hide
Free keywords:
imaging photoplethysmography, heart rate, signal processing, benchmark, pulse rate
Abstract:
Objective: to provide an algorithmic framework for comparing methods of pulse rate estimation using imaging photoplethysmography (iPPG), and to investigate performance of several existing methods on a publicly available dataset. Approach: first we reveal essential steps of pulse rate estimation from facial video and review methods applied at each of the steps. Then we investigate performance of these methods for DEAP dataset www.eecs.qmul.ac.uk/mmv/datasets/deap/ containing facial videos and reference contact photoplethysmograms. Main results: best assessment precision is achieved when pulse rate is estimated using continuous wavelet transform from iPPG extracted by the POS method (overall mean absolute error below 2 heart beats per minute). Significance: a framework is provided for theoretical comparison of methods for pulse rate estimation from iPPG; performance of the most popular methods is reported for a publicly available dataset that can be used as a benchmark.
