<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-04484074</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-22T06:32:31+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Using pixel- or superpixel-based segmentation for efficient classification of green roof digital images and rapid estimation of plant species abundance</title>
            <author role="aut">
              <persName>
                <forename type="first">Didier</forename>
                <surname>Técher</surname>
              </persName>
              <email type="md5">b96bf60f014328e45290fca040edfe56</email>
              <email type="domain">univ-lorraine.fr</email>
              <idno type="idhal" notation="string">didier-techer</idno>
              <idno type="idhal" notation="numeric">17291</idno>
              <idno type="halauthorid" notation="string">1337045-17291</idno>
              <idno type="IDREF">https://www.idref.fr/163844674</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-7378-8685</idno>
              <affiliation ref="#struct-1170591"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Didier</forename>
                <surname>Techer</surname>
              </persName>
              <email type="md5">245a5c50d8de4ea6d9f6b7ce617e1689</email>
              <email type="domain">cerema.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2024-02-29 15:09:55</date>
              <date type="whenModified">2024-03-04 15:33:07</date>
              <date type="whenReleased">2024-02-29 15:09:55</date>
              <date type="whenProduced">2022</date>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="589166">
                <persName>
                  <forename>Didier</forename>
                  <surname>Techer</surname>
                </persName>
                <email type="md5">245a5c50d8de4ea6d9f6b7ce617e1689</email>
                <email type="domain">cerema.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04484074</idno>
            <idno type="halUri">https://hal.science/hal-04484074</idno>
            <idno type="halBibtex">techer:hal-04484074</idno>
            <idno type="halRefHtml">&lt;i&gt;SFE² GfÖ EEF Joint meeting, International Conference on Ecological Sciences&lt;/i&gt;, 2022, Metz, France. &lt;a target="_blank" href="https://sfe2gfomeeting.sciencesconf.org/"&gt;&lt;/a&gt;</idno>
            <idno type="halRef">SFE² GfÖ EEF Joint meeting, International Conference on Ecological Sciences, 2022, Metz, France. </idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="SDE">Sciences De l'Environnement</idno>
            <idno type="stamp" n="GIP-BE">GIP Bretagne Environnement</idno>
            <idno type="stamp" n="CEREMA">Centre d'études et d'expertise sur les risques, l'environnement, la mobilité et l'aménagement</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="invited" n="0">No</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
            <note type="proceedings" n="0">No</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Using pixel- or superpixel-based segmentation for efficient classification of green roof digital images and rapid estimation of plant species abundance</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Didier</forename>
                    <surname>Técher</surname>
                  </persName>
                  <email type="md5">b96bf60f014328e45290fca040edfe56</email>
                  <email type="domain">univ-lorraine.fr</email>
                  <idno type="idhal" notation="string">didier-techer</idno>
                  <idno type="idhal" notation="numeric">17291</idno>
                  <idno type="halauthorid" notation="string">1337045-17291</idno>
                  <idno type="IDREF">https://www.idref.fr/163844674</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-7378-8685</idno>
                  <affiliation ref="#struct-1170591"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>SFE² GfÖ EEF Joint meeting,International Conference on Ecological Sciences</title>
                  <date type="start">2022</date>
                  <settlement>Metz</settlement>
                  <country key="FR">France</country>
                </meeting>
                <imprint/>
              </monogr>
              <ref type="publisher">https://sfe2gfomeeting.sciencesconf.org/</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">image analysis</term>
                <term xml:lang="en">green roof</term>
                <term xml:lang="en">superpixel segmentation</term>
                <term xml:lang="en">machine learning</term>
                <term xml:lang="en">Image J</term>
              </keywords>
              <classCode scheme="halDomain" n="sde.be">Environmental Sciences/Biodiversity and Ecology</classCode>
              <classCode scheme="halTypology" n="POSTER">Poster communications</classCode>
              <classCode scheme="halOldTypology" n="POSTER">Poster communications</classCode>
              <classCode scheme="halTreeTypology" n="POSTER">Poster communications</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Green roofs are “nature-based solutions” that may provide numerous ecosystemservices in the context of urban greening. Vegetation development in stronginteractions with green roof media and microbial communities play a key role in theecosystem multifunctionality of these green infrastructures. Consequently, researchon plant selection has increased in recent years in order to expand the list of speciesable to grow on green roofs in cold or arid climates, with special efforts to clarify therelationships between species diversity, functional traits and ecosystem services.There is still a need, however, for carrying out long-term vegetation survey to avoidpremature conclusions regarding plant adaptation as well as to better understand theecosystem functioning and ecological trajectories of these engineered ecosystems.Nevertheless, vegetation cover determination on green roofs may rapidly becometime-consuming and quite tedious, especially in the case of densely covered mixedspecies roofs or due to plant species (sometimes overlapping) with similar leaf shapeand colours (e.g. sedums). Therefore, the aim of this work was to investigate theability of two freely available plugins, which were recently developed for the opensourceimage analysis software Fiji (a distribution of the free ImageJ platform, initiallydedicated to biological image analysis), to rapidly and efficiently perform supervisedmachine-learning for the classification of green roof vegetation from photographs.Two workflows are thus described, depending on the use of the “Trainable WekaPixel Segmentation” or the “Trainable Superpixel Segmentation”, and compared withthe traditional “point frame measurement” method for plant abundance determinationat the species level. Both machine-learning based methods performed very wellregarding image classification efficiency and reproducibility (using fast random forestalgorithm), with the best results obtained with a minimum image label number of 16per object category to be classified (pouzzolane, moss, sedum and grass species).Moreover, preliminary image segmentation into superpixels with jSLIC (SimpleLinear Iterative Clustering) with an initial grid size of 1 (and a minimum label numberof 4 per object category to be classified) allowed for highly satisfactory classificationresults in a few seconds only, which would facilitate the use of such imagery tool forroutine survey.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-1170591" status="VALID">
          <orgName>Transferts et interactions liés à l'eau en milieu construit</orgName>
          <orgName type="acronym">TEAM</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-422961" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-422961" status="VALID">
          <idno type="ROR">https://ror.org/05k0nvr25</idno>
          <orgName>Centre d'Etudes et d'Expertise sur les Risques, l'Environnement, la Mobilité et l'Aménagement</orgName>
          <orgName type="acronym">Cerema</orgName>
          <date type="start">2017-10-16</date>
          <desc>
            <address>
              <addrLine>Siège : Cités des Mobilités - 25 avenue François Mitterrand - CS 92803 -  69674 BRON Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.cerema.fr/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>