Shuffle-rPPGNet: Efficient Network With Global Context for Remote Heart Rate Variability Measurement

In the field of remote physiological indicator measurement, there are relatively few studies on measuring heart rate variability (HRV). Moreover, some methods using deep neural networks are computationally intensive due to high network complexity. In this article, a HRV measurement method is proposed based on an efficient 3-D convolutional neural network (3DCNN) model defined as Shuffle-rPPGNet. The basic idea of the proposed method is to extract more precise remote photoplethysmography (rPPG) signals from facial videos by this model and then calculate relevant indicators of HRV through the post-processed rPPG signals. Shuffle-rPPGNet uses a lightweight network structure named ShuffleNetV2 as a baseline to construct an efficient 3DCNN with additional parts including 3-D global context, 3-D channel shuffle, and up-sample blocks. The proposed method has been evaluated on two public datasets, i.e., UBFC-rPPG and PURE datasets. The results show that the proposed method has a better performance in HRV measurement compared to the state-of-the-art methods. Especially, the mean absolute errors (MAEs) of the average values of the normal-to-normal interval (NNI) sequence reach 2.35 and 6.62, respectively, on these two public datasets.