Exploiting Weak Head Movements for Camera-based Respiration Detection

Deep learning and remote photoplethysmography powered advancements in contactless physiological measurement

In recent decades, there has been ongoing development in the application of computer vision (CV) in the medical field. As conventional contact-based physiological measurement techniques often restrict a patient's mobility in the clinical environment, the ability to achieve continuous, comfortable and convenient monitoring is thus a topic of interest to researchers. One type of CV application is remote imaging photoplethysmography (rPPG), which can predict vital signs using a video or image. While contactless physiological measurement techniques have an excellent application prospect, the lack of uniformity or standardization of contactless vital monitoring methods limits their application in remote healthcare/telehealth settings. Several methods have been developed to improve this limitation and solve the heterogeneity of video signals caused by movement, lighting, and equipment. The fundamental algorithms include traditional algorithms with optimization and developing deep learning (DL) algorithms. This article aims to provide an in-depth review of current Artificial Intelligence (AI) methods using CV and DL in contactless physiological measurement and a comprehensive summary of the latest development of contactless measurement techniques for skin perfusion, respiratory rate, blood oxygen saturation, heart rate, heart rate variability, and blood pressure.

An Evaluation of Non-Contact Photoplethysmography-Based Methods for Remote Respiratory Rate Estimation

The respiration rate (RR) is one of the physiological signals deserving monitoring for assessing human health and emotional states. However, traditional devices, such as the respiration belt to be worn around the chest, are not always a feasible solution (e.g., telemedicine, device discomfort). Recently, novel approaches have been proposed aiming at estimating RR in a less invasive yet reliable way, requiring the acquisition and processing of contact or remote Photoplethysmography (contact reference and remote-PPG, respectively). The aim of this paper is to address the lack of systematic evaluation of proposed methods on publicly available datasets, which currently impedes a fair comparison among them. In particular, we evaluate two prominent families of PPG processing methods estimating Respiratory Induced Variations (RIVs): the first encompasses methods based on the direct extraction of morphological features concerning the RR; and the second group includes methods modeling respiratory artifacts adopting, in the most promising cases, single-channel blind source separation. Extensive experiments have been carried out on the public BP4D+ dataset, showing that the morphological estimation of RIVs is more reliable than those produced by a single-channel blind source separation method (both in contact and remote testing phases), as well as in comparison with a representative state-of-the-art Deep Learning-based approach for remote respiratory information estimation.

Motion- Based Respiratory Rate Estimation with Motion Artifact Removal Using Video of Face and Upper Body

Respiratory rate (RR) is a significant indicator of health conditions. Remote contactless measurement of RR is gaining popularity with recent respiratory tract infection awareness. Among various methods of contactless RR measurement, a video of an individual can be used to obtain an instantaneous RR. In this paper, we introduce an RR estimation based on the subtle motion of the head or upper chest captured on an RGB camera. Motion-based respiratory monitoring allows us to acquire RR from individuals with partial face coverings, such as glasses or a face mask. However, motion-based RR estimation is vulnerable to the subject's voluntary movement. In this work, adaptive selection between face and chest regions plus a motion artifact removal technique enables us to obtain a much cleaner respiratory signal from the video recordings. The average mean absolute error (MAE) for controlled and natural breathing is 1.95 BPM using head motion only and 1.28 BPM using chest motion only. Our results demonstrate the possibility of continuous monitoring of breathing rate in real-time with any personal device equipped with an RGB camera, such as a laptop or a smartphone.

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

Respiratory monitoring is receiving growing interest in different fields of use, ranging from healthcare to occupational settings. Only recently, non-contact measuring systems have been developed to measure the respiratory rate (fR) over time, even in unconstrained environments. Promising methods rely on the analysis of video-frames features recorded from cameras. In this work, a low-cost and unobtrusive measuring system for respiratory pattern monitoring based on the analysis of RGB images recorded from a consumer-grade camera is proposed. The system allows (i) the automatized tracking of the chest movements caused by breathing, (ii) the extraction of the breathing signal from images with methods based on optical flow (FO) and RGB analysis, (iii) the elimination of breathing-unrelated events from the signal, (iv) the identification of possible apneas and, (v) the calculation of fR value every second. Unlike most of the work in the literature, the performances of the system have been tested in an unstructured environment considering user-camera distance and user posture as influencing factors. A total of 24 healthy volunteers were enrolled for the validation tests. Better performances were obtained when the users were in sitting position. FO method outperforms in all conditions. In the fR range 6 to 60 breaths/min (bpm), the FO allows measuring fR values with bias of −0.03 ± 1.38 bpm and −0.02 ± 1.92 bpm when compared to a reference wearable system with the user at 2 and 0.5 m from the camera, respectively.