dc.contributor.author | Maskeliūnas, Rytis | |
dc.contributor.author | Kulikajevas, Audrius | |
dc.contributor.author | Damaševičius, Robertas | |
dc.contributor.author | Griškevičius, Julius | |
dc.contributor.author | Adomavičienė, Aušra | |
dc.date.accessioned | 2023-09-18T16:32:50Z | |
dc.date.available | 2023-09-18T16:32:50Z | |
dc.date.issued | 2023 | |
dc.identifier.issn | 2076-3417 | |
dc.identifier.other | (crossref_id)144233531 | |
dc.identifier.uri | https://etalpykla.vilniustech.lt/handle/123456789/114628 | |
dc.description.abstract | The research introduces a unique deep-learning-based technique for remote rehabilitative analysis of image-captured human movements and postures. We present a ploninomial Pareto-optimized deep-learning architecture for processing inverse kinematics for sorting out and rearranging human skeleton joints generated by RGB-based two-dimensional (2D) skeleton recognition algorithms, with the goal of producing a full 3D model as a final result. The suggested method extracts the entire humanoid character motion curve, which is then connected to a three-dimensional (3D) mesh for real-time preview. Our method maintains high joint mapping accuracy with smooth motion frames while ensuring anthropometric regularity, producing a mean average precision (mAP) of 0.950 for the task of predicting the joint position of a single subject. Furthermore, the suggested system, trained on the MoVi dataset, enables a seamless evaluation of posture in a 3D environment, allowing participants to be examined from numerous perspectives using a single recorded camera feed. The results of evaluation on our own self-collected dataset of human posture videos and cross-validation on the benchmark MPII and KIMORE datasets are presented. | eng |
dc.format | PDF | |
dc.format.extent | p. 1-32 | |
dc.format.medium | tekstas / txt | |
dc.language.iso | eng | |
dc.relation.isreferencedby | Science Citation Index Expanded (Web of Science) | |
dc.relation.isreferencedby | Scopus | |
dc.relation.isreferencedby | INSPEC | |
dc.relation.isreferencedby | Agris | |
dc.relation.isreferencedby | DOAJ | |
dc.rights | Laisvai prieinamas internete | |
dc.source.uri | https://talpykla.elaba.lt/elaba-fedora/objects/elaba:153216920/datastreams/MAIN/content | |
dc.title | Biomac3D: 2D-to-3D human pose analysis model for tele-rehabilitation based on pareto optimized deep-learning architecture | |
dc.type | Straipsnis Web of Science DB / Article in Web of Science DB | |
dcterms.license | Creative Commons – Attribution – 4.0 International | |
dcterms.references | 114 | |
dc.type.pubtype | S1 - Straipsnis Web of Science DB / Web of Science DB article | |
dc.contributor.institution | Kauno technologijos universitetas | |
dc.contributor.institution | Vilniaus Gedimino technikos universitetas | |
dc.contributor.institution | Vilniaus universitetas | |
dc.contributor.faculty | Mechanikos fakultetas / Faculty of Mechanics | |
dc.subject.researchfield | T 009 - Mechanikos inžinerija / Mechanical enginering | |
dc.subject.researchfield | M 001 - Medicina / Medicine | |
dc.subject.researchfield | T 007 - Informatikos inžinerija / Informatics engineering | |
dc.subject.vgtuprioritizedfields | MC0404 - Bionika ir biomedicinos inžinerinės sistemos / Bionics and Biomedical Engineering Systems | |
dc.subject.ltspecializations | L105 - Sveikatos technologijos ir biotechnologijos / Health technologies and biotechnologies | |
dc.subject.en | Pareto optimization | |
dc.subject.en | 2D to 3D | |
dc.subject.en | human posture analysis | |
dc.subject.en | remote rehabilitation | |
dc.subject.en | telehealth | |
dcterms.sourcetitle | Applied sciences | |
dc.description.issue | iss. 2 | |
dc.description.volume | vol. 13 | |
dc.publisher.name | MDPI | |
dc.publisher.city | Basel | |
dc.identifier.doi | 144233531 | |
dc.identifier.doi | 1 | |
dc.identifier.doi | 2-s2.0-85146750760 | |
dc.identifier.doi | 000919563100001 | |
dc.identifier.doi | 10.3390/app13021116 | |
dc.identifier.elaba | 153216920 | |