Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Non-contact vital sensor technology for care

: Wiede, Christian; Seidl, Karsten


Biomedizinische Technik 66 (2021), Nr.s1, S.S423
ISSN: 0013-5585
ISSN: 1862-278X
Deutsche Gesellschaft für Biomedizinische Technik (DGBMT Jahrestagung) <55, 2021, Hannover>
Fraunhofer IMS ()

Vital signs are an important indicator of a person's state of health. A disturbance can result in serious illnesses. Conventional methods such as ECG or pulse oximetry have the disadvantage of being contact-based. In addition to low comfort when worn, this poses a problem for people with sensitive skin, such as newborns or the elderly. One solution is optical contactless vital sign measurement. We are presenting an overview and our lastest research for the most accurate and fastest possible detection of these vital signs in different wavelength ranges and quantifies them using machine learning methods. The use of contactless vital parameter sensors offers considerable benefits, particularly for use in nursing scenarios and care facilities.
The following vital signs are scientifically examined: heart rate, respiration rate, oxygen saturation and blood pressure. Our approach to non-contact measurement uses camera-based photoplethysmography (PPG). The physical basis of this technique is the different absorption or reflection spectra of human skin. By measuring and analyzing the time course of color, spectral and temperature values of the human skin, various vital parameters can be determined. The heart rate is measured using color image analysis and extraction and filtering of PPG signals. Through in-depth analysis of RGB (red, green, blue) PPG signals, the oxygen saturation can also be determined without contact. For determining the respiratory rate, intelligent image processing analyses the movement of the chest and filters out the signal of respiratory movement. Latest research includes the determination of the blood pressure.
We successfully determined and evaluated the heart rate and respiration rate in clinical and care environment. The hospital staff can then make an assessment of the patient based on the displayed values. In particular, the use of neural networks allows to detect critical conditions and changes over time.
Contactless vital sign measurement offers considerable added value for use in care. In particular, integration into nursing robots is a promising approach. Nursing staff are thus relieved of routine tasks. By using artificial intelligence, critical conditions can be detected and changes over time can be analyzed.