A Fully Automatic Method to Extract the Heart Rate from Thermal Video

This work deals with non-invasive and non-intrusive measurements of the human facial vasculature from thermal IR to measure cardiovascular vital signs. A robust, fully automatic measurement system is developed to study infrared videos of 32 under three imaging scenarios. Vascular mapping, blood perfusion modeling, and wavelet analysis are used to calculate heart rate from 512 video frames in near real time. Multiple measurement locations are considered to analyze accuracy and sensitivity in a novel approach, revealing that the 60% of vessel segments in the forehead region are capable of producing 85% accuracy of measurement or better.