Contactless Remote Assessment of Heart Rate and Respiration Rate Using Video Magnification

Wallace, Bruce; Kassab, Leen Yassin; Law, Andrew; Goubran, Rafik; Knoefel, Frank

doi:10.1109/mim.2022.9693458

Cited by 19 publications

(15 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The existing non-contact method mainly detects the skin-color changes in order to estimate HR, and for the prediction of RR, the head and chest movements are monitored, or it is extracted from the rPPG estimation. For these, the forehead and cheek areas are set as the regions of interest (ROIs) for the PPG estimation, and the nose or mouth are set for the prediction of respiration by investigating the warm or cool air flow through them [ 24 ]. A deep-learning study has also been conducted to extract the rPPG information from facial video streams.…”

Section: Introductionmentioning

confidence: 99%

Multitask Siamese Network for Remote Photoplethysmography and Respiration Estimation

Lee

Kwon

et al. 2022

Sensors

View full text Add to dashboard Cite

Heart and respiration rates represent important vital signs for the assessment of a person’s health condition. To estimate these vital signs accurately, we propose a multitask Siamese network model (MTS) that combines the advantages of the Siamese network and the multitask learning architecture. The MTS model was trained by the images of the cheek including nose and mouth and forehead areas while sharing the same parameters between the Siamese networks, in order to extract the features about the heart and respiratory information. The proposed model was constructed with a small number of parameters and was able to yield a high vital-sign-prediction accuracy, comparable to that obtained from the single-task learning model; furthermore, the proposed model outperformed the conventional multitask learning model. As a result, we can simultaneously predict the heart and respiratory signals with the MTS model, while the number of parameters was reduced by 16 times with the mean average errors of heart and respiration rates being 2.84 and 4.21. Owing to its light weight, it would be advantageous to implement the vital-sign-monitoring model in an edge device such as a mobile phone or small-sized portable devices.

show abstract

Section: Introductionmentioning

confidence: 99%

Multitask Siamese Network for Remote Photoplethysmography and Respiration Estimation

Lee

Kwon

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Methods to assess heart rate include invasive (placement of sensors inside the body) and noninvasive techniques. The non-invasive techniques are further divided into contact methods (placing sensors on the skin) [2], [3] and contactless methods (video camera, microphone) [4]. Over the last decade, advances had been made in the area of video based contactless remote assessment of heart rate.…”

Section: Problem Statementmentioning

confidence: 99%

Section: State Of the Literature On The Video Magnification Technique...mentioning

confidence: 99%

“…Over the last decade, advances had been made in the area of contactless remote assessment of heart rate [4]. These advances began with the publication of two important works: Eulerian Video Magnification (EVM) [5] and Remote Photoplethysmography (rPPG) [6] in 2012 and 2013 respectively [4]. Both techniques are founded on the principle of detecting subtle colour changes in the skin captured by a video -which are imperceptible to the human eye-occurring as a result of the heart compression and recovery cycle [4].…”

Section: State Of the Literature On The Video Magnification Technique...mentioning

confidence: 99%

“…Recent research has typically built upon one of the two techniques but not both, leading to parallel bodies of work that at first appear to define two distinct algorithms [4]. However, after further analysis, the two techniques appear to belong to the same family of video processing, and the distinction accounts more to the choices made at every step of the processing pipeline [4].…”

Section: State Of the Literature On The Video Magnification Technique...mentioning

confidence: 99%

See 2 more Smart Citations

Heart Rate Detection using Video Magnification: Impact of Algorithmic Parameters and Noise

Kassab¹

View full text Add to dashboard Cite

Screening people for illnesses in public spaces using contactless techniques such as Video Magnification (VM) can be beneficial for both the crowd and the operators. One important vital sign to screen for is heart rate because it is indicative of the overall health of humans. In this thesis, first the impact of varying two input parameters (region of interest (ROI) size and window segment length) on VM is explored. Second, the impact of noise from three different sources (quantization, modern camera systems coupled with software enhancements, and light illumination) is explored.Results show that heart rate can be detected from very small ROIs, but that larger ROIs have higher accuracy. Larger window segment lengths are useful in the presence of motion. VM detects signals with amplitudes equal to one quantization level in 8-bit videos. VM is affected by modern camera systems, and it is more accurate with higher light illuminations.

show abstract

Sensor Technologies: Collecting the Data in the Home

Knoefel,

Wallace,

Thomas

et al. 2023

Synthesis Lectures on Technology and Health

View full text Add to dashboard Cite

Contactless Remote Assessment of Heart Rate and Respiration Rate Using Video Magnification

Cited by 19 publications

References 32 publications

Multitask Siamese Network for Remote Photoplethysmography and Respiration Estimation

Multitask Siamese Network for Remote Photoplethysmography and Respiration Estimation

Heart Rate Detection using Video Magnification: Impact of Algorithmic Parameters and Noise

Sensor Technologies: Collecting the Data in the Home

Contact Info

Product

Resources

About