Scholarlink

<p>The passive millimeter wave (PMMW) imaging sensor can generate images using the passive detection of the natural millimeter wave radiation from a scene. Despite the advantages of PMMW images in detecting concealed objects under clothing, they have lower resolution and fewer details than visible images. This paper proposes a new method to fuse PMMW and visible images to highlight concealed objects on the human body while preserving the details of the visible images. In this method, the PMMW image is initially segmented into three binary images, target, foreground, and background, utilizing an innovative segmentation algorithm that incorporates histogram-based thresholding and the generation of a saliency map image. Subsequently, the visible and PMMW images are individually decomposed into base and detail subbands using the new Gradient Transform (GT). Then, by individually fusing the base and detail subbands of the PMMW and visible images using innovative L2-norm weighting criteria, the fused image’s base and detail subbands are produced. Based on these criteria, between the two corresponding subbands of the input images, the subband with more detail contributes more to the final fused subband. Finally, the fused image is generated by applying the inverse GT to the newly generated fused subbands. Experimental results demonstrate a notable enhancement in terms of evaluation criteria like <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="11760_2024_3761_Article_IEq1.gif" Format="GIF" Height="20" Rendition="HTML" Resolution="72" Type="Linedraw" Width="50" /> </InlineMediaObject> <EquationSource Format="TEX">\({Q_{AB/F}}\)</EquationSource> <EquationSource Format="MATHML"><math> <msub> <mi>Q</mi> <mrow> <mi>A</mi> <mi>B</mi> <mo stretchy="false">/</mo> <mi>F</mi> </mrow> </msub> </math></EquationSource> </InlineEquation> and <i>MI</i>, surpassing the most recent algorithms in this field.</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

Passive millimeter wave and visible image fusion using concealed object detection and gradient transform

  • 期刊论文

  • 发表日期：

    2025年1月3日

查看全文
  • Iraj Hadinejad,
  • Mohammad Amin Amiri,
  • Mohammad Hossein Fahimifar

摘要

The passive millimeter wave (PMMW) imaging sensor can generate images using the passive detection of the natural millimeter wave radiation from a scene. Despite the advantages of PMMW images in detecting concealed objects under clothing, they have lower resolution and fewer details than visible images. This paper proposes a new method to fuse PMMW and visible images to highlight concealed objects on the human body while preserving the details of the visible images. In this method, the PMMW image is initially segmented into three binary images, target, foreground, and background, utilizing an innovative segmentation algorithm that incorporates histogram-based thresholding and the generation of a saliency map image. Subsequently, the visible and PMMW images are individually decomposed into base and detail subbands using the new Gradient Transform (GT). Then, by individually fusing the base and detail subbands of the PMMW and visible images using innovative L2-norm weighting criteria, the fused image’s base and detail subbands are produced. Based on these criteria, between the two corresponding subbands of the input images, the subband with more detail contributes more to the final fused subband. Finally, the fused image is generated by applying the inverse GT to the newly generated fused subbands. Experimental results demonstrate a notable enhancement in terms of evaluation criteria like \({Q_{AB/F}}\) Q A B / F and MI, surpassing the most recent algorithms in this field.