized a comparison between test and reference pose sequences using DTW (dynamic time warping), and finally compared pose angles for each joint. Experimental results demonstrate that our method successfully synchronizes test action sequences with the reference sequence and reflects a considerable gap in performance between practitioners and professionals. Thus, our method can detect incorrect poses and help practitioners improve accuracy, balance, and speed of movement.

Keywords

Acknowledgement

This study was supported by the Research Program funded by SeoulTech (Seoul National University of Science and Technology).

References

  1. J. Wang, S. Tan, X. Zhen, S. Xu, F. Zheng, Z. He, and L. Shao, "Deep 3D human pose estimation: A review," in Computer Vision and Image Understanding, vol. 210, p. 103225, Sep. 2021. DOI: 10.1016/j.cviu.2021.103225.
  2. K Kim, and Y. Kim, "Real-time dance evaluation by markerless human pose estimation," Multimedia Tools and Applications, vol. 77, pp. 31199-31220, Jun. 2018. DOI: 10.1007/s11042-018-6068-4
  3. R. Schramm, C. R. Jung, and E. R. Miranda, "Dynamic time warping for music conducting gestures evaluation," IEEE Transactions on Multimedia, vol. 17, no. 2, pp. 243-255, Feb. 2015. DOI: 10.1109/TMM.2014.2377553.
  4. Z. Cao, T. Simon, S-E. Wei, and Y. Sheikh, "Realtime multi-person 2d pose estimation using part affinity fields," in Proceedings of the IEEE conference on computer vision and pattern recognition, Honolulu, USA, pp. 7291-7299, 2017. DOI: 10.1109/cvpr.2017.143.
  5. M. Kocabas, N. Athanasiou, and M. J. Black, "Vibe: Video inference for human body pose and shape estimation," in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Seattle, WA, USA, pp. 5252-5262, 2020. DOI: 10.1109/CVPR42600.2020.00530.
  6. H. Choi, G. Moon, J. Y. Chang, and K. M. Lee, "Beyond static features for temporally consistent 3d human pose and shape from a video," in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Nashville, USA, pp. 1964-1973, 2021. DOI: 10.1109/CVPR46437.2021.00200. 
  7. M. Loper, N. Mahmood, J. Romero, G. Pons-Moll, and M. J. Black, "SMPL: A skinned multi-person linear model", ACM transactions on graphics (TOG), vol. 34, no. 6, pp. 1-16, Nov. 2015. DOI:10.1145/2816795.2818013.
  8. K. Iskakov, E. Burkov, V. Lempitsky, and Y. Malkov, "Learnable triangulation of human pose," in Proceedings of the IEEE/CVF international conference on computer vision (ICCV), Seoul, Korea, pp. 7717-7726, 2019. DOI: 10.1109/ICCV.2019.00781.
  9. S. Chun, S. Park, and J. Y. Chang, "Learnable human mesh triangulation for 3D human pose and shape estimation," in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA, pp. 2849-2858, 2023. DOI: 10.1109/WACV56688.2023.00287.
  10. H. Dai, B. Cai, J. Song, and D. Zhang, "Skeletal animation based on BVH motion data," in 2010 2nd International Conference on Information Engineering and Computer Science, Wuhan, China, pp. 1-4, 2010. DOI: 10.1109/ICIECS.2010.5678292.
  11. T. Hachaj, M. R. Ogiela, and K. Koptyra, "Application of assistive computer vision methods to Oyama karate techniques recognition," Symmetry, vol. 7, no. 4, pp. 1670-1698, Sep. 2015. DOI: 10.3390/sym7041670.
  12. KCISA, Taekwondo Poomsae 3D data, 2020. [Online], Available: https://www.kcisa.