Cargando…
Two-Stage Motion Artifact Reduction Algorithm for rPPG Signals Obtained from Facial Video Recordings
Recent years have witnessed the publication of many research articles regarding the contactless measurement and monitoring of heart rate signals deduced from facial video recordings. The techniques presented in these articles, such as examining the changes in the heart rate of an infant, provide a n...
Autor principal: | |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Springer Berlin Heidelberg
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10088718/ https://www.ncbi.nlm.nih.gov/pubmed/37361465 http://dx.doi.org/10.1007/s13369-023-07845-2 |
_version_ | 1785022623675056128 |
---|---|
author | Abdulrahaman, Luqman Qader |
author_facet | Abdulrahaman, Luqman Qader |
author_sort | Abdulrahaman, Luqman Qader |
collection | PubMed |
description | Recent years have witnessed the publication of many research articles regarding the contactless measurement and monitoring of heart rate signals deduced from facial video recordings. The techniques presented in these articles, such as examining the changes in the heart rate of an infant, provide a noninvasive assessment in many cases where the direct placement of any hardware equipment is undesirable. However, performing accurate measurements in cases that include noise motion artifacts still presents an obstacle to overcome. In this research article, a two-stage method for noise reduction in facial video recording is proposed. The first stage of the system consists of dividing each (30) seconds of the acquired signal into (60) partitions and then shifting each partition to the mean level before recombining them to form the estimated heart rate signal. The second stage utilizes the wavelet transform for denoising the signal obtained from the first stage. The denoised signal is compared to a reference signal acquired from a pulse oximeter, resulting in the mean bias error (0.13), root mean square error (3.41) and correlation coefficient (0.97). The proposed algorithm is applied to (33) individuals being subjected to a normal webcam for acquiring their video recording, which can easily be performed at homes, hospitals, or any other environment. Finally, it is worth noting that this noninvasive remote technique is useful for acquiring the heart signal while preserving social distancing, which is a desirable feature in the current period of COVID-19. |
format | Online Article Text |
id | pubmed-10088718 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Springer Berlin Heidelberg |
record_format | MEDLINE/PubMed |
spelling | pubmed-100887182023-04-12 Two-Stage Motion Artifact Reduction Algorithm for rPPG Signals Obtained from Facial Video Recordings Abdulrahaman, Luqman Qader Arab J Sci Eng Research Article-Computer Engineering and Computer Science Recent years have witnessed the publication of many research articles regarding the contactless measurement and monitoring of heart rate signals deduced from facial video recordings. The techniques presented in these articles, such as examining the changes in the heart rate of an infant, provide a noninvasive assessment in many cases where the direct placement of any hardware equipment is undesirable. However, performing accurate measurements in cases that include noise motion artifacts still presents an obstacle to overcome. In this research article, a two-stage method for noise reduction in facial video recording is proposed. The first stage of the system consists of dividing each (30) seconds of the acquired signal into (60) partitions and then shifting each partition to the mean level before recombining them to form the estimated heart rate signal. The second stage utilizes the wavelet transform for denoising the signal obtained from the first stage. The denoised signal is compared to a reference signal acquired from a pulse oximeter, resulting in the mean bias error (0.13), root mean square error (3.41) and correlation coefficient (0.97). The proposed algorithm is applied to (33) individuals being subjected to a normal webcam for acquiring their video recording, which can easily be performed at homes, hospitals, or any other environment. Finally, it is worth noting that this noninvasive remote technique is useful for acquiring the heart signal while preserving social distancing, which is a desirable feature in the current period of COVID-19. Springer Berlin Heidelberg 2023-04-10 /pmc/articles/PMC10088718/ /pubmed/37361465 http://dx.doi.org/10.1007/s13369-023-07845-2 Text en © King Fahd University of Petroleum & Minerals 2023, Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. This article is made available via the PMC Open Access Subset for unrestricted research re-use and secondary analysis in any form or by any means with acknowledgement of the original source. These permissions are granted for the duration of the World Health Organization (WHO) declaration of COVID-19 as a global pandemic. |
spellingShingle | Research Article-Computer Engineering and Computer Science Abdulrahaman, Luqman Qader Two-Stage Motion Artifact Reduction Algorithm for rPPG Signals Obtained from Facial Video Recordings |
title | Two-Stage Motion Artifact Reduction Algorithm for rPPG Signals Obtained from Facial Video Recordings |
title_full | Two-Stage Motion Artifact Reduction Algorithm for rPPG Signals Obtained from Facial Video Recordings |
title_fullStr | Two-Stage Motion Artifact Reduction Algorithm for rPPG Signals Obtained from Facial Video Recordings |
title_full_unstemmed | Two-Stage Motion Artifact Reduction Algorithm for rPPG Signals Obtained from Facial Video Recordings |
title_short | Two-Stage Motion Artifact Reduction Algorithm for rPPG Signals Obtained from Facial Video Recordings |
title_sort | two-stage motion artifact reduction algorithm for rppg signals obtained from facial video recordings |
topic | Research Article-Computer Engineering and Computer Science |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10088718/ https://www.ncbi.nlm.nih.gov/pubmed/37361465 http://dx.doi.org/10.1007/s13369-023-07845-2 |
work_keys_str_mv | AT abdulrahamanluqmanqader twostagemotionartifactreductionalgorithmforrppgsignalsobtainedfromfacialvideorecordings |