Tracking human face features in thermal images for respiration monitoring

Abstract

A method has been developed to track a region related to respiration process in thermal images. The respiration region of interest (ROI) consisted of the skin area around the tip of the nose. The method was then used as part of a non-contact respiration rate monitoring that determined the skin temperature changes caused by respiration. The ROI was located by the first determining the relevant salient features of the human face physiology. These features were the warmest and coldest facial points. The tracking method was tested on thermal video images containing no head movements, small random and regular head movements. The method proved valuable for tracking the ROI in all these head movement types. It was also possible to use this tracking method to monitor respiration rate involving a number of head movement types. Currently, more investigations are underway to improve the tracking method so that it can track the ROI in cases larger head movements.