Predicting Sagittal Plane Lifting Postures From Image Bounding Box Dimensions
Authors:
- Runyu L. GreeneRGRunyu L. Greene
- Yu Hen HuYHYu Hen Hu
- Nicholas DifrancoNDNicholas Difranco
- Stephen BaoSBStephen Bao
- Robert G. RadwinRRRobert G. Radwin
- 9 August 2018
- journal article
- research article
- Published by SAGE Publications in Human Factors: The Journal of the Human Factors and Ergonomics Society
- Vol. 61 (1) , 64-77
Abstract
Objective: A method for automatically classifying lifting postures from simple features in video recordings was developed and tested. We explored if an “elastic” rectangular bounding box, drawn tightly around the subject, can be used for classifying standing, stooping, and squatting at the lift origin and destination. Background: Current marker-less video tracking methods depend on a priori skeletal human models, which are prone to error from poor illumination, obstructions, and difficulty placing cameras in the field. Robust computer vision algorithms based on spatiotemporal features were previously applied for evaluating repetitive motion tasks, exertion frequency, and duty cycle. Methods: Mannequin poses were systematically generated using the Michigan 3DSSPP software for a wide range of hand locations and lifting postures. The stature-normalized height and width of a bounding box were measured in the sagittal plane and when rotated horizontally by 30°. After randomly ordering the data, a classification and regression tree algorithm was trained to classify the lifting postures. Results: The resulting tree had four levels and four splits, misclassifying 0.36% training-set cases. The algorithm was tested using 30 video clips of industrial lifting tasks, misclassifying 3.33% test-set cases. The sensitivity and specificity, respectively, were 100.0% and 100.0% for squatting, 90.0% and 100.0% for stooping, and 100.0% and 95.0% for standing. Conclusions: The tree classification algorithm is capable of classifying lifting postures based only on dimensions of bounding boxes. Applications: It is anticipated that this practical algorithm can be implemented on handheld devices such as a smartphone, making it readily accessible to practitioners.Keywords
Funding Information
- National Institute for Occupational Safety and Health (R01OH011024)
This publication has 30 references indexed in Scilit:
- Risk factors for work‐related musculoskeletal disorders: a systematic review of recent longitudinal studiesAmerican Journal of Industrial Medicine, 2009
- Lower extremity joint kinetics and lumbar curvature during squat and stoop liftingBMC Musculoskeletal Disorders, 2009
- Digital Human Modeling for Workspace DesignReviews of Human Factors and Ergonomics, 2008
- Quantifying repetitive hand activity for epidemiological research on musculoskeletal disorders – Part II: comparison of different methods of measuring force level and repetitivenessErgonomics, 2006
- Toward a Quantitative Definition of Manual Lifting PosturesHuman Factors: The Journal of the Human Factors and Ergonomics Society, 1997
- Posture prediction for static sagittal-plane liftingJournal of Biomechanics, 1996
- Biomechanical risk factors for occupationally related low back disordersErgonomics, 1995
- A video-based system for acquiring biomechanical data synchronized with arbitrary events and activitiesIEEE Transactions on Biomedical Engineering, 1995
- The Role of Dynamic Three-Dimensional Trunk Motion in Occupationally-Related Low Back DisordersSpine, 1993
- Low Back and Neck/Shoulder Pain in Construction WorkersSpine, 1992