Fully Automated Unsupervised Learning Approach for Thermal Camera Calibration and An Accurate COVID-19 Human Temperature Tracking

Abstract

During the past three years, people have suffered a lot from what the World Health Organization called the emerging Covid-19. The world lacked the means and methods for early detection of this virus, several methods were used traditional methods for detecting this virus, such as thermometers, a remote thermal detection gun, and other traditional methods. Most of these systems monopolized making profits or selling their camera products, as the prices of these cameras equipped with a temperature detection system exceeded three thousand dollars. An unsupervised model for real-time detection of thermal face skin temperature was proposed, despite the scarcity and availability of thermal video data, we found and used a database created at Nazarbayev University in Nur-Sultan, Kazakhstan, which contains clips of thermal video and RGB video. Where the two different videos were calibrated, and the congruence was measured by two measures, SSIM and Correlation, and then four methods of registration were used to achieve perfect congruence, and the congruence was also measured through the two previous measures, and then the K-means method was used to extract clusters, and then functions for post-processing were built, then, the thermal face skin was extracted by multiplying the binary face into the thermal face, and the temperature of the face was calculated by taking the average values of the thermal face skin pixels and converting them from Fahrenheit to Celsius. Satisfactory results were obtained for us, as temperatures were detected for some cases within the normal range, others below the normal range, and others higher than this rate.