• Do Huu Son Tan Trao University, Viet Nam
  • Dinh Thai Son Hung Vuong University, Phu Tho, Vietnam
  • Luong Thi Thanh Minh ICTU
  • Phan Van Nam Tan Trao University, Viet Nam
  • Te Trung Hieu Tan Trao University, Viet Nam
  • Le Van Hung Tan Trao University, Viet Nam




3D human skeleton, Convolutional, Neural, Networks, Hand action recognition.


Human posture estimation is important research applied in many fields such as human-machine interaction, surveillance, sports anal-ysis, etc. From there, it is possible to build intuitive and practical applications with science, technology and life. Therefore, fast and accurate estimation of human posture is a pre-processing step but very important in the process of building applications. In this paper, we propose to use Mediapipe, which is a Microsoft built-in frame-work for 3D human pose estimation. The test was evaluated against the MADS (Martial Arts, Dancing, and Sports Dataset) database, in which we focused on sports videos such as: basketball, volleyball, football, rugby, tennis and badminton. The average estimate error is between 100-200mm. The 3D human posture estimation results are a good result in supporting sports analysis.


Download data is not yet available.


[1] Y. Lin, X. Jiao, L. Zhao, “Detection of 3D Hu¬man Posture Based on Improved Mediapipe,” Journal of Computer and Communications, 11(02), 102-121, 2023, doi:10.4236/jcc.2023.112008.

[2] S. Radhakrishna, A. Balasubramanyam, “Economical Quaternion Extraction from a Human Skeletal Pose Estimate using 2-D Cameras,” 2023.

[3] S. Radhakrishna, A. Balasubramanyam, “Pedes¬trian Intention Classifier using ID3 Mod¬elled Decision Trees for IoT Edge Devices,” https://arxiv.org/abs/2304.00206, 2023.

[4] V.A.R.Barao, R.C.Coata, J.A.Shibli, M.Bertolini, J.G.S.Souza, “APPLICATIONS OF GOOGLE ME-DIAPIPE POSE ESTIMATION USING A SINGLE CAMERA,” Braz Dent J., 33(1), 1-12, 2022.

[5] J. W. Kim, J. Y. Choi, E. J. Ha, J. H. Choi, “Hu¬man Pose Estimation Using MediaPipe Pose and Op¬timization Method Based on a Humanoid Model,” Applied Sciences (Switzerland), 13(4), 2023, doi:10. 3390/app13042700.

[6] Bazarevsky, V., Grishchenko, I. On-Device, “Real-Time Body Pose Tracking with MediaPipe BlazePose,” Google Research, 2020.

[7] Denavit, J., Hartenberg, R.S, “A kinematic notation for lower-pair mechanisms based on matrices,” Appl. Mech. 1955, 77, 215-221, 1955.

[8] Kim, Tran, Dang, Kang, “Motion and walking stabi¬lization of humanoids using sensory reflex control,” Int. J. Adv. Robot. Syst, 2016.

[9] V. Goldberg, Available online, https://www.vicon.com/, 2021.

[10] J. W. Kim, T. Kim, J. Y. Choi, S. W. Kim, “On the global convergence of univariate dynamic encoding algorithm for searches (uDEAS),” Int. J. Control Au- tom. Syst, 2008.

[11] J. Yun, Choi, J.-W. Kim, S. Kim, “ Automatic detec¬tion of cracks in raw steel block using Gabor filter op¬timized by univariate dynamic encoding algorithm for searches (uDEAS),” NDT E Int, 2009.

[12] E. Kim, M. Kim, S. Kim, J. Kim, “Trajectory gener¬ation schemes for bipedal ascending and descending stairs using univariate dynamic encoding algorithm for searches (uDEAS),” Int. J. Control Autom. Syst, 1061-1071,2010.

[13] J. Kim, H. Ahn, H. Seo, S. Lee, “Optimization of So- lar/Fuel Cell Hybrid Energy System Using the Com¬binatorial Dynamic Encoding Algorithm for Searches (cDEAS),” Energies 2022, 2779, 2022.

[14] D. Goldberg, “Genetic Algorithm in Search, Opti¬mization and Machine Learning,” Addison Wesley: Berkeley, CA, USA, 1999.

[15] J.-W. Kim, T. Kim, Y. Park, S. Kim, “ On load motor parameter identification using univariate dynamic en¬coding algorithm for searches (uDEAS),” IEEE Trans. Energy Convers, 804—-813, 2008.




How to Cite

Đỗ, S., Đinh, S., Lương, M., Phan, N., Tề, H., & Lê, H. (2023). 3D HUMAN POSE ESTIMATION FROM SPORT VIDEOS USING MEDIAPIPE FRAMEWORK. SCIENTIFIC JOURNAL OF TAN TRAO UNIVERSITY, 9(3). https://doi.org/10.51453/2354-1431/2023/975



Natural Science and Technology