University of Twente Student Theses

Login

Non-Contact Measurement of Heart Rate Independent of Skin Tone and Environment Light Using Near-Infrared Illumination

Gringhuis, M.J.H. (2024) Non-Contact Measurement of Heart Rate Independent of Skin Tone and Environment Light Using Near-Infrared Illumination.

[img] PDF
15MB
Abstract:Newborns requiring intensive medical care are placed in a specialized area of the hospital known as the neonatal intensive care unit (NICU). In the NICU, electrocardiography (ECG) is employed to continuously monitor heart function. Due to the delicate nature of infants’ skin epidermis, removing ECG electrodes can result in skin lesions and discomfort for the infant, causing pain and disrupting sleep. Introducing a reliable, contactless measurement technique could significantly enhance comfort levels for neonates in a NICU. Remote photoplethysmography (rPPG) is an contactless technology that utilizes video recordings of individuals to extract vital health parameters, such as heart rate. This thesis explores the functionality and reliability of near-infrared remote photoplethysmography (NIR-rPPG) for non-contact heart rate measurement, irrespective of skin tone and environmental lighting conditions. NIR-rPPG is particularly intriguing due to its potential to operate without disrupting sleep and its likely independence from variations in skin tone compared to ambient rPPG. Additionally, a Python-based rPPG application will be developed. The rPPG application will undergo optimization initially on a single test subject to assess the impact of factors such as camera type, noise, motion artifacts, environmental lighting, and stability. Subsequently, tests will be conducted with eighteen human test subjects representing all skin types according to the Fitzpatrick skin type classification. The experimental procedures were approved by the ethics committee of the University of Twente (application nr. 230114). Heart rate error (HRE), signal-to-noise ratio (SNR), and analysis of variance (ANOVA) will be utilized to interpret the results. During the human subject experiments, our rPPG application demonstrated independence from variations in skin tone and environmental lighting under NIR conditions. The heart rate error was found to be within a 95% confidence interval ranging from -6.1% to 6.2%. Additionally, a demonstrator resembling a mirror was developed for heart rate measurement purposes. Through optimization, we identified the optimal parameters and settings within the scope of this research. The HQCAM was chosen as the camera for experiments with human subjects. Furthermore, after evaluating various rPPG algorithms, the POS algorithm emerged as the most promising option under NIR conditions.
Item Type:Essay (Master)
Faculty:TNW: Science and Technology
Subject:50 technical science in general
Programme:Biomedical Engineering MSc (66226)
Link to this item:https://purl.utwente.nl/essays/98733
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page