RADIANT: Better rPPG estimation using signal embeddings and Transformer

Remote photoplethysmography can provide non-contact heart rate (HR) estimation by analyzing the skin color variations obtained from face videos. These variations are subtle, imperceptible to human eyes, and easily affected by noise. Existing deep learning-based rPPG estimators are incompetent due to three reasons. Firstly, they suppress the noise by utilizing information from the whole face even though different facial regions contain different noise characteristics. Secondly, local noise characteristics inherently affect the convolutional neural network (CNN) architectures. Lastly, the CNN sequential architectures fail to preserve long temporal dependencies. To address these issues, we propose RADIANT, that is, rPPG estimation using Signal Embeddings and Transformer. Our architecture utilizes a multi-head attention mechanism that facilitates feature subspace learning to extract the multiple correlations among the color variations corresponding to the periodic pulse. Also, its global information processing ability helps to suppress local noise characteristics. Furthermore, we propose novel signal embedding to enhance the rPPG feature representation and suppress noise. We have also improved the generalization of our architecture by adding a new training set. To this end, the effectiveness of synthetic temporal signals and data augmentations were explored. Experiments on extensively utilized rPPG datasets demonstrate that our architecture outperforms previous well-known architectures. Code: https://github.com/Deep-Intelligence-Lab/RADIANT.git