Contact-based Sensors Research Articles

Application of regression and remote sensing technology for determining sufficiency of contact-based sensors in long-term SHM of civil structures

Long-span bridges are huge, complex, and vital civil engineering structures for every society. Due to the critical importance of such structures, structural health monitoring (SHM) systems utilizing both contact and non-contact sensor platforms are often considered to measure influential parameters, such as environmental/operational factors and various structural responses. In some circumstances, such as bridge locations, services, weather conditions, harsh environments, and budget constraints, it may not be practical or necessary to utilize all possible sensor systems and measure all parameters, especially environmental/operational (E/O) factors. To devise and implement an affordable SHM program for large-scale civil structures, it is necessary to develop more efficient sensing systems compared to state-of-the-art ones. Against this backdrop, this paper proposes a new methodology for verifying the sufficiency of contact-based E/O sensors installed in long-span bridges using spaceborne remote sensing and regression modeling. The main premise of the proposed methodology is that structural responses obtained from certain remote sensing products enable us to assess the sufficiency of contact sensors and the impacts of both measured and unmeasured E/O conditions. Utilizing structural displacement responses from remote sensing and measured E/O data from contact-based sensors, a supervised regression model using a feedforward artificial neural network is developed to reconstruct or predict displacement responses and to determine the regression accuracy using the R-squared measure. When the accuracy rate is high, one can infer that the contact-based E/O sensors are sufficient; otherwise, it may be essential to install additional E/O sensors and apply the proposed methodology with new information. Real-world long-span bridges are examined to validate the proposed methodology, using displacement responses and recorded temperature data from contact-based thermocouples. The results demonstrate that the methodology offers an effective but affordable system for long-term SHM programs.

Evaluation of Lateral Radar Positioning for Vital Sign Monitoring: An Empirical Study.

Vital sign monitoring is dominated by precise but costly contact-based sensors. Contactless devices such as radars provide a promising alternative. In this article, the effects of lateral radar positions on breathing and heartbeat extraction are evaluated based on a sleep study. A lateral radar position is a radar placement from which multiple human body zones are mapped onto different radar range sections. These body zones can be used to extract breathing and heartbeat motions independently from one another via these different range sections. Radars were positioned above the bed as a conventional approach and on a bedside table as well as at the foot end of the bed as lateral positions. These positions were evaluated based on six nights of sleep collected from healthy volunteers with polysomnography (PSG) as a reference system. For breathing extraction, comparable results were observed for all three radar positions. For heartbeat extraction, a higher level of agreement between the radar foot end position and the PSG was found. An example of the distinction between thoracic and abdominal breathing using a lateral radar position is shown. Lateral radar positions could lead to a more detailed analysis of movements along the body, with the potential for diagnostic applications.

Exploring neural motion transfer for unsupervised remote physiological measurement: A practicality study

Remote Photoplethysmography (rPPG) is a method to measure cardiac activity without the need for any contact-based sensors, garnering attention due to its non-invasive and convenient nature. Addressing the issue of substantial missing data in large-scale datasets, current research is inclined towards unsupervised learning methods. However, prevailing unsupervised learning methods often prioritize inter-sample comparative learning while neglecting individual sample features, severely impacting performance and generalizability. Meanwhile, body movement is one of the most important influencing factors when attempting to extract the rPPG signal from videos. Hence, we embarked on the inaugural exploration of integrating Neural Motion Transfer into unsupervised learning methods for remote physiological measurements, aiming to enrich the inherent motion characteristics and diversity of samples. Employing Neural Motion Transfer, we synthesized videos encompassing diverse movements as a means of data augmentation. Through an in-depth comparison with other synthetic video methods, we extensively analyzed the physiological information within motion-enhanced synthetic videos. We investigated the applicability of these motion-enhanced synthetic videos to unsupervised learning methods and various associated impacts. We conducted extensive experiments on four benchmark datasets. After utilizing motion-enhanced synthetic videos to aid unsupervised training, our approach achieved an improvement of approximately 52% in intra-dataset testing and up to 97% in cross-dataset testing compared to the baseline unsupervised method, achieving the state-of-the-art (SOTA) performance among current unsupervised methods. Our research underscores the importance of neural motion networks in enhancing unsupervised learning methods and highlights the significant potential of synthetic videos.

CalibrationPhys: Self-Supervised Video-Based Heart and Respiratory Rate Measurements by Calibrating Between Multiple Cameras.

Video-based heart and respiratory rate measurements using facial videos are more useful and user-friendly than traditional contact-based sensors. However, most of the current deep learning approaches require ground-truth pulse and respiratory waves for model training, which are expensive to collect. In this paper, we propose CalibrationPhys, a self-supervised video-based heart and respiratory rate measurement method that calibrates between multiple cameras. CalibrationPhys trains deep learning models without supervised labels by using facial videos captured simultaneously by multiple cameras. Contrastive learning is performed so that the pulse and respiratory waves predicted from the synchronized videos using multiple cameras are positive and those from different videos are negative. CalibrationPhys also improves the robustness of the models by means of a data augmentation technique and successfully leverages a pre-trained model for a particular camera. Experimental results utilizing two datasets demonstrate that CalibrationPhys outperforms state-of-the-art heart and respiratory rate measurement methods. Since we optimize camera-specific models using only videos from multiple cameras, our approach makes it easy to use arbitrary cameras for heart and respiratory rate measurements.

Motor and bearing multi-fault diagnosis with sound quality metrics

The occurrence of multi-faults is more critical as compared to single faults, and it creates unfavourable working conditions. The number of contact-based sensors and their placement plays a crucial role in diagnosing the multi-faults. The use of non-contact-based acoustic sensors could be a cost-effective potential solution to this problem. In this work, two rotating components, a motor and a separate bearing of a system situated away from the motor, were considered for forming system-level multi-fault conditions. The acoustic signature of various multi-fault conditions was acquired at different rotational speeds. Thereafter, a moving window was employed on the acquired raw acoustic signals to extract statistical and sound quality features. A feature fusion approach was implemented on the extracted features, and a machine learning model was trained with optimised hyperparameters. A comparative study was performed to analyse the model's performance, which was trained with the extracted statistical, sound quality and fused features. It was found that the proposed feature fusion-based methodology was helpful for diagnosing multi-faults with acoustic signatures. The importance of psychoacoustical features on model performance was also observed. It mitigated the complexity of mounting the sensors and showed the potential usage of sound quality metrics for multi-fault diagnosis.

Depression Recognition Using Remote Photoplethysmography From Facial Videos

Depression is a mental illness that may be harmful to an individual's health. The detection of mental health disorders in the early stages and a precise diagnosis are critical to avoid social, physiological, or psychological side effects. This work analyzes physiological signals to observe if different depressive states have a noticeable impact on the blood volume pulse (BVP) and the heart rate variability (HRV) response. Although typically, HRV features are calculated from biosignals obtained with contact-based sensors such as wearables, we propose instead a novel scheme that directly extracts them from facial videos, just based on visual information, removing the need for any contact-based device. Our solution is based on a pipeline that is able to extract complete remote photoplethysmography signals (rPPG) in a fully unsupervised manner. We use these rPPG signals to calculate over 60 statistical, geometrical, and physiological features that are further used to train several machine learning regressors to recognize different levels of depression. Experiments on two benchmark datasets indicate that this approach offers comparable results to other audiovisual modalities based on voice or facial expression, potentially complementing them. In addition, the results achieved for the proposed method show promising and solid performance that outperforms hand-engineered methods and is comparable to deep learning-based approaches.

Contactless camera-based AHI score estimation in SAS patients

Abstract Sleep apnea syndrome (SAS) is a common sleeprelated breathing disorder characterized by recurring cessations of airflow during sleep. The gold standard for diagnosing SAS is polysomnography (PSG) which requires the patient to spend one or several nights in a sleep clinic. A PSG involves a significant amount of contact-based sensors, which leads to discomfort and deviations in sleep behavior. In this work, a contactless, multispectral camera-based approach for the autonomous detection of events of nocturnal airflow reduction is presented. The detected events are further employed in estimators of sleep diagnostic metrics, such as the apnea-hypopnea index (AHI) and the SAS stage. The AHI estimation resulted in a Pearson correlation coefficient of r = 0.9993. The SAS stage estimator correctly predicted the SAS stage for all three recruited patients.

Investigation of Temperature Effects into Long-Span Bridges via Hybrid Sensing and Supervised Regression Models

Temperature is an important environmental factor for long-span bridges because it induces thermal loads on structural components that cause considerable displacements, stresses, and structural damage. Hence, it is critical to acquire up-to-date information on the status, sustainability, and serviceability of long-span bridges under daily and seasonal temperature fluctuations. This paper intends to investigate the effects of temperature variability on structural displacements obtained from remote sensing and represent their relationship using supervised regression models. In contrast to other studies in this field, one of the contributions of this paper is to leverage hybrid sensing as a combination of contact and non-contact sensors for measuring temperature data and structural responses. Apart from temperature, other unmeasured environmental and operational conditions may affect structural displacements of long-span bridges separately or simultaneously. For this issue, this paper incorporates a correlation analysis between the measured predictor (temperature) and response (displacement) data using a linear correlation measure, the Pearson correlation coefficient, as well as nonlinear correlation measures, namely the Spearman and Kendall correlation coefficients and the maximal information criterion, to determine whether the measured environmental factor is dominant or other unmeasured conditions affect structural responses. Finally, three supervised regression techniques based on a linear regression model, Gaussian process regression, and support vector regression are considered to model the relationship between temperature and structural displacements and to conduct the prediction process. Temperature and limited displacement data related to three long-span bridges are used to demonstrate the results of this research. The aim of this research is to assess and realize whether contact-based sensors installed in a bridge structure for measuring environmental and/or operational factors are sufficient or if it is necessary to consider further sensors and investigations.

Elimination of Thermal Effects from Limited Structural Displacements Based on Remote Sensing by Machine Learning Techniques

Confounding variability caused by environmental and/or operational conditions is a big challenge in the structural health monitoring (SHM) of large-scale civil structures. The elimination of such variability is of paramount importance in avoiding economic and human losses. Machine learning-aided data normalization provides a good solution to this challenge. Despite proper studies on data normalization using structural responses/features acquired from contact-based sensors, this issue has not been explored properly via new features, such as displacement responses from remote sensing products, including synthetic aperture radar (SAR) images. Hence, the main aim of this work was to eliminate environmental variability, particularly thermal effects, from different and limited structural displacements retrieved from a few SAR images related to long-term health monitoring programs of long-span bridges. For this purpose, we conducted a comprehensive comparative study to investigate two supervised and two unsupervised data normalization algorithms. The supervised algorithms were based on Gaussian process regression (GPR) and support vector regression (SVR), for which temperature records acquired from contact temperature sensors and structural displacements retrieved from spaceborne remote sensors produce univariate predictor (input) and response (output) data for the regression problem. For the unsupervised algorithms, this paper employed principal component analysis (PCA) and proposed a deep autoencoder (DAE), both of which conform with unsupervised reconstruction-based data normalization. In contrast to the GPR- and SVR-based data normalization algorithms, both the PCA and DAE methods only consider the SAR-based displacement (output) data without any requirement of the environmental and/or operational (input) data. Limited displacement sets of long-span bridges from a few SAR images of Sentinel-1A, related to long-term SHM programs, were considered to assess the aforementioned techniques. Results demonstrate that the proposed DAE-aided data normalization is the best approach to remove thermal effects and other unmeasured environmental and/or operational variability.

Physics-Guided Real-Time Full-Field Vibration Response Estimation from Sparse Measurements Using Compressive Sensing.

In civil, mechanical, and aerospace structures, full-field measurement has become necessary to estimate the precise location of precise damage and controlling purposes. Conventional full-field sensing requires dense installation of contact-based sensors, which is uneconomical and mostly impractical in a real-life scenario. Recent developments in computer vision-based measurement instruments have the ability to measure full-field responses, but implementation for long-term sensing could be impractical and sometimes uneconomical. To circumvent this issue, in this paper, we propose a technique to accurately estimate the full-field responses of the structural system from a few contact/non-contact sensors randomly placed on the system. We adopt the Compressive Sensing technique in the spatial domain to estimate the full-field spatial vibration profile from the few actual sensors placed on the structure for a particular time instant, and executing this procedure repeatedly for all the temporal instances will result in real-time estimation of full-field response. The basis function in the Compressive Sensing framework is obtained from the closed-form solution of the generalized partial differential equation of the system; hence, partial knowledge of the system/model dynamics is needed, which makes this framework physics-guided. The accuracy of reconstruction in the proposed full-field sensing method demonstrates significant potential in the domain of health monitoring and control of civil, mechanical, and aerospace engineering systems.

Data-driven full-field vibration response estimation from limited measurements in real-time using dictionary learning and compressive sensing

Full-field online sensing provides dense spatial information of vibrating structures in real-time. Such compact sensing is essential to pinpoint the location of possible damage and for real-time active/semi-active control of structures where the vibration responses are necessary for controller feedback. To accurately harness these dense sensor time history, contact-based sensors need to be installed in a dense way that is cost-inefficient and infeasible for a real-life scenario. Computer vision-based technologies like Digital Image Correlation (DIC), and edge tracking methods are capable of capturing dense responses. However, when the structures are in operating condition, long-term implementation of such techniques could be expensive and, at times, impractical. In this paper, to address these problems, we propose a framework to estimate full-field vibration responses from the time histories of a few sensors. In this framework, we use the compressive sensing technique in the spatial domain, where the full-field spatial signal is recovered from a handful of sensors for a definite time instant and repeating this procedure for all the time instants will lead to online full-field response estimation. This framework does not require any prior information on the structural model, making it entirely data-driven. This framework learns the spatial basis functions needed for compressive sensing operations from the training data using the Dictionary learning technique. We also address the optimal/minimum number of sensors required to accurately estimate the dense responses, which is based on the Singular Value Decomposition (SVD) of the basis matrix. This technique primarily applies to Linear Time-Invariant (LTI) systems, and implementation to Linear Time-Varying (LTV) systems could be explored in future work. We validate the proposed method numerically on a simply supported beam (1D system) and a simply supported plate (2D system) and experimentally on a cantilever beam. The reconstruction accuracy in the proposed full-field sensing shows excellent potential in health monitoring and control of aerospace, mechanical, and civil systems.

Machine-Learning-Based Human Fall Detection Using Contact- and Noncontact-Based Sensors.

Automated human fall detection is an essential area of research due to its health implications in day-to-day life. Detecting and timely reporting of human falls may lead to saving human life. In this paper, fall detection has been targeted using machine-learning-based approaches from two perspectives regarding data sources, that is, contact-based and noncontact-based sensors. In both of these cases, various methods based on deep learning and machine learning techniques have been attempted, and their performances were compared. The approaches analyze data in fixed time windows and extract features in the time domain or spatial domain which obtain relative information between consecutive data samples. After experimentation, it was found that the proposed noncontact-based sensor techniques outperformed the contact-based sensor techniques by a margin of 1.82%. After this, it was also found that the noncontact-based sensor techniques outperformed the state of the art of noncontact-based sensor results by a margin of 3.15%. To better suit these techniques for real-world applications, embedded board implementation and privacy preservation of subject by using advanced methods such as compressive sensing and feature encoding need to be attempted.

Employing vision-based sensing for long-term monitoring

Despite the crucial role of structural health monitoring (SHM), traditional contact-based sensors are costly and lacking automation. Vision-based sensors have recently emerged as a potential substitute, due to their non-contact nature and low cost. However, investigations lack validating their long-term performance. This study assesses vision-based sensing for robust and efficient long-term displacement monitoring. Additionally, the suitability of various machine learning (ML) algorithms in automatically extracting information from the generated data are examined. A first experiment examines the capability to monitor ambiently excited structures over long periods. The parameters assessed are: a) noise and drift (e.g., related to environmental changes such as temperature, humidity, and lighting); and b) obtainable displacement resolution related to ambient excitation. Then, a second experiment examines the capability to monitor dynamically excited structures over long periods (via the employment of an artificial excitation, e.g., an eccentrically loaded mass motor). Here, the following parameters assessed are the: a) frequency bandwidth range; b) frequency resolution; c) displacement resolution related to dynamic excitation; and d) maximum number monitored points for given computational resources. Finally, for processing the generated data, the following ML algorithms are examined: a) Artificial Neural Networks (ANNs); b) support vector machines (SVMs); c) decision trees; and d) Convolutional Neural Networks (CNNs). Concerning long-term monitoring, the paper found that non-contact sensing had comparable accuracy with traditional contact-based sensors. About the ML models, the CNNs were found to be advantageous. Whilst this study was carried out on a small-scale structure, the potential of vision-based sensing for long-term monitoring of full-scale structures was highlighted.

A Systematic Review on Emotion Recognition System Using Physiological Signals: Data Acquisition and Methodology

Emotion recognition systems (ERS) have become a popular research field to contribute to human-machine interaction in different areas. Different kinds of applications on ERS can serve different purposes. Artificial intelligence (AI) and the internet of things (IoT) are the technologies behind such applications. The main objective of this study is to enable researchers and developers to search for the most suitable options to develop an emotional state recognition system. More specifically, this paper presents work on ERS, which is built using physiological signals extracted from biosensors. It also presents details of how the extracted physiological signals are used to identify the user's emotional state. In this review, the sensors are categorized based on their modality: contact-based sensors and contactless sensors. Next, the ERS process is presented together with the reported results for each described technique. Articles from four different research databases were reviewed, of which 147 articles from 2009 to 2021 were referred to that are related to ERS using physiological signals. This paper should be significant for researchers developing systems that integrate human emotion recognition capability. The findings reported here can guide them in choosing suitable methods for their systems. Doi: 10.28991/ESJ-2022-06-05-017 Full Text: PDF

Measuring vertical displacement using laser lines and cameras

Measuring displacements in model tests typically involves contact-based sensors such as linear potentiometers, where contact between two moving parts occurs at the sensing point. The sensor's finite mass, the limited stiffness of the beams and the clamping mechanism, and the slippage and hinging of the sensor body could affect the object's response and lead to measurement errors. Also, the physical mounting rack required to hold these sensors often obstructs the view and makes significant areas unavailable for conducting some other essential investigations. The advancement in high-speed, high-resolution and reasonably priced rugged cameras makes it feasible to obtain better displacement measurements by image analysis. This paper introduces a non-contact method that works by video recording the projection of laser lines on a test object to measure static and dynamic vertical displacements. The technique produces a continuous settlement distribution along the laser line passing through multiple objects of interest. This paper presents the theory for converting laser line images to displacements. The new method's validity is demonstrated by comparing the results from other measurement techniques: hand measurements, linear potentiometers and three-dimensional stereophotogrammetry.

A Noncontact Vital Signs (NCVS) System for Potential Patient Monitoring Enabled by Robust Software Defined Radio (SDR)

This research proposes a robust non-contact vital signs (NCVS) sensor system for continuously monitoring the human respiration rate (RR) and heart rate (HR) within a distance of 1 to 2 meters. The novel Doppler-based NCVS sensor system is realized using an SDR (software defined radio) unit with optimized transmit/receive gain in commercial broadband, which filters intermediate frequency (IF) and operates at 2.4 GHz ISM band using a pair of small antennas. When compared with the vital signs data measured by traditional contact-based sensors, the NCVS sensing system demonstrates excellent accuracy in real-time RR/HR monitoring within 0.5/3 BPM (breath/beat per minute). We have obtained an IRB (Internal Review Board) approval to start a small clinical trial at Texas Tech University Health Sciences Center (TTUHSC) soon, hoping to use this system to effectively monitor vital signs of COVID-19 patients and to help telehealth delivery in the post-COVID-19 era.

SPIDERS[formula omitted]: A light-weight, wireless, and low-cost glasses-based wearable platform for emotion sensing and bio-signal acquisition

We present a System for Processing In-situ Bio-signal Data for Emotion Recog-nition and Sensing (SPIDERS+) – a low-cost, wireless, glasses-based platform for continuous in-situ monitoring of user’s facial expressions (apparent emotions) and real emotions. We present algorithms to provide four core functions to detect eye shape and eyebrow movements, pupillometry, zygomaticus muscle movements, and head movements, using the bio-signals acquired from three non-contact sensors (IR camera, proximity sensor, and IMU). SPIDERS+ distinguishes between different classes of apparent and real emotion states based on the aforementioned four bio-signals. We prototype advanced functionalities including facial expression detection and real emotion classification with a facial expression detector based on landmarks and optical flow that leverages changes in a user’s eyebrows and eye shapes to achieve the average true positive rate up to 83.87%, as well as a pupillometry-based real emotion classifier with higher accuracy than existing low-cost wearable platforms that use sensors requiring skin contact. In addition, SPIDERS+ also includes optional contact-based sensors such as photoplethysmography (PPG) and multi-channel electroencephalogram (EEG) to monitor other bio-signals. SPIDERS+ costs less than $20 to assemble and can continuously run for up to 9 h before recharging. We design, implement and evaluate accompanying desktop and smartphone applications to demonstrate that SPIDERS+ is a truly wireless and portable platform that can impact a wide range of applications, where the knowledge of the user’s emotional state is critical.

Computer vision‐based real‐time cable tension estimation in Dubrovnik cable‐stayed bridge using moving handheld video camera

Cables are essential components of the cable-stayed bridges as they serve as the main load-bearing component. Hence, continuous monitoring of such cables becomes necessary as they are vulnerable to the fatigue damage induced by dynamic loads. Sensors are attached to the cables to examine the health of the cables; however, these contact-based sensors can malfunction in harsh weather condition, which makes impossible to estimate the cable health in such unfavorable condition. Therefore, in this paper, we propose a completely noncontact video-based stay-cable tension measurement technique where the video is recorded using a moving handheld camera at a significant distance from the structure itself. Here, the cable tension is determined from vibration-based measurement, but the vibration of the cable recorded in the video includes the true vibration of the cable along with the camera motion. Hence, we amalgamated a series of image processing techniques to nullify the camera movement. First, we detect the camera movement based on the movement of the bridge deck and pylon, which are fixed objects, using Kanade–Lucas–Tomasi (KLT) feature tracking algorithm. Then we nullify the camera movement by using the affine transformation matrix obtained by random sample consensus (RANSAC) algorithm. Subsequently from the steady video, the cable motions are estimated using the phase-based motion estimation technique. From the time history of the cable vibration, real-time frequency variations are estimated using Short-Time Fourier Transform (STFT). Finally, the real-time tension is determined from this dominant frequency variation history using the taut-string theory. This paper shows the significant potential of camera-based sensing techniques in structural health monitoring as the mean estimated tension and the design cable tension are found to be comparable.

A Novel Method of Using Bifilar Spiral Resonator for Designing Thin Robust Flexible Glucose Sensors

Nowadays, robust sensors for glucose-sensing application are almost a necessity for every diabetic individual. In this work, a (20 mm $\times10$ mm) contact-based sensor has been successfully realized on a thin and flexible polyamide substrate, with the sensing area being a bifilar spiral resonator (BSR). The proposed sensor was based on detecting resonance frequencies shifts at ultrahigh frequencies (UHFs) as a result of changes in the glucose concentration. The BSR acts as a cascaded metasurface which, at around the resonant frequency, forms a plasmon dispersion at the interface between a glucose solution and the BSR. An empirical formula has been developed to express the sensing sensitivity as a function of the loss factor, the oscillator strengths and the steady state permittivity. The model has been experimentally validated with an in vitro measurement on an aqueous glucose solution and an ex-vivo measurement on a serum blood solution. The measured results suggest that there exists a positive and linear correlation between glucose concentration and the resonant frequency shift within the clinical diabetic range. The sensor sensitivity was 250 megahertz (MHz)/(mg/mL) for the aqueous glucose solution and 130 MHz/(mg/mL) for the serum blood along with a $Q$ -factor of 20. Overall, the measured results were highly consistent with our theoretical expectation. Moreover, the proposed sensor was highly resistant to bending losses.

A Remote Respiration Rate Measurement Method for Non-Stationary Subjects Using CEEMDAN and Machine Learning

Respiratory Rate (RR) monitoring can inform healthcare providers of early indicators of critical illnesses. However, the obtrusive nature of contact-based sensors for RR monitoring makes them uncomfortable for extended use and vulnerable to movement-derived noise. Hence, camera-based approaches have attracted considerable attention as they enable contact-free RR monitoring. This paper presents an improved non-contact method for RR monitoring that leverages camera derived remote photoplethysmography (rPPG) to measure RR. Unlike previous work, the proposed method supports subject movement during monitoring. We apply Independent Component Analysis (ICA) on the RGB channels of facial videos to distinguish the source (i.e. PPG signal) from noise. We use the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) scheme to decompose the selected ICA output into its Intrinsic Mode Functions (IMFs). We propose a Machine Learning (ML) algorithm to select the IMF that best reflects the RR. We evaluated the proposed method on 200 facial videos collected from 10 subjects. Our approach decreased the RMSE by at least 39.6% compared to state-of-the-art techniques when subjects were stationary. For subjects in movement, we achieved an RMSE of 2.30 BPM (breaths/min). The proposed method can facilitate non-contact continuous measurement of RR for various clinical and home-based healthcare solutions including the monitoring of infants in neonatal intensive care, elderly individuals in senior care centers, patients in hospital emergency waiting rooms, and prisoners on suicide watch.