Is low-cost motion capture with artificial intelligence applicable for human working posture risk assessment during manual material handling? A pilot study
Restricted accessResearch articleFirst published online January 13, 2023
Is low-cost motion capture with artificial intelligence applicable for human working posture risk assessment during manual material handling? A pilot study
Assessing working posture risks is important for occupational safety and health. However, low-cost assessment techniques for human motion injuries in the logistics delivery industry have rarely been reported.
OBJECTIVE:
To propose a novel approach for posture risk assessment using low-cost motion capture with artificial intelligence.
METHODS:
A Kinect was adopted to obtain red-green-blue (RGB) and depth images of the subject with 24 postures, and the human joints were extracted using artificial intelligence. The images were registered to obtain the actual three-dimensional (3D) human joint angle.
RESULTS:
The root mean square error (RMSE) significantly decreased. Finally, two common methods for evaluating human working posture injuries—the Rapid Upper Limb Assessment and Ovako Working Posture Analysis System—were investigated.
CONCLUSIONS:
The outputs of the proposed method are consistent with those of the commercial ergonomic evaluation software.
ChryssolourisG, MavrikiosD, FragosD, KarabatsouV. A virtual reality-based experimentation environment for the verification of human-related factors in assembly processes. Robot Cim-Int Manuf. 2000;16:267–276.
2.
LamkullD, HansonL, OrtengrenR. A comparative study of digital human modelling simulation results and their outcomes in reality: A case study within manual assembly of automobiles. Int J Ind Ergonom. 2009;39:428–441.
3.
SavinoM, MazzaA, BattiniD. New easy to use postural assessment method through visual management. Int J Ind Ergonom. 2016;53:48–58.
AbobakrA, NahavandiD, IskanderJ, HossnyM, NahavandiS, SmetsM. RGB-D Human Posture Analysis for Ergonomic Studies using Deep Convolutional Neural Network. IEEE Sys Man Cybern. 2017;2885–2890.
6.
HuB, MaLA, ZhangW, SalvendyG, ChablatD, BennisF. Predicting real-world ergonomic measurements by simulation in a virtual environment. Int J Ind Ergonom. 2011;41:64–71.
7.
De MagistrisG, MicaelliA, EvrardP, AndriotC, SavinJ, GaudezC, MarsotJ. Dynamic control of DHM for ergonomic assessments. Int J Ind Ergonom. 2013;43:170–180.
8.
PeppoloniL, FilippeschiA, RuffaldiE, AvizzanoCA. A novel wearable system for the online assessment of risk for biomechanical load in repetitive efforts. Int J Ind Ergonom. 2016;52:1–11.
9.
ChanderDS, CavatortaMP. An observational method for Postural Ergonomic Risk Assessment (PERA). Int J Ind Ergonom. 2017;57:32–41.
10.
BarimMS, SesekRF, CapanogluMF, DrinkausP, SchallMC, GallagherS, DavisGA. Improving the risk assessment capability of the revised NIOSH lifting equation by incorporating personal characteristics. Appl Ergon. 2019;74:67–73.
11.
HilfikerS W, SantanaS, FreedmanM, HarrisL. There’s a gap between digital health information and users — let’s close it. Information Services & Use. 2019;39(1-2):15–22.
12.
VinkP, BazleyC, JacobsK. Modeling the relationship between the environment and human experiences. Work. 2016;54(4):765.
13.
DuttaT. Evaluation of the Kinect (TM) sensor for 3-D kinematic measurement in the workplace. Appl Ergon. 2012;43:645–649.
14.
PlantardP, ShumHPH, Le PierresAS, MultonF. Validation of an ergonomic assessment method using Kinect data in real workplace conditions. Appl Ergon. 2017;65:562–569.
15.
ParkSU, ParkJH, Al-masniMA, Al-antariMA, UddinMZ, KimTS. A Depth Camera-based Human Activity Recognition via Deep Learning Recurrent Neural Network for Health and Social Care Services. Procedia Comput Sci. 2016;100:78–84.
16.
XuX, McGorryRW. The validity of the first and second generation Microsoft Kinect (TM) for identifying joint center locations during static postures. Appl Ergon. 2015;49:47–54.
17.
ManghisiVM, UvaAE, FiorentinoM, BevilacquaV, TrottaGF, MonnoG. Real time RULA assessment using Kinect v2 sensor. Appl Ergon. 2017;65:481–491.
18.
KwonW, ParkY, LeeS, SuhIH. Human Activity Recognition Using Deep Recurrent Neural Networks and Complexity-based Motion Features. Conference Proceedings, DLAI. 2016, New York, NY, 10 July 2016.
19.
Diego-MasJA, Alcaide-MarzalJ. Using Kinect (TM) sensor in observational methods for assessing postures at work. Appl Ergon. 2014;45:976–985.
20.
BogoF, KanazawaA, LassnerC, GehlerP, RomeroJ, BlackMJ. Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image. Computer Vision – Eccv. 2016;9909:561–578.
21.
DuY, WongYK, LiuYH, HanFL, GuiYL, WangZ, KankanhalliM, GengWD. Marker-Less 3D Human Motion Capture with Monocular Image Sequence and Height-Maps. Computer Vision – ECCV. 2016;9908:20–36.
22.
SarafianosN, BoteanuB, IonescuB, KakadiarisIA. 3D Human pose estimation: A review of the literature and analysis of covariates. Comput Vis Image Und. 2016;152:1–20.
23.
TomeD, RussellC, AgapitoL. Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image. Proc Cvpr IEEE. 2017;5689–5698.
24.
IqbalU, DoeringA, YasinH, KrugerB, WeberA, GallJ. A dual-source approach for 3D human pose estimation from single images. Comput Vis Image Und. 2018;172:37–49.
25.
TekinB, KatirciogluI, SalzmannM, LepetitV, FuaP. Structured Prediction of 3D Human Pose with Deep Neural Networks. 27th British Machine Vision Conference, September 19 2016 – September 22. 2016:130,1-130,11
26.
MehtaD, SridharS, SotnychenkoO, RhodinH, ShafieiM, SeidelHP, XuWP, CasasD, TheobaltC. VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera. ACM Trans Graph. 2017;36:4, Article 44, 14 pages.
27.
GulerA, KardarisN, ChandraS, PitsikalisV, WernerC, HauerK, TzafestasC, MaragosP, KokkinosI. Human Joint Angle Estimation and Gesture Recognition for Assistive Robotic Vision. Computer Vision – ECCV. 2016;9914:415–431.
PeresSC, MehtaRK, RitcheyP. Assessing ergonomic risks of software: Development of the SEAT. Appl Ergon. 2017;59:377–386.
30.
TianRR, DuffyVG. Computerized task risk assessment using digital human modeling based Job Risk Classification Model. Comput Ind Eng. 2011;61:1044–1052.
31.
ShikdarA, Al-AraimiS, OmurtagB. Development of a software package for ergonomic assessment of manufacturing industry. Comput Ind Eng. 2002;43:485–493.
32.
KushwahaDK, KanePV. Ergonomic assessment and workstation design of shipping crane cabin in steel industry. Int J Ind Ergonom. 2016;52:29–39.
33.
XuG, ZhangZ. Epipolar Geometry in Stereo Motion and Object Recognition. Kluwer Academic Publishers, Dordrecht: The Netherlands. 1996.
34.
ZhangZY. A flexible new technique for camera calibration. IEEE T Pattern Anal. 2000;22:1330–1334.
