An end-to-end smart IoT-Driven navigation for social distance monitoring framework for Covid-19 using deep convolutional neural networks in Deep Learning

The extraordinary worldwide spread of the COVID-19 coronavirus pandemic has considerably boosted the development of new Internet-of-things (IoT)-based strategies to stop, stop, monitor, or foresee virus propagation among people. These technologies are being used more often for a variety of practical purposes that include enhanced safety, discipline, and control. The novel coronavirus creates a global pandemic and affects a human, besides a huge death rate. As there is no proper medication, at least the spread should be stopped or it should be minimized. One way is to avoid physical contact. People should maintain a minimum distance to avoid direct contact. This paper presents detecting the social distance between pedestrians in public places. The idea is to take live videos from the camera we set up in a public place and create bounding boxes for each person in the video. If two or more people are close to each other violating social distance, then we put a red box around them otherwise we put a green box. The proposed framework's experimental results exhibit good results in monitoring the distance among humans in public areas compared to the existing methods.