Computer-Vision-Enabled Worker Video Analysis for Motion Amount Quantification
This work addresses the challenge of real-time motion monitoring for physical workers to improve ergonomic safety, representing an incremental application of existing computer vision methods to a specific domain.
This paper tackles the problem of monitoring and assessing physical worker motions by introducing a framework that tracks and quantifies upper and lower limb motions using joint position data and Hotelling's T^2 statistic, with results showing a correlation between motion warnings and workload ratings (r=0.218, p=0.0024) and a Random Forest model achieving up to 94% accuracy in identifying ergonomic risks.
The performance of physical workers is significantly influenced by the extent of their motions. However, monitoring and assessing these motions remains a challenge. Recent advancements have enabled in-situ video analysis for real-time observation of worker behaviors. This paper introduces a novel framework for tracking and quantifying upper and lower limb motions, issuing alerts when critical thresholds are reached. Using joint position data from posture estimation, the framework employs Hotelling's $T^2$ statistic to quantify and monitor motion amounts. A significant positive correlation was noted between motion warnings and the overall NASA Task Load Index (TLX) workload rating (\textit{r} = 0.218, \textit{p} = 0.0024). A supervised Random Forest model trained on the collected motion data was benchmarked against multiple datasets including UCF Sports Action and UCF50, and was found to effectively generalize across environments, identifying ergonomic risk patterns with accuracies up to 94\%.