Non-Contact Monitoring of Breathing Pattern and Respiratory Rate via RGB Signal Measurement

Abstract

Among all the vital signs, respiratory rate remains the least measured in several scenarios, mainly due to the intrusiveness of the sensors usually adopted. For this reason, all contactless monitoring systems are gaining increasing attention in this field. In this paper, we present a measuring system for contactless measurement of the respiratory pattern and the extraction of breath-by-breath respiratory rate. The system consists of a laptop’s built-in RGB camera and an algorithm for post-processing of acquired video data. From the recording of the chest movements of a subject, the analysis of the pixel intensity changes yields a waveform indicating respiratory pattern. The proposed system has been tested on 12 volunteers, both males and females seated in front of the webcam, wearing both slim-fit and loose-fit t-shirts. The pressure-drop signal recorded at the level of nostrils with a head-mounted wearable device was used as reference respiratory pattern. The two methods have been compared in terms of mean of absolute error, standard error, and percentage error. Additionally, a Bland–Altman plot was used to investigate the bias between methods. Results show the ability of the system to record accurate values of respiratory rate, with both slim-fit and loose-fit clothing. The measuring system shows better performance on females. Bland–Altman analysis showed a bias of −0.01 breaths · min − 1 , with respiratory rate values between 10 and 43 breaths · min − 1 . Promising performance has been found in the preliminary tests simulating tachypnea.

A Contactless Respiratory Rate Estimation Method Using a Hermite Magnification Technique and Convolutional Neural Networks

“…Compared to other recent works using Bland-Altman analysis, the work of Massaroni et al [20] obtains an agreement of ≈98% (bias = −0.01 ± 1.01) falling to a difference error with respect of the reference < ±2 bpm, consistent with our results. The work of Al-Naji et al [30] obtains an agreement of ≈99% (bias = 0.21 ± 0.62) falling to a difference error with respect to the reference < ±1 bpm, consistent with our work.…”

“…The contribution of this work is that the final proposed system does not require the selection of a ROI as others methods have reported in the literature [18,20,[23][24][25][26]34]. In addition, to the best of our knowledge, this is the first time that a CNN is trained using tagged frames as inhalation and exhalation, instead of a raw respiratory rate signal used to train other CNN strategies [18].…”

“…Different strategies to track motion are proposed. For example, Massaroni et al [20] employed frame subtraction and temporal filtering to extract signal, and Chebin et al detected the motion of the face and the shoulders for a spirometry study [21]. Several works have used magnification video motion technique to track subtle motions [22].…”

“…Most studies listed in Table 1 were limited to use of motion magnification method from a single subject and for short distances. In this Table 1, the characteristics of each method to extract RR is summarized: choice of ROI (manually [20,29,30], automatically [18,24,25], or not ROI [26] ), the kind of signal extracted to estimate RR (raw respiratory signal [18,20,24,25] or binary signal corresponding to inhalations and exhalations [26,29,30]), the method to obtain motion (amplitude magnification [24,29,30], phase magnification [25,26], frame subtraction [18]), the obtaining of the reference used to validate the method (visually using magnified video directly [24,26,29,30], using an electronic device [20,25,26]) and the number of subjects used in the work to validate the method. All works in this review use their own database.…”

“…Other works [25] use Root Mean Squared Error (RMSE) between estimated RR and the reference one. Bland-Altman (BA) analysis [33] was used to obtain the Mean of the Differences (MOD) between the reference value and the estimated value and the limits of Agreements (LOAs) values that are typically reported in other studies and very useful for comparing our results to relevant scientific literature [20,30]. In addition, correlation coefficients as Spearman coefficients (SCC) and Pearson coefficients (PCC) are also reported in some works [30].…”