MOPED25: A multimodal dataset of full-body pose and motion in occupational tasks

A systematic literature review of computer vision-based biomechanical models for physical workload estimation

Ergonomic risks, driven by strenuous physical demands in complex work settings, are prevalent across industries. Addressing these challenges through detailed assessment and effective interventions enhances safety and employee well-being. Proper and timely measurement of physical workloads is the initial step towards holistic ergonomic control. This study comprehensively explores existing computer vision-based biomechanical analysis methods for workload assessment, assessing their performance against traditional techniques, and categorising them for easier use. Recent strides in artificial intelligence have revolutionised workload assessment, especially in realistic work settings where conventional methods fall short. However, understanding the accuracy, characteristics, and practicality of computer vision-based methods versus traditional approaches remains limited. To bridge this knowledge gap, a literature review along with a meta-analysis was completed in this study to illuminate model accuracy, advantages, and challenges, offering valuable insights for refined technology implementation in diverse work environments.

Effect of Face Blurring on Human Pose Estimation: Ensuring Subject Privacy for Medical and Occupational Health Applications

The face blurring of images plays a key role in protecting privacy. However, in computer vision, especially for the human pose estimation task, machine-learning models are currently trained, validated, and tested on original datasets without face blurring. Additionally, the accuracy of human pose estimation is of great importance for kinematic analysis. This analysis is relevant in areas such as occupational safety and clinical gait analysis where privacy is crucial. Therefore, in this study, we explore the impact of face blurring on human pose estimation and the subsequent kinematic analysis. Firstly, we blurred the subjects’ heads in the image dataset. Then we trained our neural networks using the face-blurred and the original unblurred dataset. Subsequently, the performances of the different models, in terms of landmark localization and joint angles, were estimated on blurred and unblurred testing data. Finally, we examined the statistical significance of the effect of face blurring on the kinematic analysis along with the strength of the effect. Our results reveal that the strength of the effect of face blurring was low and within acceptable limits (<1°). We have thus shown that for human pose estimation, face blurring guarantees subject privacy while not degrading the prediction performance of a deep learning model.