Time-varying rPPG signal separation via block-sparse signal model
For researchers in remote health monitoring, this method improves rPPG extraction robustness to illumination changes, but results are demonstrated only on a single public dataset without quantitative comparison to state-of-the-art.
The paper tackles the challenge of extracting weak rPPG signals from facial videos under illumination noise by modeling quasi-periodicity as a block-sparse structure in the time-frequency domain, achieving effective signal separation on a public dataset.
Remote photoplethysmography (rPPG) enables non-contact measurement of cardiac pulse signals by analyzing subtle color changes in facial videos. Nevertheless, extracting rPPG signals remains challenging because of their extremely weak signal strength and susceptibility to illumination noise. In this paper, we propose an rPPG signal extraction method that exploits the quasi-periodic characteristics of rPPG signals. Our approach models quasi-periodicity of the rPPG signal, which arises from the stable cardiac cycle, as a block-sparse structure in the time-frequency domain. To incorporate a block-sparse model and enable adaptive signal separation under illumination fluctuations, we construct a time-varying signal separation framework. Experiments using a public dataset demonstrate the effectiveness of our method.