Machine-learning-based microwave ghost imaging using reconfigurable metasurface

Yash Fafolawala; Axel Bangert; Samaneh Moeini

doi:10.1117/12.2690801

30 November 2023 Machine-learning-based microwave ghost imaging using reconfigurable metasurface

Yash Fafolawala, Axel Bangert, Samaneh Moeini

Proceedings Volume 12796, Functional Material Applications: From Energy to Sensing; 1279602 (2023) https://doi.org/10.1117/12.2690801
Event: SPIE Photonex, 2023, Glasgow, United Kingdom

Abstract

This paper presents a machine-learning based approach to microwave ghost imaging. Unlike traditional imaging techniques, ghost imaging is a non-local imaging technique that does not involve scanning. Since ghost imaging uses a single detector at a fixed location, measurements are taken under various random or pseudo-random illuminations to recover the image. Moving from the optical frequency regime to the microwave regime, the accurate measurement of such a random field becomes more complicated because there is no device such as a Charge Coupled Device (CCD) camera at microwaves. In this work, we generate pseudo-random field patterns using a reconfigurable metasurface and we use a single detector at a fixed location to measure the reflection from the target. Reconfigurability plays a fundamental role in ghost imaging. The microstrip line-fed metasurface is formed by unit cells of size 2.564 × 1 mm², which are tuned by a pair of PIN diodes. By activating these diodes in forward or reverse bias, different field patterns can be generated. A receiver is placed in the centre of the aperture. The resonance frequency is set to 40 GHz. To recover the image, we present a machine-learning approach. A neural network is trained using a synthetic dataset obtained from ANSYS High Frequency Structure Simulator (HFSS) simulations to learn the second-order correlation between the incident field patterns and the measured scattered fields at the detector in order to recover the target image.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Yash Fafolawala, Axel Bangert, and Samaneh Moeini "Machine-learning-based microwave ghost imaging using reconfigurable metasurface", Proc. SPIE 12796, Functional Material Applications: From Energy to Sensing, 1279602 (30 November 2023); https://doi.org/10.1117/12.2690801

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available