Scholarlink

Abstract <p>This paper discusses the potential of deep learning in solving the inverse problem of computational ghost polarimetry. For the first time, it is demonstrated that the spatial distribution of the polarization properties of objects with linear amplitude anisotropy can be restored using a neural network trained on model data. The spatial distribution of the parameters of linear amplitude anisotropy is determined with an accuracy of 7.8<InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="11972_2025_8761_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="15" /> </InlineMediaObject> <EquationSource Format="TEX">\(\%\)</EquationSource> <!--BPhysMGU2570016Chernousov-m1--> </InlineEquation> and 15.6<InlineEquation ID="IEq2"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="11972_2025_8761_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="15" /> </InlineMediaObject> <EquationSource Format="TEX">\(\%\)</EquationSource> <!--BPhysMGU2570016Chernousov-m2--> </InlineEquation> for the azimuth and the value of anisotropy, respectively.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deep Learning Ghost Polarimetry of Two-Dimensional Objects with Amplitude Anisotropy

  • 期刊论文

  • 发表日期：

    2025年2月1日

查看全文
  • D. A. Chernousov,
  • D. P. Agapov

摘要

Abstract

This paper discusses the potential of deep learning in solving the inverse problem of computational ghost polarimetry. For the first time, it is demonstrated that the spatial distribution of the polarization properties of objects with linear amplitude anisotropy can be restored using a neural network trained on model data. The spatial distribution of the parameters of linear amplitude anisotropy is determined with an accuracy of 7.8 \(\%\) and 15.6 \(\%\) for the azimuth and the value of anisotropy, respectively.