Weighted combination and singular spectrum analysis based remote photoplethysmography pulse extraction in low-light environments. (July 2022)

• Record Type: Journal Article
• Authors: Xi, Lin; Wu, Xingming; Chen, Weihai; Wang, Jianhua; Zhao, Changchen
• Is Part Of: Medical engineering & physics. Volume 105(2022)
• Publication Date: 2022-07
• Subjects: Biosignal processing -- Remote photoplethysmography -- Heart rate estimation -- Noise suppression -- Low-illumination environments; Biomedical engineering -- Periodicals; Biomedical Engineering -- Periodicals; Physics -- Periodicals; Génie biomédical -- Périodiques; Biomedical engineering; Electronic journals; Periodicals; 610.28
• DOI: 10.1016/j.medengphy.2022.103822
• Languages: English
• ISSNs: 1350-4533

Abstract

Highlights: The influence of light illumination on the rPPG measurement is investigated in a mathematical context with optical and physiological reasoning. A new core rPPG method is introduced to achieves competitive performance than state-of-theart methods under extremely low illumination environments. A decomposition method is used to decompose the pulse signal, and spectral masking is proposed to select relevant components based on the frequency structure of rPPG signal. A weight combination strategy is proposed to build the final signal with the suitable candidates related to the pulse signal Graphical abstract: Abstract: Camera-based vital signs monitoring in recent years has attracted more and more researchers and the results are promising. However, a few research works focus on heart rate extraction under extremely low illumination environments. In this paper, we propose a novel framework for remote heart rate estimation under low-light conditions. This method uses singular spectrum analysis (SSA) to decompose the filtered signal into several reconstructed components. A spectral masking algorithm is utilized to refine the preliminary candidate components on the basis of a reference heart rate. The contributive components are fused into the final pulse signal. To evaluate the performance of our framework in low-light conditions, the proposed approach is tested on a large-scale multi-illumination HR dataset (named MIHR). The test results verify that the proposed method has stronger robustness to low illumination than state-of-the-art methods, effectively improving the signal-to-noise ratio and heart rate estimation precision. We further perform experiments on the PUlse RatE detection (PURE) dataset which is recorded under normal light conditions to demonstrate the generalization of our method. The experiment results show that our method can stably detect pulse rate and achieve comparative results. The proposed method pioneers a new solution to the remote heart rate estimation in low-light conditions.