{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T01:22:02Z","timestamp":1792632122702,"version":"4.5.0"},"reference-count":57,"publisher":"Public Library of Science (PLoS)","issue":"11","license":[{"start":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T00:00:00Z","timestamp":1699488000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/M023281\/1"],"award-info":[{"award-number":["EP\/M023281\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/T022523\/1"],"award-info":[{"award-number":["EP\/T022523\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>This study examined if occluded joint locations, obtained from 2D markerless motion capture (single camera view), produced 2D joint angles with reduced agreement compared to visible joints, and if 2D frontal plane joint angles were usable for practical applications. Fifteen healthy participants performed over-ground walking whilst recorded by fifteen marker-based cameras and two machine vision cameras (frontal and sagittal plane). Repeated measures Bland-Altman analysis illustrated that markerless standard deviation of bias and limits of agreement for the occluded-side hip and knee joint angles in the sagittal plane were double that of the camera-side (visible) hip and knee. Camera-side sagittal plane knee and hip angles were near or within marker-based error values previously observed. While frontal plane limits of agreement accounted for 35\u201346% of total range of motion at the hip and knee, Bland-Altman bias and limits of agreement (-4.6\u20131.6 \u00b1 3.7\u20134.2\u02da) were actually similar to previously reported marker-based error values. This was not true for the ankle, where the limits of agreement (\u00b1 12\u02da) were still too high for practical applications. Our results add to previous literature, highlighting shortcomings of current pose estimation algorithms and labelled datasets. As such, this paper finishes by reviewing methods for creating anatomically accurate markerless training data using marker-based motion capture data.<\/jats:p>","DOI":"10.1371\/journal.pone.0293917","type":"journal-article","created":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T18:48:26Z","timestamp":1699555706000},"page":"e0293917","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":43,"title":["Examination of 2D frontal and sagittal markerless motion capture: Implications for markerless applications"],"prefix":"10.1371","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9973-9934","authenticated-orcid":true,"given":"Logan","family":"Wade","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laurie","family":"Needham","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Murray","family":"Evans","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Polly","family":"McGuigan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steffi","family":"Colyer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Darren","family":"Cosker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Bilzon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2023,11,9]]},"reference":[{"key":"pone.0293917.ref001","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1186\/s40798-018-0139-y","article-title":"A Review of the Evolution of Vision-Based Motion Analysis and the Integration of Advanced Computer Vision Methods Towards Developing a Markerless System","volume":"4","author":"SL Colyer","year":"2018","journal-title":"Sports Medicine\u2014Open"},{"issue":"1","key":"pone.0293917.ref002","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1016\/j.neuron.2020.09.017","article-title":"A Primer on Motion Capture with Deep Learning: Principles, Pitfalls, and Perspectives","volume":"108","author":"A Mathis","year":"2020","journal-title":"Neuron"},{"key":"pone.0293917.ref003","doi-asserted-by":"crossref","first-page":"e12995","DOI":"10.7717\/peerj.12995","article-title":"Applications and limitations of current markerless motion capture methods for clinical gait biomechanics","volume":"10","author":"L Wade","year":"2022","journal-title":"PeerJ"},{"key":"pone.0293917.ref004","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/j.jbiomech.2019.02.021","article-title":"Markerless 2D kinematic analysis of underwater running: A deep learning approach","volume":"87","author":"NJ Cronin","year":"2019","journal-title":"Journal of Biomechanics"},{"key":"pone.0293917.ref005","doi-asserted-by":"crossref","first-page":"4054","DOI":"10.1038\/s41467-020-17807-z","article-title":"Deep neural networks enable quantitative movement analysis using single-camera videos","volume":"11","author":"\u0141 Kidzi\u0144ski","year":"2020","journal-title":"Nature Communications"},{"key":"pone.0293917.ref006","doi-asserted-by":"crossref","first-page":"2097","DOI":"10.1145\/3341105.3373963","volume-title":"Proceedings of the 35th Annual ACM Symposium on Applied Computing","author":"M Moro","year":"2020"},{"issue":"1","key":"pone.0293917.ref007","doi-asserted-by":"crossref","first-page":"14065","DOI":"10.1038\/s41598-021-93530-z","article-title":"Algorithm based on one monocular video delivers highly valid and reliable gait parameters","volume":"11","author":"A Azhand","year":"2021","journal-title":"Scientific Reports"},{"key":"pone.0293917.ref008","article-title":"OpenCap: 3D human movement dynamics from smartphone videos","author":"SD Uhlrich","year":"2022","journal-title":"bioRxiv"},{"key":"pone.0293917.ref009","doi-asserted-by":"crossref","first-page":"111338","DOI":"10.1016\/j.jbiomech.2022.111338","article-title":"The development and evaluation of a fully automated markerless motion capture workflow","volume":"144","author":"L Needham","year":"2022","journal-title":"Journal of Biomechanics"},{"key":"pone.0293917.ref010","doi-asserted-by":"crossref","first-page":"1271","DOI":"10.3233\/JPD-212544","article-title":"Quantitative Gait Analysis Using a Pose-Estimation Algorithm with a Single 2D-Video of Parkinson\u2019s Disease Patients","volume":"11","author":"JH Shin","year":"2021","journal-title":"Journal of Parkinson\u2019s Disease"},{"key":"pone.0293917.ref011","doi-asserted-by":"crossref","first-page":"2666","DOI":"10.1109\/TNSRE.2021.3135879","article-title":"Accuracy of Temporo-Spatial and Lower Limb Joint Kinematics Parameters Using OpenPose for Various Gait Patterns With Orthosis","volume":"29","author":"M Yamamoto","year":"2021","journal-title":"IEEE Transactions on Neural Systems and Rehabilitation Engineering"},{"key":"pone.0293917.ref012","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1016\/j.gaitpost.2021.02.006","article-title":"Verification of validity of gait analysis systems during treadmill walking and running using human pose tracking algorithm","volume":"85","author":"M Ota","year":"2021","journal-title":"Gait & Posture"},{"issue":"1","key":"pone.0293917.ref013","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1109\/TPAMI.2019.2929257","article-title":"OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields","volume":"43","author":"Z Cao","year":"2019","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"7","key":"pone.0293917.ref014","doi-asserted-by":"crossref","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","article-title":"Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments","volume":"36","author":"C Ionescu","year":"2014","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"pone.0293917.ref015","volume-title":"European Conference on Computer Vision","author":"S Jin","year":"2020"},{"issue":"8","key":"pone.0293917.ref016","doi-asserted-by":"crossref","first-page":"1235","DOI":"10.2522\/ptj.20100324","article-title":"Frontal-Plane Gait Mechanics in People With Medial Knee Osteoarthritis Are Different From Those in People With Lateral Knee Osteoarthritis","volume":"91","author":"RJ Butler","year":"2011","journal-title":"Physical Therapy"},{"issue":"9","key":"pone.0293917.ref017","doi-asserted-by":"crossref","first-page":"1203","DOI":"10.1016\/j.joca.2018.04.011","article-title":"Relationship between knee joint contact forces and external knee joint moments in patients with medial knee osteoarthritis: effects of gait modifications","volume":"26","author":"RE Richards","year":"2018","journal-title":"Osteoarthritis and Cartilage"},{"issue":"6","key":"pone.0293917.ref018","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1080\/16501970310012428","article-title":"Associations between lower limb impairments, locomotor capacities and kinematic variables in the frontal plane during walking in adults with chronic stroke","volume":"35","author":"E De Bujanda","year":"2003","journal-title":"Journal of rehabilitation medicine"},{"issue":"3","key":"pone.0293917.ref019","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1080\/14763140802233215","article-title":"Gender differences in lower limb frontal plane kinematics during landing","volume":"7","author":"G Hughes","year":"2008","journal-title":"Sports Biomechanics"},{"key":"pone.0293917.ref020","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1016\/j.gaitpost.2017.03.017","article-title":"Relationship between ankle frontal plane kinematics during different functional tasks","volume":"54","author":"L Donovan","year":"2017","journal-title":"Gait & Posture"},{"issue":"1","key":"pone.0293917.ref021","doi-asserted-by":"crossref","first-page":"20673","DOI":"10.1038\/s41598-021-00212-x","article-title":"The accuracy of several pose estimation methods for 3D joint centre localisation","volume":"11","author":"L Needham","year":"2021","journal-title":"Scientific Reports"},{"issue":"1","key":"pone.0293917.ref022","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1115\/1.3662552","article-title":"A New Approach to Linear Filtering and Prediction Problems","volume":"82","author":"RE Kalman","year":"1960","journal-title":"Journal of Basic Engineering"},{"key":"pone.0293917.ref023","author":"A Bewley","year":"2016"},{"issue":"1\u20132","key":"pone.0293917.ref024","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1002\/nav.3800020109","article-title":"The Hungarian method for the assignment problem","volume":"2","author":"HW Kuhn","year":"1955","journal-title":"Naval Research Logistics Quarterly"},{"issue":"1","key":"pone.0293917.ref025","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/0167-9457(89)90020-1","article-title":"Prediction of hip joint centre location from external landmarks","volume":"8","author":"AL Bell","year":"1989","journal-title":"Human Movement Science"},{"key":"pone.0293917.ref026","doi-asserted-by":"crossref","first-page":"110547","DOI":"10.1016\/j.jbiomech.2021.110547","article-title":"Moving outside the lab: Markerless motion capture accurately quantifies sagittal plane kinematics during the vertical jump","volume":"125","author":"JF Drazan","year":"2021","journal-title":"Journal of Biomechanics"},{"issue":"4","key":"pone.0293917.ref027","doi-asserted-by":"crossref","first-page":"e1008935","DOI":"10.1371\/journal.pcbi.1008935","article-title":"Two-dimensional video-based analysis of human gait using pose estimation","volume":"17","author":"J Stenum","year":"2021","journal-title":"PLOS Computational Biology"},{"key":"pone.0293917.ref028","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.gaitpost.2021.03.003","article-title":"A novel dataset and deep learning-based approach for marker-less motion capture during gait","volume":"86","author":"S Vafadar","year":"2021","journal-title":"Gait & Posture"},{"issue":"8476","key":"pone.0293917.ref029","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/S0140-6736(86)90837-8","article-title":"Statistical methods for assessing agreement between two methods of clinical measurement","volume":"327","author":"M Bland","year":"1986","journal-title":"The Lancet"},{"issue":"3","key":"pone.0293917.ref030","doi-asserted-by":"crossref","first-page":"567","DOI":"10.1016\/j.jbiomech.2012.09.023","article-title":"Kinematic differences between optical motion capture and biplanar videoradiography during a jump\u2013cut maneuver","volume":"46","author":"DL Miranda","year":"2013","journal-title":"Journal of Biomechanics"},{"key":"pone.0293917.ref031","doi-asserted-by":"crossref","first-page":"199","DOI":"10.3389\/fbioe.2019.00199","article-title":"A Direct Comparison of Biplanar Videoradiography and Optical Motion Capture for Foot and Ankle Kinematics","volume":"7","author":"SE Kessler","year":"2019","journal-title":"Frontiers in Bioengineering and Biotechnology"},{"issue":"2","key":"pone.0293917.ref032","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1016\/j.gaitpost.2005.04.012","article-title":"Effect of skin movement artifact on knee kinematics during gait and cutting motions measured in vivo","volume":"24","author":"DL Benoit","year":"2006","journal-title":"Gait & Posture"},{"issue":"4","key":"pone.0293917.ref033","doi-asserted-by":"crossref","first-page":"571","DOI":"10.1080\/10543400701329422","article-title":"Agreement Between Methods of Measurement with Multiple Observations Per Individual","volume":"17","author":"JM Bland","year":"2007","journal-title":"Journal of biopharmaceutical statistics"},{"issue":"31","key":"pone.0293917.ref034","doi-asserted-by":"crossref","first-page":"1026","DOI":"10.21105\/joss.01026","article-title":"Pingouin: statistics in Python","volume":"3","author":"R. Vallat","year":"2018","journal-title":"J Open Source Softw"},{"key":"pone.0293917.ref035","first-page":"8","article-title":"Repeated Measures Correlation","author":"JZ Bakdash","year":"2017","journal-title":"Frontiers in Psychology"},{"key":"pone.0293917.ref036","first-page":"1","article-title":"Artificial Intelligence-Assisted motion capture for medical applications: a comparative study between markerless and passive marker motion capture","author":"I Takeda","year":"2020","journal-title":"Computer Methods in Biomechanics and Biomedical Engineering"},{"issue":"1","key":"pone.0293917.ref037","doi-asserted-by":"crossref","first-page":"17719","DOI":"10.1038\/s41598-022-22246-5","article-title":"Verification of gait analysis method fusing camera-based pose estimation and an IMU sensor in various gait conditions","volume":"12","author":"M Yamamoto","year":"2022","journal-title":"Scientific Reports"},{"key":"pone.0293917.ref038","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"S-H Zhang","year":"2019"},{"key":"pone.0293917.ref039","doi-asserted-by":"crossref","first-page":"110460","DOI":"10.1016\/j.jbiomech.2021.110460","article-title":"Using deep neural networks for kinematic analysis: Challenges and opportunities","volume":"123","author":"NJ Cronin","year":"2021","journal-title":"Journal of Biomechanics"},{"key":"pone.0293917.ref040","article-title":"Movement science needs different pose tracking algorithms","author":"N Seethapathi","year":"2019","journal-title":"arXiv preprint arXiv:190710226"},{"key":"pone.0293917.ref041","doi-asserted-by":"crossref","first-page":"110422","DOI":"10.1016\/j.jbiomech.2021.110422","article-title":"Inter-session repeatability of markerless motion capture gait kinematics","volume":"121","author":"RM Kanko","year":"2021","journal-title":"Journal of Biomechanics"},{"key":"pone.0293917.ref042","doi-asserted-by":"crossref","first-page":"110665","DOI":"10.1016\/j.jbiomech.2021.110665","article-title":"Concurrent assessment of gait kinematics using marker-based and markerless motion capture","volume":"127","author":"RM Kanko","year":"2021","journal-title":"Journal of Biomechanics"},{"key":"pone.0293917.ref043","doi-asserted-by":"crossref","first-page":"110414","DOI":"10.1016\/j.jbiomech.2021.110414","article-title":"Assessment of spatiotemporal gait parameters using a deep learning algorithm-based markerless motion capture system","volume":"122","author":"RM Kanko","year":"2021","journal-title":"Journal of Biomechanics"},{"issue":"1","key":"pone.0293917.ref044","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1298\/jjpta.6.9","article-title":"Test-Retest Reliability and Inter-Tester Reliability of Kinematic Data from a Three-Dimensional Gait Analysis System","volume":"6","author":"H Tsushima","year":"2003","journal-title":"Journal of the Japanese Physical Therapy Association"},{"issue":"3","key":"pone.0293917.ref045","first-page":"189","article-title":"Spatiotemporal Gait Patterns During Overt and Covert Evaluation in Patients With Parkinson\u2019s Disease and Healthy Subjects","volume":"31","author":"V Robles-Garc\u00eda","year":"2015","journal-title":"Is There a Hawthorne Effect?"},{"key":"pone.0293917.ref046","first-page":"34","author":"M Loper","year":"2015","journal-title":"SMPL: a skinned multi-person linear model"},{"key":"pone.0293917.ref047","article-title":"editors. AGORA: Avatars in geography optimized for regression analysis","author":"P Patel","year":"2021","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"pone.0293917.ref048","author":"K Iskakov","year":"2019"},{"key":"pone.0293917.ref049","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1016\/j.gaitpost.2022.03.008","article-title":"Assessment of a novel deep learning-based marker-less motion capture system for gait study","volume":"94","author":"S Vafadar","year":"2022","journal-title":"Gait & Posture"},{"issue":"17","key":"pone.0293917.ref050","doi-asserted-by":"crossref","first-page":"6522","DOI":"10.3390\/s22176522","article-title":"Synthesising 2D Video from 3D Motion Data for Machine Learning Applications","volume":"22","author":"M Mundt","year":"2022","journal-title":"Sensors"},{"key":"pone.0293917.ref051","volume-title":"2016 Fourth International Conference on 3D Vision (3DV)","author":"W Chen","year":"2016"},{"key":"pone.0293917.ref052","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"G Varol","year":"2017"},{"key":"pone.0293917.ref053","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"S Zhang","year":"2021"},{"key":"pone.0293917.ref054","article-title":"Playing for 3D human recovery","author":"Z Cai","year":"2021","journal-title":"arXiv preprint arXiv:211007588"},{"key":"pone.0293917.ref055","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"H Yan","year":"2021"},{"issue":"1","key":"pone.0293917.ref056","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11832-016-0713-0","article-title":"EOS\u00ae biplanar X-ray imaging: Concept, developments, benefits, and limitations","volume":"10","author":"E Melhem","year":"2016","journal-title":"Journal of Children\u2019s Orthopaedics"},{"issue":"12","key":"pone.0293917.ref057","doi-asserted-by":"crossref","first-page":"121002","DOI":"10.1115\/1.4005471","article-title":"Static and Dynamic Error of a Biplanar Videoradiography System Using Marker-Based and Markerless Tracking Techniques","volume":"133","author":"DL Miranda","year":"2011","journal-title":"Journal of Biomechanical Engineering"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0293917","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T18:49:02Z","timestamp":1699555742000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0293917"}},"subtitle":[],"editor":[{"given":"Yaodong","family":"Gu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2023,11,9]]},"references-count":57,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2023,11,9]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0293917","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,9]]}}}