Contactless Blood Oxygen Saturation Estimation from Facial Videos Using Deep Learning

Blood oxygen saturation (SpO) is an essential physiological parameter for evaluating a person’s health. While conventional SpO measurement devices like pulse oximeters require skin contact, advanced computer vision technology can enable remote SpO monitoring through a regular camera without skin contact. In this paper, we propose novel deep learning models to measure SpO remotely from facial videos and evaluate them using a public benchmark database, VIPL-HR. We utilize a spatial–temporal representation to encode SpO information recorded by conventional RGB cameras and directly pass it into selected convolutional neural networks to predict SpO. The best deep learning model achieves 1.274% in mean absolute error and 1.71% in root mean squared error, which exceed the international standard of 4% for an approved pulse oximeter. Our results significantly outperform the conventional analytical Ratio of Ratios model for contactless SpO measurement. Results of sensitivity analyses of the influence of spatial–temporal representation color spaces, subject scenarios, acquisition devices, and SpO ranges on the model performance are reported with explainability analyses to provide more insights for this emerging research field.