LGI-rPPG-Net: A shallow encoder-decoder model for rPPG signal estimation from facial video streams

Chowdhury, Moajjem Hossain; Chowdhury, Muhammad E.H.; Reaz, Mamun Bin Ibne; Md Ali, Sawal Hamid; Rakhtala, Seyed Mehdi; Murugappan, M.; Mahmud, Sakib; Shuzan, Nazmul Islam; Bakar, Ahmad Ashrif A.; Shapiai, Mohd Ibrahim Bin; Khan, Muhammad Salman; Khandakar, Amith

Abstract

A method to accurately estimate physiological signals from video streams at a minimal cost is invaluable. The importance of such a technique in pre-clinical health monitoring cannot be understated. Remote photoplethysmography (rPPG) can be used as a substitute for finger photoplethysmography (PPG) when such sensors are not recommended, such as for burn victims, premature babies, and patients with sensitive skin. Good quality rPPG signal that is highly correlated to finger PPG can be used to estimate many vital health signs. In this work, a shallow encoder-decoder architecture, LGI-rPPG-Net is proposed. The proposed model aims to produce highly correlated rPPG signals which can be substituted for finger PPG. In the reconstruction of rPPG, the model achieved a very good Pearson's Correlation Coefficient (PCC), Root Mean Squared Error (RMSE), and dynamic time warping distance of 0.862, 0.148, and 0.699, respectively. This highly correlated rPPG was compared to finger PPG by calculating heart rate from rPPG and finger PPG. The model achieved a PCC of 0.984 and RMSE, and MAE of 2.91, 1.51 beats per minute (BPM), respectively. LGI-rPPG-Net model with video streaming to predict rPPG can thus be used as a replacement for finger PPG where in-contact collection is not feasible.

• Journal Article Type: Article
• Acceptance Date: Oct 29, 2023
• Online Publication Date: Nov 11, 2023
• Publication Date: Mar 31, 2024
• Deposit Date: Nov 16, 2023
• Publicly Available Date: Nov 12, 2025
• Journal: Biomedical Signal Processing and Control
• Print ISSN: 1746-8094
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 89
• Article Number: 105687
• DOI: https://doi.org/10.1016/j.bspc.2023.105687
• Keywords: Health Informatics; Signal Processing; Biomedical Engineering
• Public URL: https://uwe-repository.worktribe.com/output/11446179
• Additional Information: This article is maintained by: Elsevier; Article Title: LGI-rPPG-Net: A shallow encoder-decoder model for rPPG signal estimation from facial video streams; Journal Title: Biomedical Signal Processing and Control; CrossRef DOI link to publisher maintained version: https://doi.org/10.1016/j.bspc.2023.105687; Content Type: article; Copyright: © 2023 Elsevier Ltd. All rights reserved.