Enforcing Social Distancing with YOLO Algorithm Utilizing Object-to-Object Distance

Instances of COVID-19 transmission occur daily due to individuals failing to maintain distance or engaging in physical contact with others who may be contaminated with the virus. To mitigate this issue, this study has developed a system to detect human subjects practicing social distancing. The syst...

Full description

Saved in:
Bibliographic Details
Main Authors: Irsan, Muhamad, Hassan, Rosilah, Abdali, Taj-Aldeen Naser, Ishak, Mohamad Khairi
Format: Conference Proceeding
Language:English
Subjects:
Cameras
COVID
Graphics processing units
Human factors
Raspberry Pi
Social distancing
System performance
Training
Webcams
YOLO
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Instances of COVID-19 transmission occur daily due to individuals failing to maintain distance or engaging in physical contact with others who may be contaminated with the virus. To mitigate this issue, this study has developed a system to detect human subjects practicing social distancing. The system utilizes a Raspberry Pi 4 Model B 8GB device in combination with a Logitech HD Webcam C270 camera. To detect human subjects, the Convolutional Neural Network is employed, utilizing the You Only Look Once (YOLO) method. In the testing phase of the tool, the system successfully identifies human subjects and assesses their proximity to others. It also detects instances of social distancing violations. The system achieved an average mean Average Precision (mAP) of 0.9792, a Precision of 0.9482, a Recall of 0.9819, and an f1 score of 0.9648.
ISSN:2831-4948
DOI:10.1109/ACIT58888.2023.10453716