SOCIAL DISTANCE MONITORING WITH SURVEILLANCE

In December , Wuhan, China, became the origin of COVID 19. The WHO has classified the outbreak, which briefly afflicted numerous nations throughout the world, as an epidemic. Keeping Social Distance has emerged as one of the trendy ways to aid in the spread of COVID-19 as the epidemic crisis has expanded to every corner of the globe and made things worse. Maintaining social distance is crucial because cases have been increasing at an incredibly rapid rate everywhere. The prevention of contagion transmission by reducing human physical contacts, like the millions of people, is what social distancing refers to. Social distancing refers to preventative measures used to stop the spread of disease. These include avoiding crowds and maintaining a suitable distance between individuals. Examples of these places include shopping malls, public buildings, seminaries, universities, airports, and workplaces. Our design’s primary goal is to ensure people’s safety in public spaces by automatically observing whether they keep a safe social distance or not. The suggested system is a deep literacy outcome that trains the model with OpenCV. For a quick and efficient deep literacy result for fatality finding in videography aqueducts, we combine the deep literacy MobileNetV2 model with the SSD Framework, and triangle similarity property is employed to quantify distance between people detected by camera in video.