The lethal infection, World Health Organization (WHO) reported coronavirus (COVID-19) as a pandemic.Lack of proper vaccine, low levels of immunity against COVID-19 has led to vulnerability of the human beings. Due tolack of efficient vaccine treatment, the only options left to fight against this pandemic are lockdown and social distance.This work offers an autonomous monitoring system on social distancing using deep learning techniques. The proposedarchitecture tracks the humans on roads and calculates their distance between each other. This surveillance detects thefurore violation of social distance utilizing CCTV cameras. The proposed framework uses YOLO v3 object-detectionmodel built on COCO dataset and used to classify human class among 79 classes. The bounding box's dimensions andcentroid coordinates are computed in the two-dimensional feature space from the pairwise vectorized L2 norm and athreshold is fixed for computing the distance maintained between each other. We illustrate the superior performance ofour framework checked against other state of the art methods regarding inference speed, mean average precision and lossdefined from the localization.
COVID-19, social distancing, YOLO v3, COCO dataset, inference, video surveillance, edge devices, objectdetection
ÖZBEK, MUHAMMED MURAT; SYED, MUSTAFA; and ÖKSÜZ, İLKAY
"Subjective analysis of social distance monitoring using YOLO v3 architecture andcrowd tracking system,"
Turkish Journal of Electrical Engineering and Computer Sciences: Vol. 29:
2, Article 43.
Available at: https://journals.tubitak.gov.tr/elektrik/vol29/iss2/43