Contactless Blood Oxygen Saturation Estimation from Facial Videos Using Deep Learning

• Published in: Bioengineering (Basel) Vol. 11; no. 3; p. 251
• Main Authors: Cheng, Chun-Hong, Yuen, Zhikun, Chen, Shutao, Wong, Kwan-Long, Chin, Jing-Wei, Chan, Tsz-Tai, So, Richard H. Y.
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 01.03.2024; MDPI
• Subjects: Artificial neural networks; Blood; blood oxygen saturation measurement; Body temperature; Cameras; Computer vision; COVID-19; Datasets; Deep learning; Face; facial videos; Health aspects; Hemoglobin; Infectious diseases; Light; Machine learning; Measuring instruments; Neural networks; non-contact monitoring; Oximetry; Oxygen; Oxygen content; Oxygen saturation; Pandemics; Physiology; Pulse oximetry; Ratios; remote health monitoring; Remote monitoring; Representations; Sensitivity analysis; Signal processing; Smartphones; Video; Vital signs; United Kingdom; deep learning; remote health monitoring; blood oxygen saturation measurement; facial videos; non-contact monitoring

Blood oxygen saturation (SpO2) is an essential physiological parameter for evaluating a person’s health. While conventional SpO2 measurement devices like pulse oximeters require skin contact, advanced computer vision technology can enable remote SpO2 monitoring through a regular camera without skin...