A Single-Camera Method for Estimating Lift Asymmetry Angles Using Deep Learning Computer Vision Algorithms

IF 3.5 3区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

IEEE Transactions on Human-Machine Systems Pub Date : 2025-02-25 DOI:10.1109/THMS.2025.3539187

Zhengyang Lou;Zitong Zhan;Huan Xu;Yin Li;Yu Hen Hu;Ming-Lun Lu;Dwight M. Werren;Robert G. Radwin

{"title":"A Single-Camera Method for Estimating Lift Asymmetry Angles Using Deep Learning Computer Vision Algorithms","authors":"Zhengyang Lou;Zitong Zhan;Huan Xu;Yin Li;Yu Hen Hu;Ming-Lun Lu;Dwight M. Werren;Robert G. Radwin","doi":"10.1109/THMS.2025.3539187","DOIUrl":null,"url":null,"abstract":"A computer vision (CV) method to automatically measure the revised NIOSH lifting equation asymmetry angle (<italic>A</i>) from a single camera is described and tested. A laboratory study involving ten participants performing various lifts was used to estimate <italic>A</i> in comparison to ground truth joint coordinates obtained using 3-D motion capture (MoCap). To address challenges, such as obstructed views and limitations in camera placement in real-world scenarios, the CV method utilized video-derived coordinates from a selected set of landmarks. A 2-D pose estimator (HR-Net) detected landmark coordinates in each video frame, and a 3-D algorithm (VideoPose3D) estimated the depth of each 2-D landmark by analyzing its trajectories. The mean absolute precision error for the CV method, compared to MoCap measurements using the same subset of landmarks for estimating <italic>A</i>, was 6.25° (SD = 10.19°, N = 360). The mean absolute accuracy error of the CV method, compared against conventional MoCap landmark markers was 9.45° (SD = 14.01°, <italic>N</i> = 360).","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"55 2","pages":"309-314"},"PeriodicalIF":3.5000,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Human-Machine Systems","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10904068/","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}

引用次数: 0

Abstract

A computer vision (CV) method to automatically measure the revised NIOSH lifting equation asymmetry angle (A) from a single camera is described and tested. A laboratory study involving ten participants performing various lifts was used to estimate A in comparison to ground truth joint coordinates obtained using 3-D motion capture (MoCap). To address challenges, such as obstructed views and limitations in camera placement in real-world scenarios, the CV method utilized video-derived coordinates from a selected set of landmarks. A 2-D pose estimator (HR-Net) detected landmark coordinates in each video frame, and a 3-D algorithm (VideoPose3D) estimated the depth of each 2-D landmark by analyzing its trajectories. The mean absolute precision error for the CV method, compared to MoCap measurements using the same subset of landmarks for estimating A, was 6.25° (SD = 10.19°, N = 360). The mean absolute accuracy error of the CV method, compared against conventional MoCap landmark markers was 9.45° (SD = 14.01°, N = 360).

查看原文本刊更多论文

求助全文

约1分钟内获得全文求助全文

来源期刊

IEEE Transactions on Human-Machine Systems COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE-COMPUTER SCIENCE, CYBERNETICS

CiteScore

7.10

自引率

11.10%

发文量

136

期刊介绍： The scope of the IEEE Transactions on Human-Machine Systems includes the fields of human machine systems. It covers human systems and human organizational interactions including cognitive ergonomics, system test and evaluation, and human information processing concerns in systems and organizations.