Lightweight CNN-Based Deep Neural Networks Application in Safety Measurement

Authors: Lua, Wilbur Kai Heng;

Yau, Peter C.Y.;

Seow, Chee Kiat;

Dennis, Wong

Source: 2022 5th International Conference on Pattern Recognition and Artificial Intelligence (PRAI)

Full text

: https://doi.org/10.1109/PRAI55851.2022.9904161

Abstract

Inspired by the face covering period in the past two years, COVID-19 pandemic has resulted in the mandate of public safety measures such as face mask-wearing in many countries. This paper provides a preliminary feasibility planning on how Artificial Intelligence (AI), Computer Vision (CV) and the Internet of Things (IoT) can work together to implement a face-mask detection system as a public health safety solution. This paper reviews how edge computing can overcome traditional cloud computing issues. This work also examines the current state of computer vision, convolutional neural networks and their potential application in the health and safety domain. This writing serves as an interim report on how the lightweight CNNs and single-shot detectors such as YOLOv5 variants with SSD to train and deploy an object detection system.

Rights

This content is not covered by the Open Government Licence. Please see source record or item for information on rights and permissions.

Cite as

Lua, W., Yau, P., Seow, C. & Dennis, W. 2022, 'Lightweight CNN-Based Deep Neural Networks Application in Safety Measurement', 2022 5th International Conference on Pattern Recognition and Artificial Intelligence (PRAI). https://doi.org/10.1109/PRAI55851.2022.9904161

Downloadable citations

HTML BIB RIS

Identifiers

DOI: https://doi.org/10.1109/PRAI55851.2022.9904161

Repository URI: https://eprints.gla.ac.uk/285976/