Remote PPG Research Articles

What Remote PPG Oximetry Tells Us about Pulsatile Volume?

While pulse oximetry using remote photoplethysmography (rPPG) is used in medicine and consumer health, sound theoretical foundations for this methodology are not established. Similarly to traditional pulse oximetry, rPPG oximetry uses two wavelengths to calculate the tissue oxygenation using the so-called ratio-of-ratios, R. However, the relationship between R and tissue oxygenation has not been derived analytically. As such, rPPG oximetry relies mostly on empirical methods. This article aimed to build theoretical foundations for pulse oximetry in rPPG geometry. Using the perturbation approach in diffuse approximation for light propagation in tissues, we obtained an explicit expression of the AC/DC ratio for the rPPG signal. Based on this ratio, the explicit expression for "ratio-of-ratios" was obtained. We have simulated the dependence of "ratio-of-ratios" on arterial blood saturation across a wide range (SaO2 = 70-100%) for several commonly used R/IR light sources (660/780, 660/840, 660/880, and 660/940 nm) and found that the obtained relationship can be modeled by linear functions with an extremely good fit (R2 = 0.98-0.99) for all considered R/IR pairs. Moreover, the location of the pulsatile volume can be extracted from rPPG data. From experimental data, we found that the depth of blood pulsations in the human forehead can be estimated as 0.6 mm on the arterial side, which points to the papillary dermis/subpapillary vascular plexus origin of the pulsatile volume.

A Fast FPGA Hardware Accelerator for Remote Heart Rate Detection Based on RGB Vision.

A fast hardware accelerator is created by this work via field programmable gate array (FPGA) to estimate heart rate (HR) through the video recorded by a RGB camera based on the technology of remote photoplethysmography (rPPG). The method of rPPG acquires physiological signals of a human body by analyzing the subtle color changes on the surface of the human skin. The hardware implementation of rPPG to estimate HR is proposed herein to aim for a much faster calculation speed than software for a number of applications, like heart failure pre-warning of an in-action athlete and drowsiness detection of a driver. In this accelerator, ICA (Independent Component Analysis) is used to recover the blood volume pulse from the raw signals of remote PPG, and then obtain the heart rate value. The architecture of the hardware circuit is described in Verilog HDL and verified by Quartus II, and also implemented in an Altera DE10-Standard FPGA board, which consists of image capture, heart rate algorithm and image display. A TRDB-D5M camera is utilized for image capture. Two experiments were conducted with image collecting duration of 16 seconds and 8 seconds respectively, and the commercial device Omron HEM-6111 was used as the golden value. The proposed system achieves an accuracy in (ME ± 1.96SD) of -0.76 ± 5.09 and -0.70 ± 8.71 bpm in the short periods of 16-second and 8-second versions, respectively, which outperforms all the reported prior works in combined computation time and accuracy.

Remote rhythm monitoring using a photoplethysmography smartphone application after cardioversion for atrial fibrillation.

Direct current cardioversion (DCCV) is a commonly utilized rhythm control technique for atrial fibrillation. Follow-up typically comprises a hospital visit for 12-lead electrocardiogram (ECG) two weeks post-DCCV. We report the feasibility, costs, and environmental benefit of remote photoplethysmography (PPG) monitoring as an alternative. We retrospectively analysed DCCV cases at our centre from May 2020 to October 2022. Patients were stratified into those with remote PPG follow-up and those with traditional 12-lead ECG follow-up. Monitoring type was decided by the specialist nurse performing the DCCV at the time of the procedure after discussing with the patient and offering them both options if appropriate. Outcomes included the proportion of patients who underwent PPG monitoring, patient compliance and experience, and cost, travel, and environmental impact. Four hundred sixteen patients underwent 461 acutely successful DCCV procedures. Two hundred forty-six underwent PPG follow-up whilst 214 underwent ECG follow-up. Patient compliance was high (PPG 89.4% vs. ECG 89.8%; P > 0.999) and the majority of PPG users (90%) found the app easy to use. Sinus rhythm was maintained in 71.1% (PPG) and 64.7% (ECG) of patients (P = 0.161). Twenty-nine (11.8%) PPG patients subsequently required an ECG either due to non-compliance, technical failure, or inconclusive PPG readings. Despite this, mean healthcare costs (£47.91 vs. £135 per patient; P < 0.001) and median cost to the patient (£0 vs. £5.97; P < 0.001) were lower with PPG. Median travel time per patient (0 vs. 44 min; P < 0.001) and CO2 emissions (0 vs. 3.59 kg; P < 0.001) were also lower with PPG. No safety issues were identified. Remote PPG monitoring is a viable method of assessing for arrhythmia recurrence post-DCCV. This approach may save patients significant travel time, reduce environmental CO2 emission, and be cost saving in a publicly-funded healthcare system.

Observation of blood motion in the internal jugular vein by contact and contactless photoplethysmography during physiological testing: case studies.

Central venous pressure is an estimate of right atrial pressure and is often used to assess hemodynamic status. However, since it is measured invasively, non-invasive alternatives would be of great utility. The aim of this preliminary study was a) to investigate whether photoplethysmography (PPG) can be used to characterize venous system fluid motion and b) to find the model for venous blood volume modulations. For this purpose, we monitored the internal jugular veins using contact (cPPG) and video PPG during clinically validated physiological tests: abdominojugular test (AJT) and breath holding (BH). Video PPG and cPPG signals were captured simultaneously on the left and right sides of the neck, respectively. ECG was also captured using the same clinical monitor as cPPG. Two volunteers underwent AJT and BH with head up/down, each with: baseline (15s), experiment (15s), and recovery (15s). Video PPG was split into remote PPG (rPPG) and micromotion detection. All signal modalities were significantly affected by physiological testing. Moreover, cPPG and micromotion waveforms exhibited primary features of jugular vein waveforms and, therefore, have great potential for venous blood flow monitoring. Specifically, remote patient monitoring applications may be enabled by this methodology, facilitating physical collection without a specially trained care provider.

Face2PPG: An Unsupervised Pipeline for Blood Volume Pulse Extraction from Faces.

Photoplethysmography (PPG) signals have become a key technology in many fields, such as medicine, well-being, or sports. Our work proposes a set of pipelines to extract remote PPG signals (rPPG) from the face robustly, reliably, and configurable. We identify and evaluate the possible choices in the critical steps of unsupervised rPPG methodologies. We assess a state-of-the-art processing pipeline in six different datasets, incorporating important corrections in the methodology that ensure reproducible and fair comparisons. In addition, we extend the pipeline by proposing three novel ideas; 1) a new method to stabilize the detected face based on a rigid mesh normalization; 2) a new method to dynamically select the different regions in the face that provide the best raw signals, and 3) a new RGB to rPPG transformation method, called Orthogonal Matrix Image Transformation (OMIT) based on QR decomposition, that increases robustness against compression artifacts. We show that all three changes introduce noticeable improvements in retrieving rPPG signals from faces, obtaining state-of-the-art results compared with unsupervised, non-learning-based methodologies and, in some databases, very close to supervised, learning-based methods. We perform a comparative study to quantify the contribution of each proposed idea. In addition, we depict a series of observations that could help in future implementations.

Multi-wavelength SPAD photoplethysmography for cardio-respiratory monitoring

There is a growing interest in photoplethysmography (PPG) for the continuous monitoring of cardio-respiratory signals by portable instrumentation aimed at the early diagnosis of cardiovascular diseases. In this context, it is conceivable that PPG sensors working at different wavelengths simultaneously can optimize the identification of apneas and the quantification of the associated heart-rate changes or other parameters that depend on the PPG shape (e.g., systematic vascular resistance and pressure), when evaluating the severity of breathing disorders during sleep and in general for health monitoring. Therefore, the objective of this work is to present a novel pulse oximeter that provides synchronous data logging related to three light wavelengths (green, red, and infrared) in transmission mode to optimize both heart rate measurements and a reliable and continuous assessment of oxygen saturation. The transmission mode is considered more robust over motion artifacts than reflection mode, but current pulse oximeters cannot employ green light in transmission mode due to the high absorbance of body tissues at this wavelength. For this reason, our device is based on a Single-Photon Avalanche Diode (SPAD) with very short deadtime (less than 1 ns) to have, at the same time, the single photon sensitivity and high-count rate that allows acquiring all the wavelengths of interest on the same site and in transmission mode. Previous studies have shown that SPAD cameras can be used for measuring the heart rate through remote PPG, but oxygen saturation and heart-rate measures through contact SPAD-based PPG sensors have never been addressed so far. The results of the preliminary validation on six healthy volunteers reflect the expected physiological phenomena, providing rms errors in the Inter Beat Interval estimation smaller than 70 ms (with green light) and a maximum error in the oxygen saturation smaller than 1% during the apneas. Our prototype demonstrates the reliability of SPAD-based devices for continuous long-term monitoring of cardio-respiratory variables as an alternative to photodiodes especially when minimal area and optical power are required.

Contactless Camera-Based Sleep Staging: The HealthBed Study.

Polysomnography (PSG) remains the gold standard for sleep monitoring but is obtrusive in nature. Advances in camera sensor technology and data analysis techniques enable contactless monitoring of heart rate variability (HRV). In turn, this may allow remote assessment of sleep stages, as different HRV metrics indirectly reflect the expression of sleep stages. We evaluated a camera-based remote photoplethysmography (PPG) setup to perform automated classification of sleep stages in near darkness. Based on the contactless measurement of pulse rate variability, we use a previously developed HRV-based algorithm for 3 and 4-class sleep stage classification. Performance was evaluated on data of 46 healthy participants obtained from simultaneous overnight recording of PSG and camera-based remote PPG. To validate the results and for benchmarking purposes, the same algorithm was used to classify sleep stages based on the corresponding ECG data. Compared to manually scored PSG, the remote PPG-based algorithm achieved moderate agreement on both 3 class (Wake-N1/N2/N3-REM) and 4 class (Wake-N1/N2-N3-REM) classification, with average κ of 0.58 and 0.49 and accuracy of 81% and 68%, respectively. This is in range with other performance metrics reported on sensing technologies for wearable sleep staging, showing the potential of video-based non-contact sleep staging.

A Study of Projection-Based Attentive Spatial–Temporal Map for Remote Photoplethysmography Measurement

The photoplethysmography (PPG) signal contains various information that is related to CVD (cardiovascular disease). The remote PPG (rPPG) is a method that can measure a PPG signal using a face image taken with a camera, without a PPG device. Deep learning-based rPPG methods can be classified into three main categories. First, there is a 3D CNN approach that uses a facial image video as input, which focuses on the spatio-temporal changes in the facial video. The second approach is a method that uses a spatio-temporal map (STMap), and the video image is pre-processed using the point where it is easier to analyze changes in blood flow in time order. The last approach uses a preprocessing model with a dichromatic reflection model. This study proposed the concept of an axis projection network (APNET) that complements the drawbacks, in which the 3D CNN method requires significant memory; the STMap method requires a preprocessing method; and the dyschromatic reflection model (DRM) method does not learn long-term temporal characteristics. We also showed that the proposed APNET effectively reduced the network memory size, and that the low-frequency signal was observed in the inferred PPG signal, suggesting that it can provide meaningful results to the study when developing the rPPG algorithm.

Effectiveness of Remote PPG Construction Methods: A Preliminary Analysis.

The contactless recording of a photoplethysmography (PPG) signal with a Red-Green-Blue (RGB) camera is known as remote photoplethysmography (rPPG). Studies have reported on the positive impact of using this technique, particularly in heart rate estimation, which has led to increased research on this topic among scientists. Therefore, converting from RGB signals to constructing an rPPG signal is an important step. Eight rPPG methods (plant-orthogonal-to-skin (POS), local group invariance (LGI), the chrominance-based method (CHROM), orthogonal matrix image transformation (OMIT), GREEN, independent component analysis (ICA), principal component analysis (PCA), and blood volume pulse (PBV) methods) were assessed using dynamic time warping, power spectrum analysis, and Pearson’s correlation coefficient, with different activities (at rest, during exercising in the gym, during talking, and while head rotating) and four regions of interest (ROI): the forehead, the left cheek, the right cheek, and a combination of all three ROIs. The best performing rPPG methods in all categories were the POS, LGI, and OMI methods; each performed well in all activities. Recommendations for future work are provided.

Non-Contact Atrial Fibrillation Detection From Face Videos by Learning Systolic Peaks.

We propose a non-contact approach for atrial fibrillation (AF) detection from face videos. Face videos, electrocardiography (ECG), and contact photoplethysmography (PPG) from 100 healthy subjects and 100 AF patients are recorded. Data recordings from healthy subjects are all labeled as healthy. Two cardiologists evaluated ECG recordings of patients and labeled each recording as AF, sinus rhythm (SR), or atrial flutter (AFL). We use the 3D convolutional neural network for remote PPG monitoring and propose a novel loss function (Wasserstein distance) to use the timing of systolic peaks from contact PPG as the label for our model training. Then a set of heart rate variability (HRV) features are calculated from the inter-beat intervals, and a support vector machine (SVM) classifier is trained with HRV features. Our proposed method can accurately extract systolic peaks from face videos for AF detection. The proposed method is trained with subject-independent 10-fold cross-validation with 30 s video clips and tested on two tasks. 1) Classification of healthy versus AF: the accuracy, sensitivity, and specificity are 96.00%, 95.36%, and 96.12%. 2) Classification of SR versus AF: the accuracy, sensitivity, and specificity are 95.23%, 98.53%, and 91.12%. In addition, we also demonstrate the feasibility of non-contact AFL detection. We achieve good performance of non-contact AF detection by learning systolic peaks. non-contact AF detection can be used for self-screening of AF symptoms for suspectable populations at home or self-monitoring of AF recurrence after treatment for chronic patients.

Remote Photoplethysmography and Heart Rate Estimation by Dynamic Region of Interest Tracking.

Remote photoplethysmography (PPG) estimates vital signs by measuring changes in the reflected light from the human skin. Compared to traditional PPG techniques, remote PPG enables contactless measurement at a reduced cost. In this paper, we propose a novel method to extract remote PPG signals and heart rate from videos. We propose an algorithm to dynamically track regions of interest (ROIs) and combine the signals from all ROIs based on signal qualities. To maintain a stable frame rate and accuracy, we propose a dynamic down-sampling approach, which makes our system robust to the different video resolutions and user-camera distances. We also propose the strategy of adaptive measurement time to estimate HR, which can achieve comparable accuracy in HR estimation while reducing the average measurement time. To test the accuracy of the proposed system, we have collected data from 30 subjects with facial masks. Experimental results show that the proposed system can achieve 3.0 bpm mean absolute error in HR estimation.

A remote PPG based approach for heart rate estimation

Heart rate (HR) estimation is an essential physiological process in the field of biosignal analysis. Recently, remote Photoplethysmography (rPPG) is a pathbreaking development in this field wherein the PPG signal is extracted from non-contact face videos. This study, aiming at building a low cost rPPG system for both heart rate estimation and detecting real face, proposes a non-contact, automatic technique of heart rate measurement from video based on the signal processing techniques. The heart rate is remotely measured from a video recording of a person's face using the camera from a smartphone. At the same time, the heart rate extracted from the videos recorded by a smartphone camera is compared with the data obtained from the PPG optical absorption sensor and achieved a similar result. The system can estimate the heart rates from faces from single subject or multiple participants, and can be applied for anti spoofing face recognition.

A new principle of pulse detection based on terahertz wave plethysmography

This study presents findings in the terahertz (THz) frequency spectrum for non-contact cardiac sensing applications. Cardiac pulse information is simultaneously extracted using THz waves based on the established principles in electronics and optics. The first fundamental principle is micro-Doppler motion effect. This motion based method, primarily using coherent phase information from the radar receiver, has been widely exploited in microwave frequency bands and has recently found popularity in millimeter waves (mmWave) for breathe rate and heart rate detection. The second fundamental principle is reflectance based optical measurement using infrared or visible light. The variation in the light reflection is proportional to the volumetric change of the heart, often referred as photoplethysmography (PPG). Herein, we introduce the concept of terahertz-wave-plethysmography (TPG), which detects blood volume changes in the upper dermis tissue layer by measuring the reflectance of THz waves, similar to the existing remote PPG (rPPG) principle. The TPG principle is justified by scientific deduction, electromagnetic wave simulations and carefully designed experimental demonstrations. Additionally, pulse measurements from various peripheral body parts of interest (BOI), palm, inner elbow, temple, fingertip and forehead, are demonstrated using a wideband THz sensing system developed by the Terahertz Electronics Lab at Arizona State University, Tempe. Among the BOIs under test, it is found that the measurements from forehead BOI gives the best accuracy with mean heart rate (HR) estimation error 1.51 beats per minute (BPM) and standard deviation 1.08 BPM. The results validate the feasibility of TPG for direct pulse monitoring. A comparative study on pulse sensitivity is conducted between TPG and rPPG. The results indicate that the TPG contains more pulsatile information from the forehead BOI than that in the rPPG signals in regular office lighting condition and thus generate better heart rate estimation statistic in the form of empirical cumulative distribution function of HR estimation error. Last but not least, TPG penetrability test for covered skin is demonstrated using two types of garment materials commonly used in daily life.

Feasibility of Specular Reflection Imaging for Extraction of Neck Vessel Pressure Waveforms.

Cardiovascular disease (CVD) is a leading cause of death worldwide and was responsible for 31% of all deaths in 2015. Changes in fluid pressures within the vessels of the circulatory system reflect the mechanical function of the heart. The jugular venous (JV) pulse waveform is an important clinical sign for assessing cardiac function. However, technology able to aid evaluation and interpretation are currently lacking. The goal of the current study was to develop a remote monitoring tool that aid clinicians in robust measurements of JV pulse waveforms. To address this need, we have developed a novel imaging modality, Specular Reflection Vascular Imaging (SRVI). The technology uses specular reflection for visualization of skin displacements caused by pressure pulsations in blood vessels. SRVI has been tested on 10 healthy volunteers. 10-seconds videos of the neck illuminated with a diffuse light source were captured at 250 fps. SRVI was able to identify and discriminate skin displacements caused by carotid artery and jugular vein pulsations to extract both carotid artery and jugular vein waveforms, making them easier to be visualized and interpreted. The method provided a 6-fold improvement in signal strength over a comparator remote PPG dataset. The current pilot study is a proof-of-concept demonstration of the potential of Specular Reflection Vascular Imaging for extraction of JV pulse waveforms.

Pulse Rate Variability Analysis Using Remote Photoplethysmography Signals.

Pulse rate variability (PRV) refers to the change in the interval between pulses in the blood volume pulse (BVP) signal acquired using photoplethysmography (PPG). PRV is an indicator of the health status of an individual’s autonomic nervous system. A representative method for measuring BVP is contact PPG (CPPG). CPPG may cause discomfort to a user, because the sensor is attached to the finger for measurements. In contrast, noncontact remote PPG (RPPG) extracts BVP signals from face data using a camera without the need for a sensor. However, because the existing RPPG is a technology that extracts a single pulse rate rather than a continuous BVP signal, it is difficult to extract additional health status indicators. Therefore, in this study, PRV analysis is performed using lab-based RPPG technology that can yield continuous BVP signals. In addition, we intended to confirm that the analysis of PRV via RPPG can be performed with the same quality as analysis via CPPG. The experimental results confirmed that the temporal and frequency parameters of PRV extracted from RPPG and CPPG were similar. In terms of correlation, the PRVs of RPPG and CPPG yielded correlation coefficients between 0.98 and 1.0.

Restoration of Remote PPG Signal through Correspondence with Contact Sensor Signal

Photoplethysmography (PPG) is an optical measurement technique that detects changes in blood volume in the microvascular layer caused by the pressure generated by the heartbeat. To solve the inconvenience of contact PPG measurement, a remote PPG technology that can measure PPG in a non-contact way using a camera was developed. However, the remote PPG signal has a smaller pulsation component than the contact PPG signal, and its shape is blurred, so only heart rate information can be obtained. In this study, we intend to restore the remote PPG to the level of the contact PPG, to not only measure heart rate, but to also obtain morphological information. Three models were used for training: support vector regression (SVR), a simple three-layer deep learning model, and SVR + deep learning model. Cosine similarity and Pearson correlation coefficients were used to evaluate the similarity of signals before and after restoration. The cosine similarity before restoration was 0.921, and after restoration, the SVR, deep learning model, and SVR + deep learning model were 0.975, 0.975, and 0.977, respectively. The Pearson correlation coefficient was 0.778 before restoration and 0.936, 0.933, and 0.939, respectively, after restoration.

Posture effects on the calibratability of remote pulse oximetry in visible light

Objective: Remote pulse oximetry in visible light (VIS) is a relevant application of photoplethysmography (PPG). However, wavelengths penetrate at different depths and VIS-based pulse oximetry may not guarantee robustness to physiological variations of the skin properties. This paper shows how a simple manoeuver like a posture change can hamper the accuracy of a method relying on red and the less penetrating green wavelengths. Approach: Stationary subjects were measured under normoxic conditions while sitting and in the supine position. For each recording, we extracted remote PPG signals from forehead video recordings of 31 healthy adults at the red and green camera channels. The resulting normalized PPG-amplitudes, and its ratio, red-over-green (RoG), were compared between postures. The observed RoG changes were translated into estimates for arterial blood oxygen saturation (SpO2, %) errors by means of Monte Carlo simulations of the skin tissue. Simulations were also used to compare the calibratability errors of SpO2 in VIS against the conventional red-IR wavelengths. Main results: RoG differs significantly between postures (RoG: sitting, 0.100 0.025; supine, 0.123 0.033), mediated by PPG-amplitude changes in green. The posture interference in RoG may be mitigated by an offset correction. Without this correction, we estimated that the observed change in RoG causes SpO2 errors >. Analogous simulations involving red-IR wavelengths indicate SpO2 errors <. Significance: Our results show that the calibrations for remote pulse oximetry in VIS require the specification of a fixed measurement position. Future work could be aimed at controlling for posture in measurements.

On Improving Recovery Performance in Multiple Measurement Vector Having Dependency

The multiple measurement vector (MMV) problem is applicable in a wide range of applications such as photoplethysmography (PPG), remote PPG measurement, heart rate estimation, and directional arrival estimation of multiple sources. Measurements in the aforementioned applications exhibit a dependency structure, which is not considered in the general MMV algorithms. Modeling the dependency or the correlation structure of the solution matrix to MMV problems can increase the recovery performance. The solution matrix $X$ can be decomposed into a mixing matrix $A$ and a sparse matrix with independent columns $S$ . The key idea of this model is that the matrix S can be sparser than the mixing matrix $A$ . Previous MMV algorithms did not consider such a structure for $X$ . This paper proposes two algorithms, which are based on orthogonal matching pursuit and basis pursuit, and derives the exact recovery guarantee conditions for both approaches. We compare the simulation results of the proposed algorithms with the conventional algorithms and show that the proposed algorithms outperform previous algorithms especially in the case of the low number of measurements.

New insights into the origin of remote PPG signals in visible light and infrared

Remote photoplethysmography (PPG) is an optical measurement technique with established applications in vital signs monitoring. Recently, the consensual understanding of blood volume variations (BVVs) as the origin of PPG signals was challenged, raising validity concerns about the remote SpO2 methodology. Recognizing the imperative for new opto-physiological evidence, this investigation supports the volumetric hypothesis with living skin experiments and Monte Carlo simulations of remote PPG-amplitude in visible light (VIS) and infrared (IR). Multilayered models of the skin were developed to simulate the separate contributions from skin layers containing pulsatile arterioles to the PPG signal in the 450–1000 nm range. The simulated spectra were qualitatively compared with observations of the resting and compressed finger pad, and complemented with videocapillaroscopy. Our results indicate that remote PPG systems indeed probe arterial blood. Green wavelengths probe dermal arterioles while red-IR wavelengths also reach subcutaneous BVVs. Owing to stable penetration depths, the red-IR diagnostic window promotes the invariance of SpO2 measurements to skin non-homogeneities.

Robust tracking of respiratory rate in high-dynamic range scenes using mobile thermal imaging.

The ability to monitor the respiratory rate, one of the vital signs, is extremely important for the medical treatment, healthcare and fitness sectors. In many situations, mobile methods, which allow users to undertake everyday activities, are required. However, current monitoring systems can be obtrusive, requiring users to wear respiration belts or nasal probes. Alternatively, contactless digital image sensor based remote-photoplethysmography (PPG) can be used. However, remote PPG requires an ambient source of light, and does not work properly in dark places or under varying lighting conditions. Recent advances in thermographic systems have shrunk their size, weight and cost, to the point where it is possible to create smart-phone based respiration rate monitoring devices that are not affected by lighting conditions. However, mobile thermal imaging is challenged in scenes with high thermal dynamic ranges (e.g. due to the different environmental temperature distributions indoors and outdoors). This challenge is further amplified by general problems such as motion artifacts and low spatial resolution, leading to unreliable breathing signals. In this paper, we propose a novel and robust approach for respiration tracking which compensates for the negative effects of variations in the ambient temperature and motion artifacts and can accurately extract breathing rates in highly dynamic thermal scenes. The approach is based on tracking the nostril of the user and using local temperature variations to infer inhalation and exhalation cycles. It has three main contributions. The first is a novel Optimal Quantization technique which adaptively constructs a color mapping of absolute temperature to improve segmentation, classification and tracking. The second is the Thermal Gradient Flow method that computes thermal gradient magnitude maps to enhance the accuracy of the nostril region tracking. Finally, we introduce the Thermal Voxel method to increase the reliability of the captured respiration signals compared to the traditional averaging method. We demonstrate the extreme robustness of our system to track the nostril-region and measure the respiratory rate by evaluating it during controlled respiration exercises in high thermal dynamic scenes (e.g. strong correlation (r = 0.9987) with the ground truth from the respiration-belt sensor). We also demonstrate how our algorithm outperformed standard algorithms in settings with different amounts of environmental thermal changes and human motion. We open the tracked ROI sequences of the datasets collected for these studies (i.e. under both controlled and unconstrained real-world settings) to the community to foster work in this area.