Fusion-based approach for respiratory rate recognition from facial video images

Abstract

The respiratory rate is an important vital parameter that provides information about persons’physical condition. In clinical practice it is currently only monitored using contact-based techniques, whichcan have negative effects on patients. In this study, a new algorithm for remote respiratory rate recognitionis presented using photoplethysmographic signals derived from facial video images in the visible lightspectrum. The effects of different implementation steps in the presented algorithm are investigated in orderto optimize the approach and gain new findings in this research field. In addition, a detailed examinationof already implemented procedures is performed and the results are compared on two different databases.We show that by fusing the results of seven different respiratory-induced modulations in combination withother processing steps, very good estimates for the respiratory rate on both moving and non-moving dataare achieved. The obtained detection rates of 72.16 % and 87.68 % are significantly higher than those of thebest comparison algorithm with 37.37 % and 59.13 %. The comparison algorithms developed so far are notcompetitive with the newly designed method, especially for video recordings involving persons in motion.This paper provides important new findings in the field of facial video-based respiratory rate recognition forthe research community. A new method has been created that delivers significantly better estimates of therespiratory rate than previously developed techniques.