Estimation of Heart Rate and Respiratory Rate using Imaging Photoplethysmography Technique

Imaging-Photoplethysmography has gathered a great amount of recognition in recent decades given to its simple, cost effective and non-contact multiparameter measurement capability. Generally, for blood volume pulse extraction, two processes are preferred. First, using green channel trace and second, using ICA or PCA to acquire underlying sources signal. ICA is used dominantly. Here, we have employed non-negative matrix factorization (NMF) for underlying source signal acquisition and compared it with the use of green channel for physiological parameter estimation. Normalized raw traces obtained from video recordings were pre-processed to keep only positive oscillations.