New insights on super-high resolution for video-based heart rate estimation with a semi-blind source separation method.

Remote photoplethysmography (rPPG), a non-contact technique to estimate heart rates (HR) from video recordings, has attracted much attention from researchers in recent years. It is well-known that rPPG signals can be extracted from low-resolution videos. However, the measurement quality may degrade due to camera quantization noise if only a small number of pixels are within the skin region of interest. The purpose of this paper is to comprehensively investigate the benefit of using a super-high resolution for the rPPG-based HR estimation under various shooting distances. A new semi-blind source separation (semi-BSS) rPPG method, which is proposed to combine the advantages of BSS and model-based methods, is fully tested on both the public UBFC-RPPG and self-collected video datasets. The experimental results demonstrate that the new semi-BSS method outperforms several existing techniques. A consistent and remarkable improvement on the rPPG signal quality has been observed with the super-high resolution when the shooting distance is no less than 1.0 m. This indicates that selecting an appropriate resolution based on a given shooting distance also plays a crucial role to improve the quality of rPPG measurements.