Accurate measurement of respiratory airflow waveforms using depth data

Abstract

Respiratory disorders are a very common and growing health problem. Signal waveforms of respiratory airflow and volume may indicate pathological signs of several diseases and, thus, it would be important to measure them accurately. Currently, devices used in respiration measurements are mostly obtrusive in nature interfering with the natural respiration patterns. We used a depth camera for the continuous measurement of respiratory function without contact on a subject. We propose a novel calibration method which enables accurate estimates of the respiratory airflow waveforms from the depth camera data. Eight subjects were measured with the depth camera and spirometer at the same time using different breathing styles. Results show that not only the respiratory volume and respiratory rate (RR) can be computed precisely from the estimated respiratory airflow, but also the respiratory airflow waveforms are very accurate. This offers interesting opportunities, e.g. in pulmonary and critical care medicine, when objective measurements are required.

Remote, Depth-Based Lung Function Assessment

“…Correlation of 0.96 was reported against a spirometer for estimating respiratory volume. Similar to [8], Seppanen et al [9] used the first generation Kinect to estimate the respiration rate (of healthy subjects) by generating respiratory airflow waveform using several models from depth sensor data. The best coefficient of determination (R 2 ) between the spirometer signal and the estimated airflow signal was reported as 0.93.…”

Depth-Based Whole Body Photoplethysmography in Remote Pulmonary Function Testing

“…Similarly, Aoki et al [9] and Yu et al [10], computed the subject's chest volume variations in depth sequences to estimate the airflow signal, and respectively reported 0.98 and 0.96 correlation against their groundtruth. Seppanen et al [11] estimated airflow signal using multi-input-singleoutput models fed by the data acquired using a depth sensor. Their best correlation against a spirometer was R 2 = 0.93.…”

“…This work is licensed under a Creative Commons Attribution 3.0 License. For more information, see http://creativecommons.org/licenses/by/3.0/ [5], [6], [8], [12], [13] and structured light depth sensors [7], [9]- [11] and RGB video cameras [14], [15]. Some of these are briefly considered in Section II.…”

Non-Contact Respiratory Measurement Using a Depth Camera for Elderly People

“…Eight subjects were included in the trial, in which they performed different breathing styles while being measured using a depth camera and spirometer. The study concluded that it was possible to measure the TV and the RR very accurately [10].…”

“…However, it is not easy for a patient to use measuring devices for spirometry, impedance pneumography, or inductance plethysmography correctly, because they are primarily designed for clinical or research centers. Hence, they are not applicable for everyday use for home monitoring due to the complexity of the devices, their high cost, their need for skilled operators, and, in some cases, their limited portability [9,10]. Additionally, these devices require the user to be in direct contact with the equipment in an obtrusive manner, which interferes with natural respiration [10].…”