Abstract
With the rapid advancements in artificial intelligence and computer vision technology, the field of visual-based human pose detection has emerged as a highly sought-after research area in recent years. The identification of human poses has practical applications in diverse domains, ranging from motion-sensing games for human-computer interaction to activity prediction and medical rehabilitation. The present study is focused on the utilization of human pose detection for fitness movement counting. The ultimate aim of the system design is to accurately detect the skeletal key points of each body part in the image and subsequently connect them to form a human pose skeleton, which serves as a vital representation of the characteristics of human motion, particularly in the context of video data, where multiple human poses can be linked to form a certain movement trajectory. By judging the trajectory and angle changes, the system can determine whether people's fitness movements are correct and help them improve their fitness effectiveness. Hence, an increasing number of researchers are investing time and effort in this field. One common approach for human pose detection is OpenPose, but this model has a large and complex structure and low detection accuracy. Therefore, this fitness movement detection and counting system uses a lightweight MediaPipe model and improves it to enhance the algorithm's accuracy and recognition speed. The specific work in this paper includes three main points: (1) a suitable network structure to detect human skeletal points; (2) the appropriate skeletal structure for fitness movements through experiments to obtain accurate results; and (3) a Qt interface for human-computer interaction.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Liu, Y., Xiong, X., Lin, P.: Warning of dangerous operations of port container crane operators based on active human posture recognition. Cranes Transport Mach. 24, 15–20 (2022)
Sheng, Y., Wang, J.: Research on human body posture recognition based on computer vision. Mod. Inform. Technol. 6(16), 87–91+95 (2022)
Jin, W., Meng, J., Huang, Y.: Medical human body posture recognition method based on CNN and high-speed communication technology. J. Microcomput. Appl. 38(07), 20–22+26 (2022)
Han, K., Huang, Z.: Falling behavior recognition method based on dynamic characteristics of human body posture. J. Hunan Univ. (Natl. Sci.) 47(12), 69–76 (2020)
Qian, Y., Shen, Y.: Hybrid of pose feature and depth feature for action recognition in static image. Acta Automatica Sinica 45(03), 626–636 (2019)
Zheng, X., Peng, X., Wang, J.: Human action recognition based on pose spatio-temporal features. J. Comput. Aided Design Comput. Graph. 30(09), 1615–1624 (2018)
Ge, D.: Application of human body posture recognition technology in intelligent control system of smart substation. Electric Eng. 13, 132–134 (2022)
Chai, D., Xu, C., He, J.: Inception neural network for human activity recognition using wearable sensor. J. Commun. 38(Z2), 122–128 (2017)
Wei, X.: Human body posture recognition algorithm based on inertial sensors. Intell. Comput. Appl. 12(06), 97–101+105 (2022)
Liu, J., Liu, Y., Jia, X.: Research on human pose visual recognition algorithm based on model constraints 41(04), 208–217 (2020)
Zheng, L., Huang, X., Liang, R.: Human posture recognition method based on SVM. J. Zhejiang Univ. Technol. 40(06), 670–675+691 (2012)
Sun, J., Han, S., Shen, Z.: Binocular human body posture distance positioning recognition based on double convolution Chain. Acta Armamentarii 43(11), 2846–2854 (2022)
Huang, G., Li, Y.: A survey of human action and pose recognition. Comput. Knowl. Technol. 9(01), 133–135 (2013)
Sun, Z., Li, H., Ye, J.: 3D human body joint recognition based on weakly supervised transfer network. J. Jilin Univ. (Eng. Technol. Edn) 1–9 (2023)
Yang, G.: Design and implementation of human posture recognition system based on deep learning. China’s New Technol. New Prod. 07, 22–24 (2022)
Duan, J., Liang, M., Wang, R.: Human pose recognition based on human bone point detection and multi-layer perceptron. Electron. Measure. Technol. 43(12), 168–172 (2020)
Guo, X., Zhang, L.: Research and implementation of human body posture feature selection method. Comput. Eng. 37(04), 184–186 (2011)
Li, Y.: Research on human posture recognition based on acceleration sensor. Electron. Compon. Inform. Technol. 6(03), 1–3+6 (2022)
Zhou, K.: Fitness motion recognition system based on deep learning. Indust. Control Comput. 34(06), 37–39 (2021)
Ma, Z., Lin, Y., Wang, Z.: Human posture recognition and fighting behavior monitoring in closed environments. Comput. Appl. 41(S2), 214–220 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chen, Y., Liu, X. (2023). Design of Fitness Movement Detection and Counting System Based on MediaPipe. In: Yu, Z., et al. Data Science. ICPCSEE 2023. Communications in Computer and Information Science, vol 1880. Springer, Singapore. https://doi.org/10.1007/978-981-99-5971-6_6
Download citation
DOI: https://doi.org/10.1007/978-981-99-5971-6_6
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-5970-9
Online ISBN: 978-981-99-5971-6
eBook Packages: Computer ScienceComputer Science (R0)