Eyes' corners detection in infrared images for real-time noncontact respiration rate monitoring

A thermal imaging based noncontact respiration rate monitoring approach is developed. The approach identified and tracked the face region in the image. The two corners where the eyes and nose meet were detected by selecting the two highest temperature regions within the face. From these sites, the nose and the nostril were identified. A respiration region of interest (ROI) was specified under the nostril. The skin surface temperature in this region is affected most by respiration. The selected ROI in each recorded thermal image was represented by a single feature. A respiration signal was produced from the plot of the feature across the series of recorded images. Respiration rate was determined by using the frequency of the highest peak in the frequency spectrum. The approach was evaluated on 5 adult subjects. It was shown that it could track the face, determine the ROI and respiration successfully in real-time, even when there were some head movements.