Cargando…

Detection of sitting posture using hierarchical image composition and deep learning

Human posture detection allows the capture of the kinematic parameters of the human body, which is important for many applications, such as assisted living, healthcare, physical exercising and rehabilitation. This task can greatly benefit from recent development in deep learning and computer vision....

Descripción completa

Detalles Bibliográficos
Autores principales: Kulikajevas, Audrius, Maskeliunas, Rytis, Damaševičius, Robertas
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8022631/
https://www.ncbi.nlm.nih.gov/pubmed/33834109
http://dx.doi.org/10.7717/peerj-cs.442
_version_ 1783674971607793664
author Kulikajevas, Audrius
Maskeliunas, Rytis
Damaševičius, Robertas
author_facet Kulikajevas, Audrius
Maskeliunas, Rytis
Damaševičius, Robertas
author_sort Kulikajevas, Audrius
collection PubMed
description Human posture detection allows the capture of the kinematic parameters of the human body, which is important for many applications, such as assisted living, healthcare, physical exercising and rehabilitation. This task can greatly benefit from recent development in deep learning and computer vision. In this paper, we propose a novel deep recurrent hierarchical network (DRHN) model based on MobileNetV2 that allows for greater flexibility by reducing or eliminating posture detection problems related to a limited visibility human torso in the frame, i.e., the occlusion problem. The DRHN network accepts the RGB-Depth frame sequences and produces a representation of semantically related posture states. We achieved 91.47% accuracy at 10 fps rate for sitting posture recognition.
format Online
Article
Text
id pubmed-8022631
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher PeerJ Inc.
record_format MEDLINE/PubMed
spelling pubmed-80226312021-04-07 Detection of sitting posture using hierarchical image composition and deep learning Kulikajevas, Audrius Maskeliunas, Rytis Damaševičius, Robertas PeerJ Comput Sci Human-Computer Interaction Human posture detection allows the capture of the kinematic parameters of the human body, which is important for many applications, such as assisted living, healthcare, physical exercising and rehabilitation. This task can greatly benefit from recent development in deep learning and computer vision. In this paper, we propose a novel deep recurrent hierarchical network (DRHN) model based on MobileNetV2 that allows for greater flexibility by reducing or eliminating posture detection problems related to a limited visibility human torso in the frame, i.e., the occlusion problem. The DRHN network accepts the RGB-Depth frame sequences and produces a representation of semantically related posture states. We achieved 91.47% accuracy at 10 fps rate for sitting posture recognition. PeerJ Inc. 2021-03-23 /pmc/articles/PMC8022631/ /pubmed/33834109 http://dx.doi.org/10.7717/peerj-cs.442 Text en © 2021 Kulikajevas et al. https://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Computer Science) and either DOI or URL of the article must be cited.
spellingShingle Human-Computer Interaction
Kulikajevas, Audrius
Maskeliunas, Rytis
Damaševičius, Robertas
Detection of sitting posture using hierarchical image composition and deep learning
title Detection of sitting posture using hierarchical image composition and deep learning
title_full Detection of sitting posture using hierarchical image composition and deep learning
title_fullStr Detection of sitting posture using hierarchical image composition and deep learning
title_full_unstemmed Detection of sitting posture using hierarchical image composition and deep learning
title_short Detection of sitting posture using hierarchical image composition and deep learning
title_sort detection of sitting posture using hierarchical image composition and deep learning
topic Human-Computer Interaction
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8022631/
https://www.ncbi.nlm.nih.gov/pubmed/33834109
http://dx.doi.org/10.7717/peerj-cs.442
work_keys_str_mv AT kulikajevasaudrius detectionofsittingpostureusinghierarchicalimagecompositionanddeeplearning
AT maskeliunasrytis detectionofsittingpostureusinghierarchicalimagecompositionanddeeplearning
AT damaseviciusrobertas detectionofsittingpostureusinghierarchicalimagecompositionanddeeplearning