Abstract
In the training of sports, video-based motion analysis is important to automatically capture the action of trainees and provide training suggestions. Focusing on the dragon boating which mainly involves periodic rowing actions, this paper proposes a motion analysis method by comparing the action patterns of the athletes in the video and the expert athletes. First, taking a dragon boating video as input, the key points of human body of the dragon boat athlete in every frame are extracted with the deep convolutional neural network HRNET. Second, the extracted key points of athlete’s body are constructed as a sequence to represent the motion of human body, and a mathematical analysis method is designed to obtain the related action parameters. Third, the parameters are compared with the standard actions of expert athletes to give the advice for action correction. Experimental results demonstrate that the proposed method can provide reliable suggestions for dragon boat athletes, which is robust to individual differences and non-uniform resolutions caused by different videos.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Rogez, G., Rihan, J., Ramalingam, S., et al.: Randomized trees for human pose detection. In: IEEE Conference on Computer Vision & Pattern Recognition, pp. 1–8 (2008)
Urtasun, R., Darrell, T.: Sparse probabilistic regression for activity-independent human pose inference. In: IEEE Conference on Computer Vision & Pattern Recognition, pp. 149–156 (2008)
Hu, G.: Research of Human Pose Estimation Based on Pictorial Structure Models. Wuhan University of Technology (2014)
Sun, K., Xiao, B., Liu, D., et al.: Deep high-resolution representation learning for human pose estimation. IEEE Conference on Computer Vision & Pattern Recognition, pp. 5686–5696 (2019)
Qiong-zhu, G., Feng, C.: Sports biomechanical analysis of landing stability of maneuvers in women’s Wushu. J. Wuhan Inst. Phys. Educ. 44(6), 48–52 (2010)
Sun, X., Xiao, B., Wei, F., et al.: Integral Human Pose Regression. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision – ECCV 2018. Lecture Notes in Computer Science, vol. 11210, pp. 536–553. Springer, Cham (2018)
Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) Computer Vision – ECCV 2016. Lecture Notes in Computer Science, vol. 9912, pp. 483–499. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46484-8_29
Luvizon, D.C., Tabia, H., Picard, D.: Human pose regression by combining indirect part detection and contextual information. Comput. Graph. 85, 15–22 (2017)
Li, S., Liu, Z.Q., Chan, A.B.: Heterogeneous multi-task learning for human pose estimation with deep convolutional neural network. Int. J. Comput. Vis. 113(1), 19–36 (2015)
Fang, H.S., Xie, S., Tai, Y.W., et al.: RMPE: regional multi-person pose estimation. In: IEEE International Conference on Computer Vision, pp. 2353–2362 (2017)
He, K., Georgia, G., Piotr, D., et al.: Mask R-CNN. In: IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)
Chen, Y., Wang, Z., Peng, Y., et al.: Cascaded pyramid network for multi-person pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7103–7112 (2017)
Cao, Z., Simon, T., Wei, S.E., et al.: Realtime multi-person 2D pose estimation using part affinity fields. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1302–1310 (2017)
Pishchulin, L., Insafutdinov, E. Tang, S., et al.: DeepCut: joint subset partition and labeling for multi person pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4929–4937 (2016)
Sheng-nan, J., En-qing, C., Ming-yao, Z., et al.: Human action recognition based on ResNeXt. J. Graph. 41(2), 277–282 (2020)
Li, Y.: Abnormal Behavior Detection Based on Head Movement Analyze in Examination Room. Changchun University of Science and Technology (2018)
Zhu Jian-bao, X., Zhi-long, SY.-w., et al.: Detection of dangerous behaviors in power stations based on OpenPose multi-person attitude recognition. Autom. Instrum. 35(2), 47–51 (2020)
Li, K.: Capture, Recognition and Analysis of Badminton Players Swing. University of Electronic Science and Technology of China (2020)
Ji, Y.: The Research on Golf Swing Action Comparison Based on Video Human Body Pose Estimation. Nanjing University of Posts and Telecommunications (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Xu, C., Wu, Z., Wu, B., Tan, Y. (2021). Motion Analysis for Dragon Boat Athlete Using Deep Neural Networks. In: Pan, L., Pang, S., Song, T., Gong, F. (eds) Bio-Inspired Computing: Theories and Applications. BIC-TA 2020. Communications in Computer and Information Science, vol 1363. Springer, Singapore. https://doi.org/10.1007/978-981-16-1354-8_26
Download citation
DOI: https://doi.org/10.1007/978-981-16-1354-8_26
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-1353-1
Online ISBN: 978-981-16-1354-8
eBook Packages: Computer ScienceComputer Science (R0)