Salvato in:
Dettagli Bibliografici
Autori principali: Xiang, Mingjun, Zhou, Kai, Yuan, Hui, Roskos, Hartmut G.
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2408.13066
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912000071696384
author Xiang, Mingjun
Zhou, Kai
Yuan, Hui
Roskos, Hartmut G.
author_facet Xiang, Mingjun
Zhou, Kai
Yuan, Hui
Roskos, Hartmut G.
contents This study proposes a novel approach utilizing a physics-informed deep learning (DL) algorithm to reconstruct occluded objects in a terahertz (THz) holographic system. Taking the angular spectrum theory as prior knowledge, we generate a dataset consisting of a series of diffraction patterns that contain information about the objects. This dataset, combined with unlabeled data measured from experiments, are used for the self-training of a physics-informed neural network (NN). During the training process, the neural network iteratively predicts the outcomes of the unlabeled data and reincorporates these results back into the training set. This recursive strategy not only reduces noise but also minimizes mutual interference during object reconstruction, demonstrating its effectiveness even in data-scarce situations. The method has been validated with both simulated and experimental data, showcasing its significant potential to advance the field of terahertz three-dimensional (3D) imaging. Additionally, it sets a new benchmark for rapid, reference-free, and cost-effective power detection.
format Preprint
id arxiv_https___arxiv_org_abs_2408_13066
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Reconstruction of partially occluded objects with a physics-driven self-training neural network
Xiang, Mingjun
Zhou, Kai
Yuan, Hui
Roskos, Hartmut G.
Optics
Image and Video Processing
This study proposes a novel approach utilizing a physics-informed deep learning (DL) algorithm to reconstruct occluded objects in a terahertz (THz) holographic system. Taking the angular spectrum theory as prior knowledge, we generate a dataset consisting of a series of diffraction patterns that contain information about the objects. This dataset, combined with unlabeled data measured from experiments, are used for the self-training of a physics-informed neural network (NN). During the training process, the neural network iteratively predicts the outcomes of the unlabeled data and reincorporates these results back into the training set. This recursive strategy not only reduces noise but also minimizes mutual interference during object reconstruction, demonstrating its effectiveness even in data-scarce situations. The method has been validated with both simulated and experimental data, showcasing its significant potential to advance the field of terahertz three-dimensional (3D) imaging. Additionally, it sets a new benchmark for rapid, reference-free, and cost-effective power detection.
title Reconstruction of partially occluded objects with a physics-driven self-training neural network
topic Optics
Image and Video Processing
url https://arxiv.org/abs/2408.13066