Published Paper Details:

The novel coronavirus which was first seen in Wuhan, China has created havoc across the world. Its rapid spreading and the virulent outbreak have created a state of emergency in the world. From a public fitness standpoint, COVID-19 is a sickness of top significance, and it has become vital to barricade the virus from spreading with preventive measures like maintaining social distance and wearing a mask. This paper mainly aims to develop a system that helps monitor if people are maintaining social distancing and also detects face masks on humans. This paper makes use of the Tiny-YOLO algorithm on Raspberry Pi for real-time object detection. Although the YOLO object detector is widely regarded as one of the quickest deep learning-based object detectors, with a high Fames Per Second, it is still too slow to run on embedded devices like the Raspberry Pi. Hence, this paper uses tiny YOLO which has a small model size (< 50MB) and rapid inference speed, making it applicable for embedded deep learning devices. We could additionally be displaying the count of human beings found in a room on an LCD. Overall, this paper facilitates lessening the range of COVID-19 sufferers and makes public locations safer.