An Evaluation of Posture Recognition Based on Intelligent Rapid Entire Body Assessment System for Determining Musculoskeletal Disorders

Li, Ze; Zhang, Ruiqiu; Lee, Ching‐Hung; Lee, Yu‐Chi

doi:10.3390/s20164414

Cited by 32 publications

(19 citation statements)

References 49 publications

(86 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The automatic ergonomic assessment system has been proposed by not only using IMU sensors for the EAWS scale 15 and the RULA 18 but also the vision-based approach for RULA and REBA 17 , 27 , 46 . However, these studies had decided the specific ergonomic assessment method prior to input the information into the automatic assessment system.…”

Section: Discussionmentioning

confidence: 99%

“…Although, in some case of body or object occlusion, the key point derived from OpenPose will lose and causing inaccurate calculation of joint angle 26 . RULA and REBA assessment were also automatically estimated based on the joint angles by using deep learning methods 17 , 27 – 29 . These studies suggest that the estimated joint angles based on OpenPose might be reliable.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic real-time occupational posture evaluation and select corresponding ergonomic assessments

Lin

Chen

et al. 2022

Sci Rep

View full text Add to dashboard Cite

The objective is to develop a system to automatically select the corresponding assessment scales and calculate the score of the risk based on the joint angle information obtained from the imaged process (OpenPose) via image-based motion capture technology. Current occupational assessments, for example, REBA, RULA, and OWAS were used to evaluate the risk of musculoskeletal disorders. However, the assessment result would not be reported immediately. Introducing real-time occupational assessments in different working environments will be helpful for occupational injury prevention. In this study, the decision tree was developed to select the most appropriate assessment method according to the joint angles derived by OpenPose image process. Fifteen operation videos were tested and these videos can be classified into six types including maintenance, handling, assembly, cleaning, office work, and driving. The selected ergonomic assessment method by our developed decision tree in each condition are consistent with the recommendation of the Labour Research Institute. Moreover, the high-risk posture could be identified immediately and provide to the inspector for further evaluation on this posture rather than the whole operation period. This approach provides a quick inspection of the operation movements to prevent musculoskeletal injuries and enhances the application of the scale assessment method in different industrial environments.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automatic real-time occupational posture evaluation and select corresponding ergonomic assessments

Lin

Chen

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Li et al [36] obtained a smaller RMS error of 4.77°. However, they used only images taken from an ideal viewpoint, so no random orientations were included.…”

Section: Discussionmentioning

confidence: 90%

Accuracy Assessment of Joint Angles Estimated from 2D and 3D Camera Measurements

Crombrugge

Sels

Ribbens

et al. 2022

Sensors

View full text Add to dashboard Cite

To automatically evaluate the ergonomics of workers, 3D skeletons are needed. Most ergonomic assessment methods, like REBA, are based on the different 3D joint angles. Thanks to the huge amount of training data, 2D skeleton detectors have become very accurate. In this work, we test three methods to calculate 3D skeletons from 2D detections: using the depth from a single RealSense range camera, triangulating the joints using multiple cameras, and combining the triangulation of multiple camera pairs. We tested the methods using recordings of a person doing different assembly tasks. We compared the resulting joint angles to the ground truth of a VICON marker-based tracking system. The resulting RMS angle error for the triangulation methods is between 12° and 16°, showing that they are accurate enough to calculate a useful ergonomic score from.

show abstract

“…This setting was found to be able to identify the highest number of visually recognisable outliers when using OpenPose. No threshold was set for what was defined as an “outlier”, opting for a visual inspection of the highest number of outliers identified, as observed in similar lower limb investigations [17].…”

Section: Methodsmentioning

confidence: 99%

Validation of two-dimensional video-based inference of finger kinematics with pose estimation

Gionfrida

Rusli

Bharath

et al. 2022

Preprint

View full text Add to dashboard Cite

Accurate capture finger of movements for biomechanical assessments has typically been achieved within laboratory environments through the use of physical markers attached to a participant's hands. However, such requirements can narrow the broader adoption of movement tracking for kinematic assessment outside these laboratory settings, such as in the home. Thus, there is the need for markerless hand motion capture techniques that are easy to use and accurate enough to evaluate the complex movements of the human hand. Several recent studies have validated lower-limb kinematics obtained with a marker-free technique, OpenPose. This investigation examines the accuracy of OpenPose, when applied to images from single RGB cameras, against a 'gold standard' marker-based optical motion capture system that is commonly used for hand kinematics estimation. Participants completed four single-handed activities with right and left hands, including hand abduction and adduction, radial walking, metacarpophalangeal (MCP) joint flexion, and thumb opposition. Accuracy of finger kinematics was assessed using the root mean square error. Mean total active flexion was compared using the Bland–Altman approach, and coefficient of determination of a linear regression. Results showed good agreement for abduction and adduction and thumb opposition activities. Lower agreement between the two methods was observed for radial walking (mean difference between the methods of 5.03°) and MCP flexion (mean difference of 6.82°) activities, due to occlusion. This investigation demonstrated that OpenPose, applied to videos captured with monocular cameras, can be used for markerless motion capture for finger tracking with an error below than 11° and on the order of that which is accepted clinically.

show abstract

An Evaluation of Posture Recognition Based on Intelligent Rapid Entire Body Assessment System for Determining Musculoskeletal Disorders

Cited by 32 publications

References 49 publications

Automatic real-time occupational posture evaluation and select corresponding ergonomic assessments

Automatic real-time occupational posture evaluation and select corresponding ergonomic assessments

Accuracy Assessment of Joint Angles Estimated from 2D and 3D Camera Measurements

Validation of two-dimensional video-based inference of finger kinematics with pose estimation

Contact Info

Product

Resources

About