<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD Journal Publishing DTD v3.0 20080202//EN" "https://jats.nlm.nih.gov/nlm-dtd/publishing/3.0/journalpublishing3.dtd">
<article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" article-type="research-article" dtd-version="3.0" xml:lang="en">
<front>
<journal-meta>
<journal-id journal-id-type="publisher">AGILE-GISS</journal-id>
<journal-title-group>
<journal-title>AGILE: GIScience Series</journal-title>
<abbrev-journal-title abbrev-type="publisher">AGILE-GISS</abbrev-journal-title>
<abbrev-journal-title abbrev-type="nlm-ta">AGILE GIScience Ser.</abbrev-journal-title>
</journal-title-group>
<issn pub-type="epub">2700-8150</issn>
<publisher><publisher-name>Copernicus Publications</publisher-name>
<publisher-loc>Göttingen, Germany</publisher-loc>
</publisher>
</journal-meta>
<article-meta>
<article-id pub-id-type="doi">10.5194/agile-giss-7-8-2026</article-id>
<title-group>
<article-title>Maximizing Data Coverage: Fusing Street View and Oblique Imagery to Quantify Vertical Greenery Potential in Urban Areas</article-title>
</title-group>
<contrib-group><contrib contrib-type="author" xlink:type="simple"><name name-style="western"><surname>Kramm</surname>
<given-names>Aruscha</given-names>
</name>
<xref ref-type="aff" rid="aff1">
<sup>1</sup>
</xref>
</contrib>
<contrib contrib-type="author" xlink:type="simple"><name name-style="western"><surname>Ludwig</surname>
<given-names>André</given-names>
</name>
<xref ref-type="aff" rid="aff2">
<sup>2</sup>
</xref>
</contrib>
<contrib contrib-type="author" xlink:type="simple"><name name-style="western"><surname>Franczyk</surname>
<given-names>Bogdan</given-names>
</name>
<xref ref-type="aff" rid="aff1">
<sup>1</sup>
</xref>
<xref ref-type="aff" rid="aff2">
<sup>2</sup>
</xref>
</contrib>
</contrib-group><aff id="aff1">
<label>1</label>
<addr-line>Leipzig University, Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI) Dresden/Leipzig, Germany</addr-line>
</aff>
<aff id="aff2">
<label>2</label>
<addr-line>Leipzig University, Information Systems Institute, Germany</addr-line>
</aff>
<pub-date pub-type="epub">
<day>10</day>
<month>06</month>
<year>2026</year>
</pub-date>
<volume>7</volume>
<elocation-id>8</elocation-id>
<permissions>
<copyright-statement>Copyright: © 2026 Aruscha Kramm et al.</copyright-statement>
<copyright-year>2026</copyright-year>
<license license-type="open-access">
<license-p>This work is licensed under the Creative Commons Attribution 4.0 International License. To view a copy of this licence, visit <ext-link ext-link-type="uri" xlink:href="https://creativecommons.org/licenses/by/4.0/">https://creativecommons.org/licenses/by/4.0/</ext-link></license-p>
</license>
</permissions>
<self-uri xlink:href="https://agile-giss.copernicus.org/articles/agile-giss-7-8-2026.html">This article is available from https://agile-giss.copernicus.org/articles/agile-giss-7-8-2026.html</self-uri>
<self-uri xlink:href="https://agile-giss.copernicus.org/articles/agile-giss-7-8-2026.pdf">The full text article is available as a PDF file from https://agile-giss.copernicus.org/articles/agile-giss-7-8-2026.pdf</self-uri>
<abstract>
<p>As urbanization intensifies globally, the Urban Heat Island (UHI) effect has emerged as a critical environmental challenge, inducing higher energy demands, compromised air quality, and significant public health risks. Vertical Greenery Systems (VGS) such as green facades and living walls, offer a spatially efficient adaptation strategy by utilizing vertical surface areas of the built environment for thermal regulation and microclimatic improvement, yet the absence of data-integrative methods hinders large-scale evaluation of factors defining a surface&amp;rsquo;s suitability for VGS. Previous methodologies for estimating city-wide greening potential have successfully integrated semantic 3D city models (LoD2) with Street View Imagery (SVI) to derive key suitability factors such as Window-to-Wall Ratio (WWR) and Solid Wall Area (SWA). However, these approaches are inherently limited by the sparse spatial coverage of SVI, which is restricted to navigable road networks, leaving rear facades and inner courtyards unassessed, and which is frequently obstructed by foreground occlusion, leading to errors in the factor calculation. This consecutive work introduces a robust computational method that enhances the existing LoD2-SVI pipeline with Oblique Aerial Imagery extending the potential estimation to over 90% of the urban building stock. To mitigate occlusion and resolution disparities, we propose a multi-view fusion algorithm that aggregates detections across multiple views within one perspective and further across two perspectives. Our evaluation demonstrates that both data sources deliver comparable results when assessing identical facades. Further, our fusion approach significantly reduces systematic biases found in single-source estimations. Ultimately, while the fusion approach maximizes assessment reliability for walls with dual coverage, the integration of oblique imagery remains critical for scalability. Although it yields lower feature fidelity than street view, it provides the only viable means to assess surfaces lying beyond the navigable road network.&lt;/p&gt;
&lt;p&gt;&lt;a href="https://doi.org/10.17605/OSF.IO/HETV8" target="_blank" rel="noopener"&gt;&lt;img src="https://contentmanager.copernicus.org/779365/10/locale/ssl" width="150px" /&gt;&lt;/a&gt;&amp;nbsp;Reproducibility review available at: &lt;a href="https://doi.org/10.17605/OSF.IO/HETV8" target="_blank" rel="noopener"&gt;https://doi.org/10.17605/OSF.IO/HETV8&lt;/a&gt;</p>
</abstract>
<counts><page-count count="13"/></counts>
</article-meta>
</front>
<body/>
<back>
</back>
</article>
