Social Distancing and Face Mask Monitoring System Using Deep Learning Based on COVID-19 Directive Measures

Abstract

We, the entire world is in the lock of a micro size virus named Corona we are in the urge of saving our life rather than the money. This virus had changed the attitude of people from generations together, in this two years people realized that their health worth more than their net worth. We are in an uncertain situation but, we can bring the world back to normal so, we need to follow the guidelines issued by the health organizations so our government insisted people wear the mask and maintain social distance to control the spread of the disease but 90% percent of people not following covid guidelines. The main motive in this paper, mask detection on face with social distancing which helps to overcome this pandemic situation. Our proposed system comprises of data processing, data augmentation, image classification using mobilenetv2 and object detection plays a vital role in this paper. The modules are developed using TensorFlow and open-cv python programming to detect the faces with mask. If a person wears a mask they will be in a safe zone and the system shows a green box where if the person doesn't wear a mask, then it will be shown in a red box and with the message of alert as well. Social distancing detection will detect that two or more person in a single frame are walking with maintaining social distancing with at least 2 meters of range with each other using the Euclidean distance method, it will work in a Reliable manner with accurate results during this current situation which will easily help to track the person and collect fine if they violate any government directive guidelines so our system, will prevent the spread of the disease. Every Automation process reduces manual inspection to inspect the people which can be used in public places to control the spread of the virus and this prototype could be used in many places like park, hospital, airports, temples, railway station etc. to control this pandemic situation