A Raspberry Pi-based Computer Vision Framework for Automatic Modified-REBA Ergonomic Analysis

International Journal of Electronics and Communication Engineering

© 2026 by SSRG - IJECE Journal

Volume 13 Issue 3

Year of Publication : 2026

Authors : Agus Prijono, Aan Darmawan Hangkawidjaja, R Ratnadewi, Winda Halim, Dasapta Erwin Irawan

10.14445/23488549/IJECE-V13I3P122

How to Cite?

Agus Prijono, Aan Darmawan Hangkawidjaja, R Ratnadewi, Winda Halim, Dasapta Erwin Irawan, "A Raspberry Pi-based Computer Vision Framework for Automatic Modified-REBA Ergonomic Analysis," SSRG International Journal of Electronics and Communication Engineering, vol. 13,  no. 3, pp. 282-291, 2026. Crossref, https://doi.org/10.14445/23488549/IJECE-V13I3P122

Abstract:

The purpose is to automatically evaluate workers’ ergonomic positions in Micro, Small, and Medium Enterprises (MSMEs) using images or video footage. It utilizes the use of ergonomics, computer vision, and Internet of Things (IoT), as well as edge computing with a Raspberry Pi-based technology system. In this research, the methodology involves applying computer vision, mainly on the respective key points of a person’s anatomical structure, in order to determine the “Modified Rapid Entire Body Assessment” (Modified-REBA) Risk Score. The development of the system has taken place via the Python Programming Language, driven by PyQT 5. The development also initially took place through the use of multiple libraries; for example, OpenCV and MediaPipe (BlazePose), and TensorFlow Lite. As for the hardware aspect of the system development, the components that have been used are Raspberry Pi 4B+, ORBBRC 3D Camera, a 1920 x 1080 Monitor, wireless peripherals, and much more. By measuring what the Modified-REBA Risk Score was through this system, it is therefore a viable means of being able to do an Ergonomic Risk Assessment to help MSMEs develop their activities further. By measuring angles through the method of computer vision, the methodology provides a straightforward method for the evaluation of a worker’s posture; however, an accurate result is best obtained through proper imaging. By adding more ergonomic factors, such as time spent and the weight of objects used by employees, improvements could be made to the current process. By utilizing the REBA (Rapid Entire Body Assessment) method as a risk assessment tool for identifying injury risks associated with the various postures used in a given task, appropriate adjustments can be made to decrease potential injury and improve employee safety. The computer vision approach for Modified-REBA development not only provides a useful addition for ergonomic assessment but also satisfies the Sustainable Development Goals (SDG), particularly for developing countries, as MSMEs provide a key contribution to their economies. This research presents a user-friendly system combining software for REBA calculations and hardware (Raspberry Pi and ORBBEC camera) to enable easy ergonomic assessments in MSMEs, allowing direct use of the device with a camera.

Keywords:

Computer-vision, Ergonomics, Modified-REBA, Raspberry-pi, MSMEs, SDGs.

References:

[1] D. Andi Asrida Reskinah, Marhawati Najib, and Muhammad Ashdaq, “Sentiment Analysis on Erspo Jersey in X Using Machine Learning Algorithms,” SAGA: Journal of Technology and Information System, vol. 2, no. 3, pp. 288-294, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Khurram Hameed, Douglas Chai, and Alexander Rassau, “A Comprehensive Review of Fruit and Vegetable Classification Techniques,” Image and Vision Computing, vol. 80, pp. 24-44, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Verena Venek, Wolfgang Kremser, and Thomas Stöggl, “Towards a Live Feedback Training System: Interchangeability of Orbbec Persee and Microsoft Kinect for Exercise Monitoring,” Designs, vol. 5, no. 2, pp. 1-15, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[4] T.A. Aris et al., “Fast k-Means Clustering Algorithm for Malaria Detection in Thick Blood Smear,” 2020 IEEE 10th International Conference on System Engineering and Technology (ICSET), Shah Alam, Malaysia, pp. 267-272, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Guduru Dhanush et al., “A Comprehensive Review of Machine Vision Systems and Artificial Intelligence Algorithms for the Detection and Harvesting of Agricultural Produce,” Scientific African, vol. 21, pp. 1-21, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Nicolas Vignais et al., “Innovative System for Real-Time Ergonomic Feedback in Industrial Manufacturing,” Applied Ergonomics, vol. 44, no. 4, pp. 566-574, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Valentin Bazarevsky et al., “BlazePose: On-device Real-time Body Pose tracking,” arXiv preprint, pp. 1-4, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Vito M. Manghisi et al., “Automatic Ergonomic Postural Risk Monitoring on the Factory Shopfloor -The Ergosentinel Tool,” Procedia Manufacturing, vol. 42, pp. 97-103, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Li Li, Tara Martin, and Xu Xu, “A Novel Vision-Based Real-Time Method for Evaluating Postural Risk Factors Associated with Musculoskeletal Disorders,” Applied Ergonomics, vol. 87, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Work-Related Musculoskeletal Disorders & Ergonomics, 2020. [Online]. Available: https://www.tunemobilechiro.com/wp content/uploads/2020/10/work-related-musculoskeletal-disorders-and-ergonomics.pdf
[11] Aminatus Suhra, Rachmad Hidayat, and Agung Firdausi Ahsan, “Work Posture Analysis with REBA and RULA Method on Production Operators Repair and Maintenance of LPG 3Kg at PT. XYZ,” Romanian Journal of Applied Sciences and Technology, vol. 17, no. 1, pp. 301-306, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Ergonomic Guidelines for Manual Material Handling, The National Institute for Occupational Safety and Health (NIOSH), 2014. [Online]. Available: https://www.cdc.gov/niosh/docs/2007-131/default.html
[13] About Hierarchy of Controls, National Institute for Occupational Safety and Health (NIOSH), CDC, 2024. [Online]. Available: https://www.cdc.gov/niosh/hierarchy-of-controls/about/index.html
[14] Dohyung Kee, “Systematic Comparison of OWAS, RULA, and REBA Based on a Literature Review,” International Journal of Environmental Research and Public Health, vol. 19, no. 1, pp. 1-23, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Osmo Karhu, Pekka Kansi, and Iikka Kuorinka, “Correcting Working Postures in Industry: A Practical Method for Analysis,” Applied Ergonomics, vol. 8, no. 4, pp. 199-201, 1977.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Lynn McAtamney, and E. Nigel Corlett, “RULA: A Survey Method for the Investigation of Work-Related Upper Limb Disorders,” Applied Ergonomics, vol. 24, no. 2, pp. 91-99, 1993.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Sue Hignett, and Lynn McAtamney, “Rapid Entire Body Assessment (REBA),” Applied Ergonomics, vol. 31, no. 2, pp. 201-205, 2000.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Andrew T. Schlussel, and Justin A. Maykel, “Ergonomics and Musculoskeletal Health of the Surgeon,” Clinics in Colon and Rectal Surgery, vol. 32, no. 6, pp. 424-434, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Wenming Cao et al., “Physiological Function Assessment Based on Kinect v2,” IEEE Access, vol. 7, pp. 105638-105651, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Manlio Massiris Fernández et al., “ErgoExplorer: Interactive Ergonomic Risk Assessment from Video Collections,” IEEE Transactions on Visualization and Computer Graphics, vol. 29, no. 1, pp. 43-52, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Ahmed Humadi et al., “In-Field Instrumented Ergonomic Risk Assessment : Inertial Measurement Units Versus Kinect V2,” International Journal of Industrial Ergonomics, vol. 84, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Mark Middlesworth, A Step-by-Step Guide Rapid Entire Body Assessment (REBA), Ergonomics, pp. 1-11, 2014. [Online]. Available: https://ergo-plus.com/wp-content/uploads/REBA-A-Step-by-Step-Guide.pdf
[23] Mangesh Joshi, and Vishwas Deshpande, “Investigative Study and Sensitivity Analysis of Rapid Entire Body Assessment (REBA),” International Journal of Industrial Ergonomics, vol. 79, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Nouha Taleb-Salah et al., “Towards Efficient Ergonomic Optimization in Industry 5.0: The Role of REBA, Motion Capture, and Decision Support Models,” IFAC-PapersOnLine, vol. 59, no. 10, pp. 987-992, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Rijun Liao et al., “A Model-Based Gait Recognition Method with Body Pose and Human Prior Knowledge,” Pattern Recognition, vol. 98, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Pin-Ling Liu, and Chien-Chi Chang, “Simple Method Integrating OpenPose and RGB-D Camera for Identifying 3D Body Landmark Locations in Various Postures,” International Journal of Industrial Ergonomics, vol. 91, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Chao Fan et al., “Computer-Vision Based Rapid Entire Body Analysis (REBA) Estimation,” Modular and Offsite Construction (MOC) Summit Proceedings, Edmonton, Canada, pp. 90-97, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Fakhradin Ghasemi, and Neda Mahdavi, “A New Scoring System for the Rapid Entire Body Assessment (REBA) based on Fuzzy Sets and Bayesian Networks,” International Journal of Industrial Ergonomics, vol. 80, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Woojoo Kim et al., “Ergonomic Postural Assessment using a New Open-Source Human Pose Estimation Technology (OpenPose),” International Journal of Industrial Ergonomics, vol. 84, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Miniar Ben Gamra, and Moulay A. Akhloufi, “A Review of Deep Learning Techniques for 2D and 3D Human Pose Estimation,” Image and Vision Computing, vol. 114, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Ahmad Mwfaq Bataineh, and Ahmad Sufril Azlan Mohamed, “Monocular 3D Human Pose Estimation for REBA Ergonomics : A Critical Review of Recent Advances,” Computers, Materials, & Continua, vol. 84, no. 1, pp. 93-124, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[32] Fajhar Muhammad Ramdhan, Agung Triayudi, and Eri Mardiani, “Implementation of Face Recognition for Lecturer Attendance Using Deep Learning CNN Algorithm,” SaNa: Journal of Blockchain, NFTs and Metaverse Technology, vol. 2, no. 2, pp. 123-130, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[33] Ahmed Jawad A. AlBdairi et al., “Face Recognition Based on Deep Learning and FPGA for Ethnicity Identification,” Applied Sciences, vol. 12, no. 5, pp. 1-15, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[34] Burhan Uddin Chowdhury, “Coffee Leaf Disease Recognition Using Gist Feature,” International Journal of Information Engineering and Electronic Business, vol. 13, no. 2, pp. 55-61, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[35] Detecting Bad Posture With Machine Learning, Towards AI, 2022. [Online]. Available: https://towardsai.net/p/machine learning/detecting-bad-posture-with-machine-learning