Non-contact vital sign monitoring
Researchers: Mauricio Villarroel, Alessandro Guazzi, Joao Jorge, Dr David Clifton, Prof. Lionel Tarassenko
Clinical collaborator: Prof. Chris Pugh (Renal Unit, Churchill Hospital)
Funding: Wellcome Trust and Department of Health (Centre of Excellence in Medical Engineering)
We have been developing novel methods for non-contact vital sign monitoring using a webcam. The webcam measures the light reflected from one or more regions of interest in the patient’s face. Previous work by others had shown that photoplethysmogram (PPG) signals could be remotely acquired from the human face with normal ambient light as the source. A problem with making this work in a real-world setting, however, is the presence of aliased components from artificial light, e.g. fluorescent light, found in most indoor environments outside daylight hours and often within daylight hours as well.
We have developed and patented a novel method of cancelling out the aliased frequencies caused by artificial light, based on auto-regressive modelling. We have also shown how accurate maps of the spatial distribution of heart rate and respiratory rate can be constructed from the coefficients of the auto-regressive model. Our vital sign data have been acquired from patients in the Oxford Renal Unit, who are double-monitored, rather than from healthy volunteers as is usually the case.