Non-invasive vital parameter detection using neuromorphic cameras

Abstract The non-invasive detection of vital parameters is gaining significance in the medical field through the use of various established and novel camera technologies and the use of artificial intelligence for data processing. A recently emerging type of imaging sensor, the neuromorphic camera, mimics the way the human eye perceives changes in its vision by responding to local changes in brightness for each pixel. The use of these neuromorphic cameras in the medical field is mostly unexplored and offers new possibilities. This research experiment is designed as a proof of concept for the use of neuromorphic cameras to detect the heart rate and respiration rate of a person by monitoring movement and subtle vibrations of the abdominal and chest area. The experimental setup consisted of a DVXplorer camera positioned 30 cm from a healthy person, directed at the abdominal and chest area. The respiration rate was detected with a mean absolute error of 0.66 bpm. The heart rate was detected with an accuracy of 95 % and a mean absolute error of less than 2 bpm. This shows the possibility to detect the heart rate and respiration rate of a person reliably, using neuromorphic cameras under controlled conditions. Future research will focus on improving reliability under more challenging environmental circumstances like varying light conditions and movement of the patient.