Validity Analysis of Monocular Human Pose Estimation Models Interfaced with a Mobile Application for Assessing Upper Limb Range of Motion
Sensors · 14.12.2024 · 24 (24) · 7983
DOI: 10.3390/s24247983 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 14.12.2024. Verfasst von Rayele Moreira und 8 weiteren Autor:innen. Beteiligte Einrichtung: Postgraduate Program in Biotechnology, Parnaíba Delta Federal University, Parnaíba 64202-020, Brazil. Hauptthemen laut MEDLINE: Range of Motion, Articular, Mobile Applications. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Federal Institute of Maranhão, Coordenação de Aperfeicoamento de Pessoal de Nível Superior, National Council for Scientific and Technological Development.
Abstract (Originalsprache)
Human Pose Estimation (HPE) is a computer vision application that utilizes deep learning techniques to precisely locate Key Joint Points (KJPs), enabling the accurate description of a person’s pose. HPE models can be extended to facilitate Range of Motion (ROM) assessment by leveraging patient photographs. This study aims to evaluate and compare the performance of HPE models for assessing upper limbs ROM. A physiotherapist evaluated the degrees of ROM in shoulders (flexion, extension, and abduction) and elbows (flexion and extension) for fifty-two participants using both Universal Goniometer (UG) and five HPE models. Participants were instructed to repeat each movement three times to obtain measurements with the UG, then positioned while photos were captured using the NLMeasurer mobile application. The paired t-test, bias, and error measures were employed to evaluate the difference and agreement between measurement methods. Results indicated that the MoveNet Thunder INT16 model exhibited superior performance. Root Mean Square Errors obtained through this model were
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Postgraduate Program in Biotechnology, Parnaíba Delta Federal University, Parnaíba 64202-020, Brazil.
- University Center Inta, Sobral 62050-100, Brazil.
- Campus Araioses, Federal Institute of Maranhão, Araioses 65570-000, Brazil.
ORCID-Profile: Rayele Moreira, Silmar Teixeira, Renan Fialho, Aline Miranda, Lucas Daniel Batista Lima, Maria Beatriz Carvalho, Ana Beatriz Alves, Victor Hugo Vale Bastos, Ariel Soares Teles
Förderung
- Federal Institute of Maranhão
- Coordenação de Aperfeicoamento de Pessoal de Nível Superior
- National Council for Scientific and Technological Development
- Fundação de Amparo à Pesquisa e ao Desenvolvimento Científico e Tecnológico do Maranhão
- Coordination for the Improvement of Higher Education Personnel-CAPES
- National Council for Scientific and Technological Development–CNPq
- State Funding Agency of Maranhão-FAPEMA
Zitieren
APA
Moreira, R., Teixeira, S., Fialho, R., Miranda, A., Lima, L. D. B., Carvalho, M. B., Alves, A. B., Bastos, V. H. V., & Teles, A. S. (2024). Validity Analysis of Monocular Human Pose Estimation Models Interfaced with a Mobile Application for Assessing Upper Limb Range of Motion. Sensors, 24(24), 7983. https://doi.org/10.3390/s24247983
Vancouver
Moreira R, Teixeira S, Fialho R, Miranda A, Lima LDB, Carvalho MB, et al. Validity Analysis of Monocular Human Pose Estimation Models Interfaced with a Mobile Application for Assessing Upper Limb Range of Motion. Sensors. 2024;24(24):7983. doi:10.3390/s24247983
BibTeX
@article{Moreira2024,
author = {Moreira, Rayele and Teixeira, Silmar and Fialho, Renan and Miranda, Aline and Lima, Lucas Daniel Batista and Carvalho, Maria Beatriz and Alves, Ana Beatriz and Bastos, Victor Hugo Vale and Teles, Ariel Soares},
title = {Validity Analysis of Monocular Human Pose Estimation Models Interfaced with a Mobile Application for Assessing Upper Limb Range of Motion},
journal = {Sensors},
year = {2024},
volume = {24},
number = {24},
pages = {7983},
doi = {10.3390/s24247983}
}
EUVIMED