A Novel Privacy-Preserving Approach for Physical Distancing Measurement Using Thermal Sensor Array

Physical distancing measurements are accepted to be critical strategies to slow the spread of COVID-19 disease. Most of the recent works to measure the physical distancing between people aims for easy-to-deploy systems such as contact tracing applications to speed up the deployment process. However, these systems, which rely heavily on the Bluetooth proximity sensor, tend to have serious performance and reliability issues. This paper proposes and explores using Thermal Sensor Array (TSA) towards physical distancing measurement. Distance estimation is achieved through using a multilayer perceptron (MLP) artificial neural network to measure the sensor-to-human distance and then to compute the physical distancing accordingly. Based on the conducted experimental work, the proposed sensor-to-human distance estimator's median overall error is +/- 0.2m for unseen testing data.