Towards a convolutional neural network coupled millimetre-wave coded aperture image classifier system

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Computational millimetre-wave (mmW) imaging and machine learning have followed parallel tracks since their inception. Recent developments in computational imaging (CI) have significantly improved the imaging capabilities of millimetre-wave imaging systems. Machine learning algorithms have also gained huge popularity among researchers in the recent past with several approaches being investigated to make use of machine learning algorithms in imaging systems. One such algorithm, image classifier, has gained significant traction in applications such as security screening and traffic surveillance. The purpose of this article is to integrate a learning algorithm such as the image classifier to a mmW CI system for the first time. The dataset used during the training is generated by developing a forward model for CI, hence eliminating the need for traditional imaging techniques.
Original languageEnglish
Title of host publicationSPIE April 2021 Passive and Active Millimeter-Wave Imaging XXIV: Proceedings
Place of PublicationSPIE April 2021 Passive and Active Millimeter-Wave Imaging XXIV.
Publication statusAccepted - 18 Dec 2020

Publication series

Name
ISSN (Print)1111-1111

Fingerprint Dive into the research topics of 'Towards a convolutional neural network coupled millimetre-wave coded aperture image classifier system'. Together they form a unique fingerprint.

Cite this