Automated Thermal Screening for COVID-19 using Machine Learning

TL;DR

This paper presents an automated, non-invasive thermal imaging system using machine learning for COVID-19 screening that is effective in various lighting conditions and introduces an open-source dataset for further research.

Contribution

The authors develop a thermal imaging-based COVID-19 screening method with machine learning and release a new dataset, addressing limitations of visual imaging under low-light conditions.

Findings

Thermal imaging-based detection performs consistently across lighting conditions.

Visual imaging classifiers degrade by over 50% in low-light scenarios.

Open-source NTIC dataset supports further research in thermal-based screening.

Abstract

In the last two years, millions of lives have been lost due to COVID-19. Despite the vaccination programmes for a year, hospitalization rates and deaths are still high due to the new variants of COVID-19. Stringent guidelines and COVID-19 screening measures such as temperature check and mask check at all public places are helping reduce the spread of COVID-19. Visual inspections to ensure these screening measures can be taxing and erroneous. Automated inspection ensures an effective and accurate screening. Traditional approaches involve identification of faces and masks from visual camera images followed by extraction of temperature values from thermal imaging cameras. Use of visual imaging as a primary modality limits these applications only for good-lighting conditions. The use of thermal imaging alone for these screening measures makes the system invariant to illumination. However, lack of open source datasets is an issue to develop such systems. In this paper, we discuss our work on using machine learning over thermal video streams for face and mask detection and subsequent temperature screening in a passive non-invasive way that enables an effective automated COVID-19 screening method in public places. We open source our NTIC dataset that was used for training our models and was collected at 8 different locations. Our results show that the use of thermal imaging is as effective as visual imaging in the presence of high illumination. This performance stays the same for thermal images even under low-lighting conditions, whereas the performance with visual trained classifiers show more than 50% degradation.