Cargando…

Non-Contact Respiration Measurement Method Based on RGB Camera Using 1D Convolutional Neural Networks

Conventional respiration measurement requires a separate device and/or can cause discomfort, so it is difficult to perform routinely, even for patients with respiratory diseases. The development of contactless respiration measurement technology would reduce discomfort and help detect and prevent fat...

Descripción completa

Detalles Bibliográficos
Autores principales: Hwang, Hyeon-Sang, Lee, Eui-Chul
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8157066/
https://www.ncbi.nlm.nih.gov/pubmed/34063527
http://dx.doi.org/10.3390/s21103456
_version_ 1783699596868845568
author Hwang, Hyeon-Sang
Lee, Eui-Chul
author_facet Hwang, Hyeon-Sang
Lee, Eui-Chul
author_sort Hwang, Hyeon-Sang
collection PubMed
description Conventional respiration measurement requires a separate device and/or can cause discomfort, so it is difficult to perform routinely, even for patients with respiratory diseases. The development of contactless respiration measurement technology would reduce discomfort and help detect and prevent fatal diseases. Therefore, we propose a respiration measurement method using a learning-based region-of-interest detector and a clustering-based respiration pixel estimation technique. The proposed method consists of a model for classifying whether a pixel conveys respiration information based on its variance and a method for classifying pixels with clear breathing components using the symmetry of the respiration signals. The proposed method was evaluated with the data of 14 men and women acquired in an actual environment, and it was confirmed that the average error was within approximately 0.1 bpm. In addition, a Bland–Altman analysis confirmed that the measurement result had no error bias, and regression analysis confirmed that the correlation of the results with the reference is high. The proposed method, designed to be inexpensive, fast, and robust to noise, is potentially suitable for practical use in clinical scenarios.
format Online
Article
Text
id pubmed-8157066
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-81570662021-05-28 Non-Contact Respiration Measurement Method Based on RGB Camera Using 1D Convolutional Neural Networks Hwang, Hyeon-Sang Lee, Eui-Chul Sensors (Basel) Communication Conventional respiration measurement requires a separate device and/or can cause discomfort, so it is difficult to perform routinely, even for patients with respiratory diseases. The development of contactless respiration measurement technology would reduce discomfort and help detect and prevent fatal diseases. Therefore, we propose a respiration measurement method using a learning-based region-of-interest detector and a clustering-based respiration pixel estimation technique. The proposed method consists of a model for classifying whether a pixel conveys respiration information based on its variance and a method for classifying pixels with clear breathing components using the symmetry of the respiration signals. The proposed method was evaluated with the data of 14 men and women acquired in an actual environment, and it was confirmed that the average error was within approximately 0.1 bpm. In addition, a Bland–Altman analysis confirmed that the measurement result had no error bias, and regression analysis confirmed that the correlation of the results with the reference is high. The proposed method, designed to be inexpensive, fast, and robust to noise, is potentially suitable for practical use in clinical scenarios. MDPI 2021-05-15 /pmc/articles/PMC8157066/ /pubmed/34063527 http://dx.doi.org/10.3390/s21103456 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Communication
Hwang, Hyeon-Sang
Lee, Eui-Chul
Non-Contact Respiration Measurement Method Based on RGB Camera Using 1D Convolutional Neural Networks
title Non-Contact Respiration Measurement Method Based on RGB Camera Using 1D Convolutional Neural Networks
title_full Non-Contact Respiration Measurement Method Based on RGB Camera Using 1D Convolutional Neural Networks
title_fullStr Non-Contact Respiration Measurement Method Based on RGB Camera Using 1D Convolutional Neural Networks
title_full_unstemmed Non-Contact Respiration Measurement Method Based on RGB Camera Using 1D Convolutional Neural Networks
title_short Non-Contact Respiration Measurement Method Based on RGB Camera Using 1D Convolutional Neural Networks
title_sort non-contact respiration measurement method based on rgb camera using 1d convolutional neural networks
topic Communication
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8157066/
https://www.ncbi.nlm.nih.gov/pubmed/34063527
http://dx.doi.org/10.3390/s21103456
work_keys_str_mv AT hwanghyeonsang noncontactrespirationmeasurementmethodbasedonrgbcamerausing1dconvolutionalneuralnetworks
AT leeeuichul noncontactrespirationmeasurementmethodbasedonrgbcamerausing1dconvolutionalneuralnetworks