Performance Analysis for Human Crowd Monitoring to Control COVID-19 disease by Drone Surveillance

This paper describes a configuration of drone swarm that can be used in support of the actions to limit the virus spread during a pandemic period, such as the COVID-19 emergency. The proposed study analyzes a system architecture for the identification of individuals affected by the virus, estimating their biomedical parameters. The presented method exploits different techniques, such as stereoscopy vision, thermal measures and remote photoplethysmography, to acquire standalone data that can be compared to evaluate the target risk. The tested solutions are proposed to measure the social distancing among multiple individuals, the skin temperature of a target person, and the image photoplethysmography signal, that are critical parameters to detect a potentially infect individual during the COVID-19 pandemic. Different test strategies were adopted to carry out the mentioned tasks. To measure the distance between target individuals, two drones equipped with visible band cameras were employed. To measure the skin temperature of a target, a drone equipped with a thermal camera was adopted, performing measures at different distances and heights. To obtain the image photoplethysmography signal, a video file from drone camera is processed. Image processing techniques are required to elaborate the data coming from several images and videos acquired by drones. Comparing the measures, altered biomedical parameters of several targets can be detected and later tested with medical equipment.