期刊
IEEE TRANSACTIONS ON HUMAN-MACHINE SYSTEMS
卷 51, 期 6, 页码 734-739出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/THMS.2021.3112962
关键词
Cameras; Videos; Pose estimation; Estimation error; Computer vision; Wrist; Task analysis; Asymmetry angle; manual lifting; NIOSH lifting equation; three-dimensional (3-D) skeletal joints estimation; video monitoring
资金
- NIOSH [5D30118P01249]
A computer vision-based approach was developed to estimate the load asymmetry angle in the revised NIOSH lifting equation, utilizing 2-D and 3-D joint location detection. A robust angle estimation method was developed, along with a technique to flag unreliable angle estimates.
A robust computer vision-based approach is developed to estimate the load asymmetry angle defined in the revised NIOSH lifting equation. The angle of asymmetry enables the computation of a recommended weight limit for repetitive lifting operations in a workplace to prevent lower back injuries. An open-source package OpenPose is applied to estimate the two-dimensional (2-D) locations of skeletal joints of the worker from two synchronous videos. Combining these joint location estimates, a computer vision correspondence and depth estimation method is developed to estimate the 3-D coordinates of skeletal joints during lifting. The angle of asymmetry is then deduced from a subset of these 3-D positions. Error analysis reveals unreliable angle estimates due to occlusions of upper limbs. A robust angle estimation method that mitigates this challenge is developed. We propose a method to flag unreliable angle estimates based on the average confidence level of 2-D joint estimates provided by OpenPose. An optimal threshold is derived that balances the percentage variance reduction of the estimation error and the percentage of angle estimates flagged. Tested with 360 lifting instances in a NIOSH-provided dataset, the standard deviation of angle estimation error is reduced from 10.13 degrees to 4.99 degrees. To realize this error variance reduction, 34% of estimated angles are flagged and require further validation.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据