Analysis of AI-Powered Human Detection Method for Social Distancing Monitoring

Social distancing is a non-medical practice that helps slow down the transmission of viruses which is suggested by the World Health Organization (WHO). However, as every country has battled the spread of the virus for almost three years, social distancing practice now seems ignored by public people due to some reason such as they are in a rush. This study aims to analyze human detection using deep learning methods in various positions and to develop social distancing detection using the proposed method. Thus, human detection and social distancing detection using a deep learning algorithm which is You Only Look Once (YOLO) version 3 is developed. This method uses custom datasets and the Euclidean distance formula to compute the distance between two people for the social distancing detector. The output distance is measured in the real world (centimetres). As a result, the current datasets for each position such as front view, back view, side view, and the crowd give the result of human detection at 94.44%, 91.67%, 97.50%, and 88.89% respectively. Hence, the highest accuracy of human detection goes to the side view position with a percentage accuracy of 97.50%. Next, the distance between the two people is calculated correctly with the acceptable range of ±0.3 cm.