COVID-19: Automatic Social Distancing Rule Voilation Detection using PP-Yolo Tensorflow in OpenCV

ABSTRACT

In this critical situations where people are fighting with dangerous pandemic disease;it is required to maintain the situation by indulging with social distancing or it can also be pronounced as physical distancing. Social or physical distancing may reflects to reduce the virus from spreading. There are several places where it should be followed properly to stop spreading COVID-19 like railway stations, malls, marts, airports and many more. It is advised to maintain at least 6 feet of social distancing as per the WHO guidelines. Various researches have been done to automatically detect the physical distancing violations but an ideal system should be available to detect it effectively with high level of accuracy. Here the system is based on PP-Yolo (PaddlePaddle - You only look once) and Tensorflow library. Tensorflow is an object detection or pattern recognition tool through which pedestrian can be detected automatically and then PP-Yolo classifies the distance between the pedestrians or classifying whether persons are following the physical distancing rule or not. Violation detection is bit challenging for any system because a crowd may have uncertain structures that can hardly classified distance among them. This challenge can be accepted through various researchers but not met the desired precision. Proposed system is intended to detect the physical distancing rule violations effectively and acquiring high level of accuracy with minimal false alarm rate. © 2022 IEEE.