CBRRES: a computer-based REBA and RULA evaluation system for musculoskeletal disorder estimation
Mohit Lal et al.
What the paper says
Objectives. This work aimed to design and develop a computerized posture assessment system that utilizes Python and MediaPipe, to calculate rapid entire body assessment (REBA) and rapid upper limb assessment (RULA) scores. The developed system aims to improve the efficiency and accuracy of ergonomic risk evaluations, and provide real-time feedback for immediate corrective action. Methods. The proposed system leverages MediaPipe, an open source machine learning solution pre-trained on pose estimation models to extract key skeletal landmarks from images and video frames. Two distinct approaches were developed, one for upper body posture estimation and another for entire body posture estimation. Results. Posture analysis and REBA/RULA scoring were achieved within 500-700 ms per frame, enabling real-time feedback. An average accuracy of 93% is achieved in estimating joint angles and computing correct ergonomic scores compared to expert humans. The developed algorithm handled a wide range of postures and lighting conditions, indicating strong potential for practical deployment. Conclusions. The proposed posture evaluation system offers a reliable, automated solution for ergonomic risk assessment, marking a significant step toward digital ergonomics. The high accuracy, low latency and ease of integration of the system make it a promising tool for real-time ergonomic monitoring and intervention.
Evidence weight
Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40
| F · citation impact | 0.50 × 0.4 = 0.20 |
| M · momentum | 0.50 × 0.15 = 0.07 |
| V · venue signal | 0.50 × 0.05 = 0.03 |
| R · text relevance † | 0.50 × 0.4 = 0.20 |
† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.