Robust tracking of respiratory rate in high-dynamic range scenes using mobile thermal imaging

摘要

The ability to monitor respiratory rate is extremely important for medicaltreatment, healthcare and fitness sectors. In many situations, mobile methods,which allow users to undertake every day activities, are required. However,current monitoring systems can be obtrusive, requiring users to wearrespiration belts or nasal probes. Recent advances in thermographic systemshave shrunk their size, weight and cost, to the point where it is possible tocreate smart-phone based respiration rate monitoring devices that are notaffected by lighting conditions. However, mobile thermal imaging is challengedin scenes with high thermal dynamic ranges. This challenge is further amplifiedby general problems such as motion artifacts and low spatial resolution,leading to unreliable breathing signals. In this paper, we propose a novel androbust approach for respiration tracking which compensates for the negativeeffects of variations in the ambient temperature and motion artifacts and canaccurately extract breathing rates in highly dynamic thermal scenes. It hasthree main contributions. The first is a novel Optimal Quantization techniquewhich adaptively constructs a color mapping of absolute temperature to improvesegmentation, classification and tracking. The second is the Thermal GradientFlow method that computes thermal gradient magnitude maps to enhance accuracyof the nostril region tracking. Finally, we introduce the Thermal Voxel methodto increase the reliability of the captured respiration signals compared to thetraditional averaging method. We demonstrate the extreme robustness of oursystem to track the nostril-region and measure the respiratory rate in highdynamic range scenes.