Subjective analysis of social distance monitoring using YOLO v3 architecture and crowd tracking system

Abstract

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 to lack of 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 proposed architecture tracks the humans on roads and calculates their distance between each other. This surveillance detects the furore violation of social distance utilizing CCTV cameras. The proposed framework uses YOLOv3 object-detection model built on COCO dataset and used to classify human class among 79 classes. The bounding-box's dimensions and centroid coordinates are computed in the two-dimensional feature space from the pairwise vectorized L2 norm and a threshold is fixed for computing the distance maintained between each other. We illustrate the superior performance of our framework checked against other state of the arts regarding inference speed, mean average precision and loss defined from the localization.

Convolutional neural network-based crowd detection for COVID-19 social distancing protocol from unmanned aerial vehicles onboard camera

“…The purpose of this paper is to find a model with a load that can be handled by a UAV companion computer. It can also be seen that social distance measurements were also carried out in the study of Özbek et al 49 . and Ahmad et al 51 .…”

“…The purpose of this paper is to find a model with a load that can be handled by a UAV companion computer. It can also be seen that social distance measurements were also carried out in the study of Özbek et al 49 and Ahmad et al 51 This paper has integrated the measurement of social distance estimation with the enumeration of social distance violators, which has not been implemented by the other five studies.…”

Fine Grained Feature Extraction Model of Riot-related Images Based on YOLOv5

“…The role of Patch Merging is similar to the maximum pooling layer of CNN, but the maximum pooling used by CNN to achieve down sampling will discard some information, so using Patch Merging can increase the accuracy of the model. Another advantage of using Swin Transformer is that the core point of the algorithm uses the Swin Transformer Block, which consists of Window Multi-Head Self-Attention (W-MSA) [31][32][33] and Shifted-Window Multi-Head Self-Attention (SW-MSA) [34][35][36], as shown in Fig. 3.…”

Deep visual social distancing monitoring to combat COVID-19: A comprehensive survey

“…After three COVID-19 waves, the growing number of new infections still reminds us of the importance of taking precautionary measures. SD and wearing masks have been proven to be efficient nonpharmaceutical intervention measures ( Özbek, Syed, & Öksüz, 2021 ). They are low-cost, convenient, and noninvasive to slow the spread of COVID-19 and flatten the curves of infection ( Srivastava, Zhao, Manay, & Chen, 2021 ).…”