Edward P. Fitts Department of Industrial and Systems Engineering, North Carolina State University, Raleigh, NC 27695, USA.
Edward P. Fitts Department of Industrial and Systems Engineering, North Carolina State University, Raleigh, NC 27695, USA.
J Biomech. 2021 Dec 2;129:110860. doi: 10.1016/j.jbiomech.2021.110860. Epub 2021 Nov 8.
Weight lifting is a risk factor of work-related low-back musculoskeletal disorders (MSD). From the ergonomics perspective, it is important to measure workers' body motion during a lifting task and estimate low-back joint moments to ensure the low-back biomechanical loadings are within the failure tolerance. With the recent development of advanced deep neural networks, an increasing number of computer vision algorithms have been presented to estimate 3D human poses through videos. In this study, we first performed a 3D pose estimation of lifting tasks using a single RGB camera and VideoPose3D, an open-source library with a fully convolutional model. Joint angle trajectories and L5/S1 joint moment were then calculated following a top-down inverse dynamic biomechanical model. To evaluate the accuracy of the computer-vision-based angular trajectories and L5/S1 joint moments, we conducted an experiment in which participants performed a variety of lifting tasks. The body motions of the participants were concurrently captured by an RGB camera and a laboratory-grade motion tracking system. The body joint angles and L5/S1 joint moments obtained from the camera were compared with those obtained from the motion tracking system. The results showed a strong correlation (r > 0.9, RMSE < 10°) between the two methods for shoulder flexion, trunk flexion, trunk rotation, and elbow flexion. The computer-vision-based method also yielded a good estimate for the total L5/S1 moment and the L5/S1 moment in the sagittal plane (r > 0.9, RMSE < 20 N·m). This study showed computer vision could facilitate safety practitioners to quickly identify the jobs with high MSD risks through field survey videos.
举重是与工作相关的下背部肌肉骨骼疾病 (MSD) 的危险因素。从人体工程学的角度来看，重要的是测量工人在举重过程中的身体运动，并估计下背部关节力矩，以确保下背部生物力学负荷在耐受范围内。随着先进深度神经网络的最新发展，越来越多的计算机视觉算法已经被提出，通过视频来估计 3D 人体姿势。在这项研究中，我们首先使用单个 RGB 相机和具有全卷积模型的开源库 VideoPose3D 进行了举重任务的 3D 姿势估计。然后，根据自上而下的逆动力学生物力学模型，计算关节角度轨迹和 L5/S1 关节力矩。为了评估基于计算机视觉的角度轨迹和 L5/S1 关节力矩的准确性，我们进行了一项实验，参与者执行了各种举重任务。参与者的身体运动由一个 RGB 相机和一个实验室级别的运动跟踪系统同时捕捉。从相机获得的身体关节角度和 L5/S1 关节力矩与从运动跟踪系统获得的进行了比较。结果表明，两种方法在肩部弯曲、躯干弯曲、躯干旋转和肘部弯曲方面具有很强的相关性 (r>0.9, RMSE<10°)。基于计算机视觉的方法还可以很好地估计总 L5/S1 力矩和矢状面的 L5/S1 力矩 (r>0.9, RMSE<20 N·m)。这项研究表明，计算机视觉可以通过现场调查视频帮助安全从业者快速识别高 MSD 风险的工作。
