A computer vision method for respiratory monitoring in intensive care environment using RGB-D cameras

Abstract

This paper presents a novel computer vision method to measure the breathing pattern in intensive care environment. The proposed system uses depth information captured by two RGB-D cameras in order to reconstruct a 3D surface of a patient's torso with a high spatial coverage. The optimal positioning for the sensors is a key step to perform an accurate 3D reconstruction without interfering with patient care. In this context, our hardware setup meets the clinical requirements while allowing accurate estimation of respiratory parameters including respiratory rate, tidal volume and inspiratory time. Our system provides the motion information not only for the top of the torso surface but also for its both lateral sides. Our method was tested in an environment designed for critically ill children, where it was compared to the gold standard method currently used in intensive care units. The performed experiments yielded high accuracy and showed significant agreement with gold standard method.

Advancements in Methods and Camera-Based Sensors for the Quantification of Respiration

“…Respiratory rate seems to be one the most attractive parameters using the non-contact methods and has been addressed in a variety of conferences and journal papers divided as follows: [ 19 , 56 , 57 , 58 , 59 , 60 , 61 , 62 , 63 , 64 , 65 , 66 , 67 , 68 , 69 , 70 , 71 , 72 , 73 , 74 , 75 , 76 , 77 , 78 , 79 ] (over the period 2010–2015), [ 9 , 11 , 12 , 29 , 32 , 42 , 44 , 45 , 46 , 47 , 48 , 49 , 50 , 51 , 53 , 55 , 61 , 69 , 80 , 81 , 82 , 83 , 84 , 85 , 86 , 87 , 88 , 89 , 90 , 91 ,…”

“…Monitoring of pulmonary function such as tidal volume, minute ventilation, forced vital capacity, and forced expiratory volume has been studied in many works as well in [ 65 , 116 , 117 , 118 , 119 , 120 ] (2010–2015), [ 6 , 7 , 8 , 9 , 32 , 46 , 52 , 88 , 91 , 92 , 100 , 103 , 110 , 121 , 122 , 123 , 124 ] (2016–2020).…”

“…With further progress, non-contact methods will become more and more viable, and will have a strong growth potential. However, at the present stage of their evolution, there is an obvious need to improve the effectiveness of these systems to meet their expected performance in the different environments [ 30 , 31 , 32 ]. This requires a definition of the challenges and opportunities facing the proposed solutions and motivating this line of research.…”

Automatic non-contact monitoring of the respiratory rate of neonates using a structured light camera

“…The algorithm was tested with 36 datasets holding data recorded with different respiratory rates (3,20,30,40,45,50, 55, 60 and 80 BPM), different breathing modes (deep with a stroke varying between 2 -5 mm and shallow with a stroke of 1 -3 mm. The variation depends on the frequency.…”

“…There are two approaches using a structured light camera which have been tested with neonates. The first one requires two cameras and calculates the breathing volume [30,31]. Out of the volume change the respiratory rate is estimated.…”