ERGOAI: GESTURE MONITORING TO PREVENT REPETITIVE STRAIN INJURIES USING STANDARD CAMERAS

Abstract

Repetitive Strain Injuries (RSI) and Work-related Musculoskeletal Disorders (WMSDs) pose serious challenges to health in today's workplaces. This paper introduces ErgoAI, an innovative computer vision system designed to help identify and prevent RSI through real-time analysis of human movement. By using advanced pose estimation technology, ErgoAI captures detailed information about how people move using regular RGB cameras. It then processes this data into useful joint angles that align with recognized ergonomic assessment methods, specifically the Rapid Upper Limb Assessment (RULA) and the Rapid Entire Body Assessment (REBA). With its combination of high-quality feature analysis and smart classification techniques, ErgoAI can identify risky postures with an impressive recall rate of 95.8%, all while still being able to process information in real time. The system performs well across a variety of different work situations and delivers instant feedback about potential risks through an easy-to-use web interface. Testing has shown that ErgoAI is effective for continuous monitoring of ergonomic conditions, offering a practical solution for preventing workplace injuries without the need for specialized motion capture equipment.