Implementing a Real-Time, YOLOv5 based Social Distancing Measuring System for Covid-19

TL;DR

This paper presents a YOLOv5-based social distancing monitoring system using overhead views, with a custom model that improves accuracy in detecting social distance violations on COCO and Visdrone datasets.

Contribution

The work introduces a modified YOLOv5 model with CSP architecture that enhances accuracy in social distancing detection compared to default YOLOv5 models.

Findings

Modified CSP YOLOv5 achieves 81.7% accuracy on COCO without transfer learning.

The model attains up to 58.1% accuracy on Visdrone for certain classes.

Transfer learning improves detection accuracy for both models.

Abstract

The purpose of this work is, to provide a YOLOv5 deep learning-based social distance monitoring framework using an overhead view perspective. In addition, we have developed a custom defined model YOLOv5 modified CSP (Cross Stage Partial Network) and assessed the performance on COCO and Visdrone dataset with and without transfer learning. Our findings show that the developed model successfully identifies the individual who violates the social distances. The accuracy of 81.7% for the modified bottleneck CSP without transfer learning is observed on COCO dataset after training the model for 300 epochs whereas for the same epochs, the default YOLOv5 model is attaining 80.1% accuracy with transfer learning. This shows an improvement in accuracy by our modified bottleneck CSP model. For the Visdrone dataset, we are able to achieve an accuracy of upto 56.5% for certain classes and especially an accuracy of 40% for people and pedestrians with transfer learning using the default YOLOv5s model for 30 epochs. While the modified bottleneck CSP is able to perform slightly better than the default model with an accuracy score of upto 58.1% for certain classes and an accuracy of ~40.4% for people and pedestrians.