Research progress on model and analysis method of jumping posture in figure skating
DOI:
https://doi.org/10.61173/tvaxym42Keywords:
Figure skating, human posture recognition, multi-view fusionAbstract
This paper reviews the human skeletal dynamics model employed in figure skating pose analysis. The prevailing contemporary technological framework is predicated on the integration of artificial observation assistance, miniature wearable unit data, and dynamic human pose recognition, a suite of technical methodologies. This paper assesses the technical tools and advantages and disadvantages of these three approaches, with a focus on neural network-based multi-fusion 3D pose recognition. Finally, the study offers a discussion of the potential for hardware and software performance improvements to facilitate more accurate analysis of various figure skating models. This, in turn, could guide and train athletes to achieve more difficult movement breakthroughs. Moreover, such improvements could enhance the enjoyment of sports competitions.
References
[1] . anazawa, A., Black, M. J., Jacobs, D. W., & Malik, J. (2018). End-to-end recovery of human shape and pose. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7122-7131).
[2] . King, D. L., Arnold, A. S., & Smith, S. L. (1994). A kinematic comparison of single, double, and triple axels. Journal of Applied Biomechanics, 10(1), 51-60.
[3] . Albert, W. J., & Miller, D. I. (1996). Takeoff characteristics of single and double axel figure skating jumps. Journal of Applied Biomechanics, 12(1), 72-87.
[4] . King, D. L. (2005). Performing triple and quadruple figure skating jumps: implications for training. Canadian Journal of Applied Physiology, 30(6), 743-753.
[5] . Mazurkiewicz, A., Iwańska, D., & Urbanik, C. (2018). Biomechanics of the Axel Paulsen figure skating jump. Polish Journal of Sport and Tourism, 25(2), 3-9.
[6] . Cao, Z., Simon, T., Wei, S. E., & Sheikh, Y. (2017). Realtime multi-person 2d pose estimation using part affinity fields. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7291-7299).
[7] . Lei, P., & Todorovic, S. (2018). Temporal deformable residual networks for action segmentation in videos. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 6742-6751).
[8] . Laptev, I. (2005). On space-time interest points. International journal of computer vision, 64, 107-123.
[9] . Si, C., Chen, W., Wang, W., Wang, L., & Tan, T. (2019). An attention enhanced graph convolutional lstm network for skeleton-based action recognition. In Proceedings of the IEEE/ Dean&Francis Zimeng He CVF conference on computer vision and pattern recognition (pp. 1227-1236).
[10] . Colbeck, S. C., Najarian, L., & Smith, H. B. (1997). Sliding temperatures of ice skates. American Journal of Physics, 65(6), 488-492.
[11] . Hooker, W., & Margulies, G. (1965). The dynamical attitude equations for n-body satellite. Journal of the Astronautical Sciences, 12, 123.
[12] . Yeadon, M. R., Atha, J., & Hales, F. D. (1990). The simulation of aerial movement—IV. A computer simulation model. Journal of biomechanics, 23(1), 85-89.
[13] . Lozowski, E., Szilder, K., & Maw, S. (2013). A model of ice friction for a speed skate blade. Sports Engineering, 16, 239- 253.
[14] . Koga, Y., Nishimura, T., Watanabe, N., Okamoto, K., & Wada, Y. (1997, March). Analysis of motion in speed skating. In International Conference on Experimental Mechanics: Advances and Applications (Vol. 2921, pp. 464-469). SPIE.
[15] . Hettinga, F. J., De Koning, J. J., Schmidt, L. J., Wind, N. A., MacIntosh, B. R., & Foster, C. (2011). Optimal pacing strategy: from theoretical modelling to reality in 1500-m speed skating. British Journal of Sports Medicine, 45(1), 30-35.
[16] . Wang, H., & Schmid, C. (2013). Action recognition with improved trajectories. In Proceedings of the IEEE international conference on computer vision (pp. 3551-3558).
[17] . Peng, X., Wang, L., Wang, X., & Qiao, Y. (2016). Bag of visual words and fusion methods for action recognition: Comprehensive study and good practice. Computer Vision and Image Understanding, 150, 109-125.
[18] . Nakamura, Y., Yamane, K., Fujita, Y., & Suzuki, I. (2005). Somatosensory computation for man-machine interface from motion-capture data and musculoskeletal human model. IEEE Transactions on Robotics, 21(1), 58-66.
[19] . Luinge, H. J., & Veltink, P. H. (2004). Inclination measurement of human movement using a 3-D accelerometer with autocalibration. IEEE Transactions on neural systems and rehabilitation engineering, 12(1), 112-121.
[20] . Leyvand, T., Meekhof, C., Wei, Y. C., Sun, J., & Guo, B. (2011). Kinect identity: Technology and experience. Computer, 44(4), 94-96.
[21] . Iskakov, K., Burkov, E., Lempitsky, V., & Malkov, Y. (2019). Learnable triangulation of human pose. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 7718-7727).
[22] . Pavlakos, G., Zhou, X., Derpanis, K. G., & Daniilidis, K. (2017). Harvesting multiple views for marker-less 3d human pose annotations. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 6988-6997).
[23] . Tian, L., Cheng, X., Honda, M., & Ikenaga, T. (2023). Multi-view 3D human pose reconstruction based on spatial confidence point group for jump analysis in figure skating. Complex & Intelligent Systems, 9(1), 865-879.
[24] . Tome, D., Toso, M., Agapito, L., & Russell, C. (2018, September). Rethinking pose in 3d: Multi-stage refinement and recovery for markerless motion capture. In 2018 international conference on 3D vision (3DV) (pp. 474-483). IEEE.
[25] . Liang, J., & Lin, M. C. (2019). Shape-aware human pose and shape reconstruction using multi-view images. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 4352-4362).
[26] . Ohashi, T., Ikegami, Y., Yamamoto, K., Takano, W., & Nakamura, Y. (2018, October). Video motion capture from the part confidence maps of multi-camera images by spatiotemporal filtering using the human skeletal model. In 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 4226-4231). IEEE.
[27] . Shi, L., Zhang, Y., Cheng, J., & Lu, H. (2019). Skeletonbased action recognition with directed graph neural networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 7912-7921).
[28] . Wen, Y. H., Gao, L., Fu, H., Zhang, F. L., & **a, S. (2019, July). Graph CNNs with motif and variable temporal block for skeleton-based action recognition. In Proceedings of the AAAI conference on artificial intelligence (Vol. 33, No. 01, pp. 8989- 8996).
Downloads
Published
Issue
Section
License
Copyright (c) 2025 by the authors.
This work is licensed under a Creative Commons Attribution 4.0 International License.
