Social Distance Monitoring System Using YOLO and Pixel-to-real-world Distance Mapping
Dewi Yanti Liliana, Rizki Elisa Nalawati, Fitria Nugrahani, Muhammad Rienaldy Muharram · 2022
Covid-19 is an infectious disease caused by the recently discovered coronavirus. This virus spreads through droplets produced when an infected person coughs, sneezes, or exhales. A person can be infected by breathing air containing the virus if a person is too close to someone who is already infected with Covid-19. A person can also be infected by touching contaminated surfaces and then touching their eyes, nose, or mouth. Social distancing is to reduce the spread of viruses, other than washing hands and wearing a mask. With the help of Computer Vision Technology, it can monitor the safe distance of human activities in a particular area or environment. The problem is to determine the safe distance in a pixel-based digital image. The difference in the same pixel distance does not always mean the actual distance between adjacent objects is the same. It must consider the actual distance to the camera. Since social distancing requires someone to keep a certain distance from another, a web-based application with a Convolutional Neural Network (CNN) algorithm is employed using the You Only Look Once (YOLO) and Pixel-to-real-world distance mapping technique. In testing, there are several test scenarios with the accuracy results obtained of 95% with a recall of 0.95 and a precision of 0.92, and MAE $5.9\mathrm{~cm}$.