Automation of Workplace Lifting Hazard Assessment for Musculoskeletal Injury Prevention

Annals of Occupational and Environmental Medicine

June T Spector⁴  Max Lieblich³  Stephen Bao¹  Kevin McQuade⁵  Margaret Hughes² 

[1] Safety and Health Assessment and Research for Prevention (SHARP) Program, Washington State Department of Labor and Industries, Olympia, WA, USA

[2] Department of Environmental & Occupational Health Sciences, University of Washington, 4225 Roosevelt Way NE, Suite 100, Seattle, WA 98105, USA

[3] Department of Mathematics, University of Washington, Seattle, WA, USA

[4] Department of Medicine, University of Washington, 4225 Roosevelt Way NE, Suite 100, Seattle, WA 98105, USA

[5] Department of Rehabilitation Medicine, University of Washington, Seattle, WA, USA

关键词: Work-related musculoskeletal disorders;    Prevention;    NIOSH lifting equation;    Musculoskeletal hazard assessment;    Microsoft Kinect;    Ergonomics;    Depth camera;    Back pain;    Back injury;   

Others  :  790429
DOI  :  10.1186/2052-4374-26-15

 received in 2014-04-30, accepted in 2014-06-12,  发布年份 2014

【 摘 要 】

Objectives

Existing methods for practically evaluating musculoskeletal exposures such as posture and repetition in workplace settings have limitations. We aimed to automate the estimation of parameters in the revised United States National Institute for Occupational Safety and Health (NIOSH) lifting equation, a standard manual observational tool used to evaluate back injury risk related to lifting in workplace settings, using depth camera (Microsoft Kinect) and skeleton algorithm technology.

Methods

A large dataset (approximately 22,000 frames, derived from six subjects) of simultaneous lifting and other motions recorded in a laboratory setting using the Kinect (Microsoft Corporation, Redmond, Washington, United States) and a standard optical motion capture system (Qualysis, Qualysis Motion Capture Systems, Qualysis AB, Sweden) was assembled. Error-correction regression models were developed to improve the accuracy of NIOSH lifting equation parameters estimated from the Kinect skeleton. Kinect-Qualysis errors were modelled using gradient boosted regression trees with a Huber loss function. Models were trained on data from all but one subject and tested on the excluded subject. Finally, models were tested on three lifting trials performed by subjects not involved in the generation of the model-building dataset.

Results

Error-correction appears to produce estimates for NIOSH lifting equation parameters that are more accurate than those derived from the Microsoft Kinect algorithm alone. Our error-correction models substantially decreased the variance of parameter errors. In general, the Kinect underestimated parameters, and modelling reduced this bias, particularly for more biased estimates. Use of the raw Kinect skeleton model tended to result in falsely high safe recommended weight limits of loads, whereas error-corrected models gave more conservative, protective estimates.

Conclusions

Our results suggest that it may be possible to produce reasonable estimates of posture and temporal elements of tasks such as task frequency in an automated fashion, although these findings should be confirmed in a larger study. Further work is needed to incorporate force assessments and address workplace feasibility challenges. We anticipate that this approach could ultimately be used to perform large-scale musculoskeletal exposure assessment not only for research but also to provide real-time feedback to workers and employers during work method improvement activities and employee training.

【 授权许可】

   
2014 Spector et al.; licensee BioMed Central Ltd.

【 图 表 】

Figure 1.

Figure 2.

Figure 3.

【 参考文献 】

• [1]National Research Council and the Institute of Medicine: Musculoskeletal Disorders and the Workplace: Low Back and Upper Extremities. Washington, DC: Panel on Musculoskeletal Disorders and the Workplace. Commission on Behavioral and Social Sciences and Education; 2011.
• [2]Dutta T: Evaluation of the Kinect™ sensor for 3-D kinematic measurement in the workplace. Appl Ergon 2012, 43:645-649.
• [3]Silverstein BA, Bao SS, Fan ZJ, Howard N, Smith C, Spielholz P, Bonauto D, Viikari-Juntura E: Rotator cuff syndrome: Personal, work-related psychosocial and physical load factors. J Occup Environ Med 2008, 50:1062-1076.
• [4]Fan ZJ, Silverstein BA, Bao S, Bonauto DK, Howard NL, Spielholz PO, Smith CK, Polissar NL, Viikari-Juntura E: Quantitative exposure-response relations between physical workload and prevalence of lateral epicondylitis in a working population. Am J Ind Med 2009, 52:479-490.
• [5]Bao S, Howard N, Spielholz P, Silverstein B, Polissar N: Interrater reliability of posture observations. Hum Factors 2009, 51:292-309.
• [6]Bao S, Howard N, Spielholz P, Silverstein B: Inter-observer reliability of forceful exertion analysis based on video-recordings. Ergonomics 2010, 53:1129-1139.
• [7]American Conference of Governmental Industrial Hygienists (ACGIH): TLV® for Hand Activity. In Threshold Limit Values/Biological Exposure Indices 2001. Cincinnati, OH: American Conference of Governmental Industrial Hygienists; 2001.
• [8]Moore JS, Garg A: The Strain Index: A proposed method to analyze jobs for risk of distal upper extremity disorders. Am Ind Hyg Assoc J 1995, 56:443-458.
• [9]Waters TR, Putz-Anderson V, Garg A: Applications Manual for the Revised NIOSH Lifting Equation. Cincinnati, OH: U.S. Dept. of Health and Human Services; 1994.
• [10]McAtamney L, Nigel Corlett E: RULA: A survey method for the investigation of work-related upper limb disorders. Appl Ergon 1993, 24:91-99.
• [11]Upper Limb Musculoskeletal Disorder Consortium[http://www.cdc.gov/niosh/topics/upperlimb/ webcite]
• [12]Predicting Incidents and Injuries in the Workplace. [http://www.predictivesolutions.com/howitworks/ webcite]
• [13]Kinect for Windows. [http://www.microsoft.com/en-us/kinectforwindows/ webcite]
• [14]Xtion Pro. [http://www.asus.com/Multimedia/Xtion_PRO/ webcite]
• [15]Stone EE, Skubic M: Passive in-home measurement of stride-to-stride gait variability comparing vision and Kinect sensing. Conf Proc IEEE Eng Med Biol Soc 2011, 2011:6491-6494.
• [16]Lange B, Chang C-Y, Suma E, Newman B, Rizzo AS, Bolas M: Development and evaluation of low cost game-based balance rehabilitation tool using the Microsoft Kinect sensor. Conf Proc IEEE Eng Med Biol Soc 2011, 2011:1831-1834.
• [17]Waters TR, Lu M-L, Piacitelli LA, Werren D, Deddens JA: Efficacy of the revised NIOSH lifting equation to predict risk of low back pain due to manual lifting: Expanded cross-sectional analysis. J Occup Environ Med 2011, 53:1061-1067.
• [18]Dempsey PG: Usability of the revised NIOSH lifting equation. Ergonomics 2002, 45:817-828.
• [19]Real-Time Human Pose Recognition in Parts from Single Depth Images. [http://research.microsoft.com/pubs/145347/BodyPartRecognition.pdf webcite]
• [20]Obdrzalek S, Kurillo G, Ofli F, Bajcsy R, Seto E, Jimison H, Pavel M: Accuracy and robustness of Kinect pose estimation in the context of coaching of elderly population. Conf Proc IEEE Eng Med Biol Soc 2012, 2012:1188-1193.
• [21]Clark RA, Pua Y-H, Fortin K, Ritchie C, Webster KE, Denehy L, Bryant AL: Validity of the Microsoft Kinect for assessment of postural control. Gait Posture 2012, 36:372-377.
• [22]Gabel M, Gilad-Bachrach R, Renshaw E, Schuster A: Full body gait analysis with Kinect. Conf Proc IEEE Eng Med Biol Soc 2012, 2012:1964-1967.
• [23]NumPy. [http://www.numpy.org webcite]
• [24]Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay É: Scikit-learn: Machine Learning in Python. JMLR 2011, 12:2825-2830.
• [25]Bonnechère B, Jansen B, Salvia P, Bouzahouene H, Sholukha V, Cornelis J, Rooze M, Van Sint Jan S: Determination of the precision and accuracy of morphological measurements using the Kinect™ sensor: Comparison with standard stereophotogrammetry. Ergonomics 2014, 57:622-631.
• [26]Han B, Stobbe TJ, Hobbs GR: The effect of asymmetry on psychophysical lifting capacity for three lifting types. Ergonomics 2005, 48:364-379.
• [27]Lavender SA, Li YC, Natarajan RN, Andersson GBJ: Does the asymmetry multiplier in the NIOSH lifting equation adequately control the biomechanical loading of the spine? Ergonomics 1991, 2009(52):71-79.
• [28]Wu H-Y, Rubinstein M, Shih E, Guttag J, Durand F, Freeman W: Eulerian video magnification for revealing subtle changes in the world. ACM Transactions on Graphics (TOG) - SIGGRAPH 2012 Conference Proceedings 2012., 31(4) Article No. 65, http://dl.acm.org/citation.cfm?id=2185561 webcite
• [29]Wright TC, Green E, Phillips JB, Kostyuk O, Brown RA: Characterization of a “blanch-blush” mechano-response in palmar skin. J Invest Dermatol 2006, 126:220-226.
• [30]Chen C, Aggarwal J: Recognition of box-like objects by fusing cues of shape and edges. In 19th Int Conf Pattern Recognit. New York, NY: IEEE Computer Society; 2008.