Key result
RGB cameras estimate respiratory rate with ~1.3 BPM mean absolute error using chest motion.
Why the study?
Motion-based contactless respiratory rate estimation using video can monitor individuals with partial face coverings, but remains vulnerable to voluntary subject movement.
Does motion-based respiratory rate estimation using RGB camera video accurately measure respiratory rate?
Does motion-based respiratory rate estimation using RGB camera video accurately measure respiratory rate?
Motion-based respiratory rate estimation using an RGB camera with motion artifact removal can accurately measure breathing rate, enabling continuous contactless monitoring.
Respiratory rate (RR) is a significant indicator of health conditions. Remote contactless measurement of RR is gaining popularity with recent respiratory tract infection awareness. Among various methods of contactless RR measurement, a video of an individual can be used to obtain an instantaneous RR. In this paper, we introduce an RR estimation based on the subtle motion of the head or upper chest captured on an RGB camera. Motion-based respiratory monitoring allows us to acquire RR from individuals with partial face coverings, such as glasses or a face mask. However, motion-based RR estimation is vulnerable to the subject's voluntary movement. In this work, adaptive selection between face and chest regions plus a motion artifact removal technique enables us to obtain a much cleaner respiratory signal from the video recordings. The average mean absolute error (MAE) for controlled and natural breathing is 1.95 BPM using head motion only and 1.28 BPM using chest motion only. Our results demonstrate the possibility of continuous monitoring of breathing rate in real-time with any personal device equipped with an RGB camera, such as a laptop or a smartphone.
No takes yet. Share an insight, caveat, or question.
Gwak et al. (2022) studied Respiratory rate estimation. Motion-based respiratory rate estimation using RGB camera was evaluated on Mean absolute error (MAE) for controlled and natural breathing. Motion-based respiratory rate estimation using an RGB camera achieved an average mean absolute error of 1.95 BPM using head motion and 1.28 BPM using chest motion.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: