Exploiting Weak Head Movements for Camera-based Respiration Detection

Abstract

In recent years, considerable progress has been made in the non-contact based detection of the respiration rate from video sequences. Common techniques either directly assess the movement of the chest due to breathing or are based on analyzing subtle color changes that occur as a result of hemodynamic properties of the skin tissue by means of remote photoplethysmography (rPPG). However, extracting hemodynamic parameters from rPPG is often difficult especially if the skin is not visible to the camera. In contrast, extracting respiratory signals from chest movements turned out to be a robust method. However, the detectability of chest regions cannot be guaranteed in any application scenario, for instance if the camera setting is optimized to provide close-up images of the head. In such a case an alternative method for respiration detection is required.It is reasonable to assume that the mechanical coupling between chest and head induces minor movements of the head which, like in rPPG, can be detected from subtle color changes as well. Although the strength of these movements is expected to be much smaller in scale, sensing these intensity variations could provide a reasonably suited respiration signal for subsequent respiratory rate analysis.In order to investigate this coupling we conducted an experimental study with 12 subjects and applied motion-and rPPGbased methods to estimate the respiratory frequency from both head regions and chest. Our results show that it is possible to derive signals correlated to chest movement from facial regions. The method is a feasible alternative to rPPG-based respiratory rate estimations when rPPG-signals cannot be derived reliably and chest movement detection cannot be applied as well.

Non-Contact Respiratory Monitoring Using an RGB Camera for Real-World Applications

“…[ 18 ] uses variation in intensity of RGB image pixels within a selected ROI at the pit of the neck to select a respiratory signal, ref. [ 19 ] tracks head movements by means the averaging of the red channel. In addition, ref.…”

Camera-Based Method for Respiratory Rhythm Extraction From a Lateral Perspective

“…As technology evolves, the feasibility of measuring physiological variables using such methods, mixed with the technological advancements in computing hardware, makes research in these area a hot topic. Some examples that can be found in the literature of these methods comprise: continuous wave doppler radar [5], [6], depth-based cameras [7], [8], [9] or even regular consumer-grade cameras [10], [11], [12], [13] to acquire respiration.…”

“…From all the different available methods, those based on computer vision analysis have been gaining popularity in the literature, as the hardware required to perform the measurements is constantly getting cheaper and they do not interfere on other measurements in any way. There are multiple computer vision approaches on how to perform a measurement of the respiration of a subject, for example: [10] uses the head movements obtained through the averaging of the red channel, [11] uses the motion of the upper torso and head obtained through an IR camera and [12] uses a combination of the RGB colours extracted from a ROI at the pit of the neck. Although all the aforementioned methods yield good results in terms of respiratory acquisition, there are some downsides to these methods.…”

“…Although all the aforementioned methods yield good results in terms of respiratory acquisition, there are some downsides to these methods. The method proposed in [10], if there is no compensation by the tracking algorithm of small head motions, the estimated respiration will be inaccurate. The algorithm proposed by [11], even though being more robust to small movements is only valid for subjects lying on a bed, and because the camera is placed above the subject any occlusion of the camera could lead to critical errors in the respiratory acquisition.…”

“…Measuring from a lateral perspective solves an issue that is not usually addressed in the studies involving video-based methods, which is the privacy of the subject. As the camera is no longer pointing at the face [10] or upper body [12] of the subject, the potential privacy issues of being recorded by a camera are greatly minimized as no facial region can be seen.…”