Heart rate estimation based on face video under unstable illumination

Yin, Ruo-Nan; Jia, Rui-Sheng; Cui, Zhe; Yu, Juan; Du, Yan-Bin; Gao, Li; Sun, Hong-Mei

doi:10.1007/s10489-020-02167-4

Cited by 18 publications

(11 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhang et al (2021) proposed the use of LAB space to resist illumination variation by converting RGB space to LAB space to separate luminance signals, and experiments were conducted in different scenes. Yin et al (2021) proposed a HR estimation method under unstable light sources and specifically studied the temporal and spatial inhomogeneity of face light species. Ensemble empirical mode decomposition (EEMD) was used to analyze the signal, and a good performance was obtained.…”

Section: Traditional Methods Of Ippg Measurementmentioning

confidence: 99%

Remote photoplethysmography based on reflected light angle estimation

Fan,

Liu,

Zhang

et al. 2024

Physiol. Meas.

View full text Add to dashboard Cite

Efficient non-contact heart rate detection has received much attention in the field of health testing. In previous studies on factors affecting the accuracy of remote photoplethysmography(rPPG) detection, light intensity, facial reflection angle, and motion artifacts have been investigated, but interference from specularly reflected light has not been studied. In this paper, a total of 84 videos were first acquired from four different angles and used to study the effect of specularly reflected light on the accuracy of heart rate estimation. Then we proposed a reflected light angle estimation method which firstly segments the face into 71 regions, and then extracts the angle and illumination of each region as possible reflected light directions and weights respectively. Secondly, all sample points are fitted by sample interpolation, and the angle value corresponding to the maximum value of the weight in the fitted curve is selected as the estimated angle of reflected light direction. Finally, the reflected light angle value is used as a reference for (region of interest) ROI selection to improve the quality of the obtained (image photoplethysmography) iPPG signal. We find that the accuracy of the estimated heart rate and the SNR of the signal are higher when the reflected light angle is larger. The overall root mean squared error (RMSE), standard deviation (SD) and mean error(MAE) of our proposed reflected light angle estimation method are 2.085, 1.745 and 0.7225, which not only have high accuracy but also have good stability. Our proposed method has low error and is superior to existing methods by comparison in publicly available databases.

show abstract

Section: Traditional Methods Of Ippg Measurementmentioning

confidence: 99%

Remote photoplethysmography based on reflected light angle estimation

Fan,

Liu,

Zhang

et al. 2024

Physiol. Meas.

View full text Add to dashboard Cite

show abstract

“…They validated the system in different illuminations and with some head motion [145]. Different researchers also looked into ambient, natural and varying illumination [234], [235], [236]; However, once again, the setup was within a controlled setting where participants were at a distance of 0.6m from the camera. The participant diversity information was not revealed in the research paper.…”

Section: Literature Review Findings: Previous Work With Its Limitationsmentioning

confidence: 99%

Remote Photoplethysmography (rPPG): A State-of-the-Art Review

Pirzada,

Wilde,

Doherty

et al. 2023

Preprint

View full text Add to dashboard Cite

Peripheral oxygen saturation (SpO2) and heart rate (HR) are critical physiological measures that clinicians need to observe to decide on an emergency intervention. These measures are typically determined using a contact-based pulse oximeter. This approach may pose difficulties in many cases, such as with young children, patients with burnt or sensitive skin, cognitive impairments, and those undergoing certain medical procedures or severe illnesses. Remote Photoplethysmography (rPPG) allows for unobtrusive sensing of these vital signs in a variety of settings for health monitoring systems. Several research studies have been conducted to use rPPG for this purpose; however, there is still not a commercially available, clinically validated system that overcomes the concerns highlighted in this paper. We present a state-of-the-art review of rPPG-related research conducted including related processes and techniques, such as regions of interest (ROI) selection, extracting the raw signal, pre-processing data, applying noise reduction algorithms, Fast Fourier transforms (FFT), filtering and extracting these vital signs. Further, we present a detailed, critical evaluation of available rPPG systems. Limitations and future directions have also been identified to aid rPPG researchers in further advancing this field.

show abstract

“…Both HR and f R can be estimated from the r-PPG signal, as the respiratory activity modulates the cardiac activity [ 8 ]. When the r-PPG technique is used to retrieve information about the pulsatile activity through a video recording of a subject’s face, different factors should be considered, including the user–camera distance [ 9 , 10 ], the lighting source [ 11 , 12 ], the resolution of the video acquisition system [ 13 ], and the region of interest (ROI) [ 14 , 15 ]. Among these factors, user–camera distance, the lighting source, and the selected ROI can affect the quality of the r-PPG waveform and thus the accuracy in the estimation of HR [ 9 , 11 , 16 , 17 ].…”

Section: Introductionmentioning

confidence: 99%

“…When the r-PPG technique is used to retrieve information about the pulsatile activity through a video recording of a subject’s face, different factors should be considered, including the user–camera distance [ 9 , 10 ], the lighting source [ 11 , 12 ], the resolution of the video acquisition system [ 13 ], and the region of interest (ROI) [ 14 , 15 ]. Among these factors, user–camera distance, the lighting source, and the selected ROI can affect the quality of the r-PPG waveform and thus the accuracy in the estimation of HR [ 9 , 11 , 16 , 17 ]. The ROI selection for HR estimation is a debated issue, single or multiple ROIs in the facial region [ 18 , 19 ] or the palm hand [ 20 ] can be employed, but performances are typically dependent on the specific application and recording environment [ 18 , 19 ].…”

Section: Introductionmentioning

confidence: 99%

Multi-ROI Spectral Approach for the Continuous Remote Cardio-Respiratory Monitoring from Mobile Device Built-In Cameras

Molinaro

Schena

Silvestri

et al. 2022

Sensors

View full text Add to dashboard Cite

Heart rate (HR) and respiratory rate (fR) can be estimated by processing videos framing the upper body and face regions without any physical contact with the subject. This paper proposed a technique for continuously monitoring HR and fR via a multi-ROI approach based on the spectral analysis of RGB video frames recorded with a mobile device (i.e., a smartphone’s camera). The respiratory signal was estimated by the motion of the chest, whereas the cardiac signal was retrieved from the pulsatile activity at the level of right and left cheeks and forehead. Videos were recorded from 18 healthy volunteers in four sessions with different user-camera distances (i.e., 0.5 m and 1.0 m) and illumination conditions (i.e., natural and artificial light). For HR estimation, three approaches were investigated based on single or multi-ROI approaches. A commercially available multiparametric device was used to record reference respiratory signals and electrocardiogram (ECG). The results demonstrated that the multi-ROI approach outperforms the single-ROI approach providing temporal trends of both the vital parameters comparable to those provided by the reference, with a mean absolute error (MAE) consistently below 1 breaths · min−1 for fR in all the scenarios, and a MAE between 0.7 bpm and 6 bpm for HR estimation, whose values increase at higher distances.

show abstract

Heart rate estimation based on face video under unstable illumination

Cited by 18 publications

References 32 publications

Remote photoplethysmography based on reflected light angle estimation

Remote photoplethysmography based on reflected light angle estimation

Remote Photoplethysmography (rPPG): A State-of-the-Art Review

Multi-ROI Spectral Approach for the Continuous Remote Cardio-Respiratory Monitoring from Mobile Device Built-In Cameras

Contact Info

Product

Resources

About