Real-time Social Distance Detection using YOLO-v5 with Bird-eye View Perspective to Suppress the Spread of COVID-19

ABSTRACT

The COVID-19 virus outbreak has continued to spread since the end of 2019 worldwide. All people also implement health protocols not to contract this disease. One of the health protocols that must be implemented is to limit interactions between humans to a length of 1-2 meters or what is usually done with social distancing. Social distance detection system to ensure that people do not violate social distancing could be a solution to this problem. Using the YOLO-v5 method, which is the latest version of the YOLO (You Only Look Once) method with a detection speed of up to 140 Frames Per Second (FPS) and 90 percent smaller than the previous version, this system detects people who violate social distancing and then gives a voice warning to keep their distance to avoid spreading the COVID-19 virus. The human detection rate in the detection system reaches 93, 5%, and the accuracy for social distance detection reaches 95%. Based on the research that has been done, it can be said that this system can work well for detecting social distance, but the detection will start detecting the distance between the camera and the object exceeding 10 meters. © 2022 IEEE.