Automated Ergonomic Risk Assessment in Offices Using Computer Vision-Based Activity Recognition

Costillo C.M.M.; Zorrilla J.M.M.; Mayhua-Quispe A. · Lecture Notes in Computer Science (2026) · DOI: 10.1007/978-3-032-09044-7_25

Resumen

Occupational health in office environments is a crucial aspect of managing the well-being and productivity of employees. However, despite the abundant research on activities in industrial, domestic, and sports settings, there is a significant gap in the recognition of activities in offices. This study aims to develop a system for analyzing ergonomic risks associated with repetitive actions and postural assessment during labor activities. The system analyzes seated posture and upper-limb activities (e.g., typing and writing) to estimate the subject’s ergonomic risk level. The proposed solution achieved an F1-score of 92.92% in detecting ergonomic risk in postures using EfficientNet, and 99.8% in identifying repetitive actions using the ConvNeXt model. The results suggest that the proposed system is a promising approach for classifying ergonomic risk based on office activities. It is concluded that effective tools exist to support specialists in occupational health, allowing for the personalization of training and improving well-being in the work environment. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

Instituciones: Universidad de Lima