Face Mask and Social Distance Monitoring Using Computer Vision with Deployable System Architecture

Research Supervisor
Journal Title
Journal Title
Journal ISSN
Volume Title
The coronavirus (COVID-19) is a lethal virus causing a rapidly infectious disease throughout the globe. Coronavirus has become one of the deadliest epidemics of the 21st century. From causing respiratory illness to severe heart and kidney failure, the world has realized the importance of preventing the spread of this destructive disease within a few months of its discovery and outbreak. To fight the spread of this virus, technologically developed architectures and systems have become very useful. Even though the world has spent a whole year preventing and curing COVID-19, the statistics show that the virus can cause an outbreak any time on a large scale if thorough preventive measures are not maintained accordingly. This paper aims to develop an automatic system to detect social distance and face mask violation in real-time simultaneously. A modified version of a convolutional neural network, ResNet50 model, has been utilized to identify masked faces in people. You only look once (YOLOv3) approach is applied for object detection and the DeepSORT technique is used to measure the social distance. The efficiency of the proposed model is tested on real-time video sequences taken from a video streaming source from an embedded system (Jetson Nano) and smartphone applications. Empirical results show that the implemented model can efficiently detect facial masks and social distance violations with acceptable accuracy and precision scores.
TECHNOLOGY::Information technology::Computer science
Department Name
Electrical and Computer Engineering
North South University
Printed Thesis