Abstract
Respiration rate (RR) and respiration patterns (RP) are considered early indicators of physiological conditions and cardiorespiratory diseases. In this study, we addressed the problem of contactless estimation of RR and classification of RP of one person or two persons in a confined space under realistic conditions. We used three impulse radio ultrawideband (IR-UWB) radars and a 3D depth camera (Kinect) to avoid any blind spot in the room and to ensure that at least one of the radars covers the monitored subjects. This article proposes a subject localization and radar selection algorithm using a Kinect camera to allow the measurement of the respiration of multiple people placed at random locations. Several different experiments were conducted to verify the algorithms proposed in this work. The mean absolute error (MAE) between the estimated RR and reference RR of one-subject and two-subjects RR estimation are 0.61±0.53 breaths/min and 0.68±0.24 breaths/min, respectively. A respiratory pattern classification algorithm combining feature-based random forest classifier and pattern discrimination algorithm was developed to classify different respiration patterns including eupnea, Cheyne-Stokes respiration, Kussmaul respiration and apnea. The overall classification accuracy of 90% was achieved on a test dataset. Finally, a real-time system showing RR and RP classification on a graphical user interface (GUI) was implemented for monitoring two subjects.
Highlights
Contactless monitoring has several advantages in comparison with wearable technologies including the fact that it does not interfere with the subject’s normal behavior, does not require any activation of the system or daily maintenance such as cleaning or charging batteries and does not require contact with the body
We have presented a real-time system for robust RR estimation including detection of the chest by using radars and a depth camera, selecting the signal from the radar that has the best “view” of the subject’s chest, classifying the respiration patterns, estimating signal quality only in case when the person is stationary and detected pattern is eupnea and estimating the respiration rate
A system comprised of an RGB-D camera and three impulse radio ultrawideband (IR-UWB) radars was developed for remote respiration patterns (RP) classification and RR estimation
Summary
Contactless monitoring has several advantages in comparison with wearable technologies including the fact that it does not interfere with the subject’s normal behavior, does not require any activation of the system or daily maintenance such as cleaning or charging batteries and does not require contact with the body. Contactless monitoring using radars has several disadvantages in comparison with wearables including reduced accuracy of monitored parameters and its dependence on the orientation of subjects and their location in the room, monitoring only in confined areas, difficulties in identifying the person being measured, or assigning the measured signals to the same person in multiple-person scenarios and interference from other moving people might affect the measurements of stationary people. These are serious problems that limit the widespread use of contactless devices in general and/or limit them to monitoring a single person. This work is a proof of concept and has not yet been used in these applications
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
