In this paper an innovative approach to microwave imaging, which combines a qualitative imaging technique and deep learning, is presented. The goal is to develop a tool for reliable and user-independent retrieval of the shape of unknown targets from the knowledge of the scattered fields. Qualitative imaging methods are powerful inverse scattering tools, as they provide morphological information in real-time. However, their outcome is a continuous map which has to be hard-thresholded to clearly identify the targets. This thresholding unavoidably results in case-dependent, often user-biased, results. To deal with this issue, a deep learning approach, based on a physics-assisted deep neural network is proposed to automatically classify image pixels, i.e., to generate binary masks, separating the targets (foreground) from the background. In particular, the proposed network binarizes the output of a qualitative imaging inversion technique known as orthogonality sampling method. For the sake of comparison, a deep learning method is also exploited, which generates the binary masks directly from the scattered fields without any qualitative imaging aid. A quantitative assessment of the performances of both methods as well as a test on experimental data are provided.
A Physics-Assisted Deep Learning Microwave Imaging Framework for Real-time Shape Reconstruction of Unknown Targets / Ruiz, A. Y.; Cavagnaro, M.; Crocco, L.. - In: IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION. - ISSN 0018-926X. - 70:8(2022), pp. 6184-6194. [10.1109/TAP.2022.3162320]
A Physics-Assisted Deep Learning Microwave Imaging Framework for Real-time Shape Reconstruction of Unknown Targets
Cavagnaro M.;
2022
Abstract
In this paper an innovative approach to microwave imaging, which combines a qualitative imaging technique and deep learning, is presented. The goal is to develop a tool for reliable and user-independent retrieval of the shape of unknown targets from the knowledge of the scattered fields. Qualitative imaging methods are powerful inverse scattering tools, as they provide morphological information in real-time. However, their outcome is a continuous map which has to be hard-thresholded to clearly identify the targets. This thresholding unavoidably results in case-dependent, often user-biased, results. To deal with this issue, a deep learning approach, based on a physics-assisted deep neural network is proposed to automatically classify image pixels, i.e., to generate binary masks, separating the targets (foreground) from the background. In particular, the proposed network binarizes the output of a qualitative imaging inversion technique known as orthogonality sampling method. For the sake of comparison, a deep learning method is also exploited, which generates the binary masks directly from the scattered fields without any qualitative imaging aid. A quantitative assessment of the performances of both methods as well as a test on experimental data are provided.File | Dimensione | Formato | |
---|---|---|---|
Ruiz_A-Physics-Assisted_2022.pdf
solo gestori archivio
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
2.32 MB
Formato
Adobe PDF
|
2.32 MB | Adobe PDF | Contatta l'autore |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.