Crowd Detection And Social Distancing Tracker

Abstract

The corona virus COVID-19 pandemic is causing a global health crisis so the effective protection methods is maintain social distance in public areas according to the World Health Organization (WHO). The COVID-19 pandemic forced governments across the world to impose lockdowns to prevent virus transmissions. Reports indicate that maintaining social distance at work clearly reduces the risk of transmission. We will use the dataset to build a COVID-19 social distance detector with computer vision using Python, OpenCV, and Tensor Flow and Yolo. In our proposed system we will use live video stream and finally in output it shows the number of violations when someone not maintaining social distance. Our goal is to identify whether the person on image/video stream is maintaining social distance or not with the help of computer vision, machine learning and deep learning. The proposed method presented in this paper is mainly for crowd surveillance and security maintenance. This system can be utilized for events, private property or places that have massive streams of people entering and leaving the area, which necessitates vigilant tracking and identification of all individuals within the premises. With deep learning, particularly CNN, the model is able to train and learn to identify human beings using the database customized.