Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Journal of Engineering Mechanics and Machinery
  4. Vol 10, Issue 2, 2025

Development of A Sitting Posture Health Detection System Based on the Centernet Model

Download as PDF

DOI: 10.23977/jemm.2025.100203 | Downloads: 0 | Views: 26

Author(s)

Laihong Zhu 1, Yihe Zhu 2

Affiliation(s)

1 Haojing College of Shanxi University of Science and Technology, Xi'an, Shaanxi, 712046, China
2 School of Mechanical Engineering, Northwestern Polytechnical University, Xi'an, Shaanxi, 710129, China

Corresponding Author

Laihong Zhu

ABSTRACT

At present, health problems caused by poor sitting posture have attracted much attention, especially affecting specific groups such as students and office workers not only causing physical health problems such as spinal curvature and cervical pain, but also triggering psychological problems such as anxiety and fatigue. Compared with traditional sitting posture detection methods, this paper proposes non-contact sitting posture detection system based on machine vision, which can capture sitting posture information in real time, accurately and conveniently, and helps to improve sitting posture habits and prevent health. Based on the lightweight human pose estimation model MoveNet under the CenterNet model, this model classifies the pose information (the coordinates of the 17 key points of the body) output by MoveNet to judge which sitting posture state the person in the picture is in. The application of this technology can help people correct bad sitting habits in time, reducing the occurrence of problems such as myopia, spinal diseases, and muscle stiffness and fatigue, and improving physical health. This system verifies the feasibility, stability, and accuracy of sitting posture detection system based on the CenterNet model. The test results show that this system can recognize the user's sitting posture state in real time and accurately, and give corresponding and suggestions, which improves the user's physical and mental health problems, and provides a solution for the future sitting posture health monitoring field.

KEYWORDS

Sitting Posture Health; Centernet Model; Fully Connected Neural Network Model

CITE THIS PAPER

Laihong Zhu, Yihe Zhu, Development of A Sitting Posture Health Detection System Based on the Centernet Model. Journal of Engineering Mechanics and Machinery (2025) Vol. 10: 15-22. DOI: http://dx.doi.org/10.23977/jemm.2025.100203.

REFERENCES

[1] Gebreyesus Tsiwaye, Nigussie Kalkidan, et al. The prevalence and risk factors of work-related musculoskeletal disorders among adults in Ethiopia: a study protocol for extending a systematic review with meta-analysis of observational studies [J]. Systematic reviews, 2020, 9(1): 103-117. 
[2] Wu Lei, Wang Shuai, Liao Haoran, Wu Qingming, Zhu Changcai, Guo Zhenzhong. Quantitative analysis method for risk factors of occupational musculoskeletal disorders. Chinese Journal of Industrial Hygiene and Occupational Diseases. 2018,36(04):318-320.
[3] Egern Matthias, Aasa Ulrika, Äng Björn O, et al. Musculoskeletal disorders and their associations with health- and-related factors: a cross-sectional comparison between Swedish air force personnel and army soldiers. [J]. BMC musculoskeletal disorders, 200, 21(1): 161-175. 
[4] Oakman Jodi, Kinsman Natasha. Barriers to more effective of work-related musculoskeletal and mental health disorders. [J]. Applied ergonomics, 2019, 75: 6674. 
[5] Sun Qian, Hu Bo, Chen Shengxiong, Huang Lin, Hu Hao, Liao Yuanpeng. Analysis of risk factors for occupational musculoskeletal diseases among office clerks [J]. Occupational Health and Emergency Rescue. 2020,38(03):233-237.
[6] Shi Ping, Li Wei, Wang Weimin, Yu Hongliu, Liu. A Portable Decubitus Ulcer Prevention System Based on Pressure Distribution Detection [J]. Biomedical Engineering & Clinical, 2020, 24(3): 233-238. 
[7] Du Yinju, Du Guiying, Zhang Furen, et al. Analysis of the situation cervical spondylosis in primary and secondary school students in Liaocheng City [J]. Chinese Journal of School Health. 2006(4): 339-340. 
[8] Wang Chunyang. Analysis of the Current Situation of Posture Survey among Adolescents in [J]. Sports Teacher and Friend, 2018, 41(01): 44-46. 
[9] Wangm, Chen Hl. Chaotic multi-swarm whale optimizer boosted support vector machine formed medical diagnosis [J]. Applied Soft Computing, 2020, 8. 
[10] Ma Zhaolong, Qiu Yong, Wang Bin, Zhu Zezhang, et al. Spinal cord and vertebral malations in patients with congenital scoliosis [J]. Chinese Journal of Spine and Spinal Cord, 2007, 17(8):588-592 
[11] Jia Yunde. Machine Vision [M]. Beijing: Science Press, 2004: 1-4. 
[12] Min Weidong, Cui Hao, Han Qing, et al. A Scene Recognition and Semantic Analysis Approach to Unhealthyitting Posture Detection during Screen Reading [J]. Sensors, 2018, 18(9): 3119-3129.
[13] Zhou Yu. Design and Implementation of a Posture Monitoring System Based on Machine Learning [D]. Zhejiang University, 2018.
[14] Ma Yehan. Design and Implementation of an Office Health Analysis System Based on Kinect [D]. Harbin Institute of Technology, 2015.

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.