A Computer Vision-Based Respiratory Rate Monitoring and Alarm System

Abstract

Breathing rate is one of the most important vital signals for monitoring health status and reflecting conditions of dangerous diseases. Previous contactless breath monitoring methods were more convenient than contact methods, but they were not suitable for the actual sleeping environment because of the narrow field of vision (FoV). This study proposed a breathing rate monitoring strategy using a mono camera to track and detect sleep apnea phenomena. Breathing rates were first tracked among consecutive image frames. The human body area was then isolated and magnified using a deep neural network (DNN) model before applying the optical flow algorithm to extract and monitor the up and down changes caused by respiration. The most variated directions of the body feature’s motions were detected based on the Principal Component Analysis (PCA) method. Breathing rate was the number of times the signal amplitude peaks per minute. The comparison between predicted values and manually estimated was used for evaluating the accuracy of the method. The accuracy of our method in various light, position, and distance conditions is 2 breaths/minute (<10%) for children and less than 1 breath/minute (<5%) for adults. The study has two main contributions: (1) monitoring breathing rate at home gives comfortable feelings to patients and caregivers, expanding the potential of applying modern technology to clinics, (2) the study has solved the problem of tracking small movements in videos with relatively large FoV in real-time. Perspectively, we will be employed the method in a home-based respiratory rate monitoring system.