rPPG Estimation

Remote photoplethysmography (rPPG) aims to non-invasively extract physiological signals, primarily heart rate, from facial videos using computer vision. Current research emphasizes improving accuracy and robustness across diverse populations and challenging conditions, focusing on deep learning models—including convolutional neural networks and transformers—and techniques like contrastive learning and self-supervised pre-training to address data scarcity and domain adaptation issues. These advancements hold significant promise for applications in remote health monitoring, biometric authentication, and human-computer interaction by providing a convenient and contactless method for vital sign assessment.