Cardiac Pulse Monitoring Through Multi-Scale Spectrum

Advancements in medical technology have paved the way for non-invasive methods of assessing vital parameters, marking a significant innovation in healthcare. This research addresses the challenge of contactless healthcare detection by introducing a novel approach that combines Multi-Scale Spectrum Filtering (M2SF) Photoplethysmography (PPG) and Videoplethysmography (VPG) techniques for estimating heart rate (HR) using RGB data. The proposed method eliminates the need for physical contact, offering a convenient solution for monitoring HR in various settings, including home environments. In experimental trials, the method demonstrates promising performance akin to wearable devices. To validate its accuracy, comparisons are drawn with established devices such as a Holter monitor and a commercial smartwatch, both renowned for extracting ECG data. Evaluation under scenarios with known or unknown average heart rates reveals minimal deviation, with HR estimation accuracy reaching 85% to 90% when considering lifestyle and HR information. This research highlights the effectiveness and reliability of the proposed approach, showcasing its potential for widespread adoption in remote healthcare monitoring and management.