Nonlinear Hyperspectral Mixture Analysis for tree cover estimates in orchards
Identifieur interne : 001F39 ( Main/Exploration ); précédent : 001F38; suivant : 001F40Nonlinear Hyperspectral Mixture Analysis for tree cover estimates in orchards
Auteurs : Ben Somers [Belgique] ; Kenneth Cools [Belgique] ; Stephanie Delalieux [Belgique] ; Jan Stuckens [Belgique] ; Dimitry Van Der Zande [Belgique] ; Willem W. Verstraeten [Belgique] ; Pol Coppin [Belgique]Source :
- Remote sensing of environment [ 0034-4257 ] ; 2009.
Descripteurs français
- Pascal (Inist)
- Non linéarité, Caractéristique hyperspectrale, Végétation, Analyse conceptuelle, Arbre, Verger, Surveillance, Variation spatiotemporelle, Information, Gestion, Mixage, Expérimentation, Diffusion multiple, In situ, Pixel, Citrus sinensis, Propriété physique, Télédétection hyperspectrale, Télédétection, Diffusion onde.
- Wicri :
- topic : Arbre, Verger, Information, Gestion, Télédétection.
English descriptors
- KwdEn :
Abstract
Accurate monitoring of spatial and temporal variation in tree cover provides essential information for steering management practices in orchards. In this light, the present study investigates the potential of Hyperspectral Mixture Analysis. Specific focus lies on a thorough study of non-linear mixing effects caused by multiple photon scattering. In a series of experiments the importance of multiple scattering is demonstrated while a novel conceptual Nonlinear Spectral Mixture Analysis approach is presented and successfully tested on in situ measured mixed pixels in Citrus sinensis L. orchards. The rationale behind the approach is the redistribution of nonlinear fractions (i.e., virtual fractions) among the actual physical ground cover entities (e.g., tree, soil). These 'virtual' fractions, which account for the extent and nature of multiple photon scattering only have a physical meaning at the spectral level but cannot be interpreted as an actual physical part of the ground cover. Results illustrate that the effect of multiple scattering on Spectral Mixture Analysis is significant as the linear approach provides a mean relative root mean square error (RMSE) for tree cover fraction estimates of 27%. While traditional nonlinear approaches only slightly reduce this error (RMSE=23%), important improvements are obtained for the novel Nonlinear Spectral Mixture Analysis approach (RMSE = 12%).
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000292
- to stream PascalFrancis, to step Curation: 000711
- to stream PascalFrancis, to step Checkpoint: 000288
- to stream Main, to step Merge: 001F89
- to stream Main, to step Curation: 001F39
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Nonlinear Hyperspectral Mixture Analysis for tree cover estimates in orchards</title>
<author><name sortKey="Somers, Ben" sort="Somers, Ben" uniqKey="Somers B" first="Ben" last="Somers">Ben Somers</name>
<affiliation wicri:level="3"><inist:fA14 i1="01"><s1>Dept. of Biosystems, M3-BIORES, Katholieke Universiteit Leuven, W. de Croylaan 34</s1>
<s2>3001 Leuven</s2>
<s3>BEL</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
<sZ>7 aut.</sZ>
</inist:fA14>
<country>Belgique</country>
<placeName><region type="province" nuts="2">Province du Brabant flamand</region>
<settlement type="town">Heverlee</settlement>
<settlement type="city">Louvain</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Cools, Kenneth" sort="Cools, Kenneth" uniqKey="Cools K" first="Kenneth" last="Cools">Kenneth Cools</name>
<affiliation wicri:level="3"><inist:fA14 i1="01"><s1>Dept. of Biosystems, M3-BIORES, Katholieke Universiteit Leuven, W. de Croylaan 34</s1>
<s2>3001 Leuven</s2>
<s3>BEL</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
<sZ>7 aut.</sZ>
</inist:fA14>
<country>Belgique</country>
<placeName><region type="province" nuts="2">Province du Brabant flamand</region>
<settlement type="town">Heverlee</settlement>
<settlement type="city">Louvain</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Delalieux, Stephanie" sort="Delalieux, Stephanie" uniqKey="Delalieux S" first="Stephanie" last="Delalieux">Stephanie Delalieux</name>
<affiliation wicri:level="3"><inist:fA14 i1="01"><s1>Dept. of Biosystems, M3-BIORES, Katholieke Universiteit Leuven, W. de Croylaan 34</s1>
<s2>3001 Leuven</s2>
<s3>BEL</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
<sZ>7 aut.</sZ>
</inist:fA14>
<country>Belgique</country>
<placeName><region type="province" nuts="2">Province du Brabant flamand</region>
<settlement type="town">Heverlee</settlement>
<settlement type="city">Louvain</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Stuckens, Jan" sort="Stuckens, Jan" uniqKey="Stuckens J" first="Jan" last="Stuckens">Jan Stuckens</name>
<affiliation wicri:level="3"><inist:fA14 i1="01"><s1>Dept. of Biosystems, M3-BIORES, Katholieke Universiteit Leuven, W. de Croylaan 34</s1>
<s2>3001 Leuven</s2>
<s3>BEL</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
<sZ>7 aut.</sZ>
</inist:fA14>
<country>Belgique</country>
<placeName><region type="province" nuts="2">Province du Brabant flamand</region>
<settlement type="town">Heverlee</settlement>
<settlement type="city">Louvain</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Van Der Zande, Dimitry" sort="Van Der Zande, Dimitry" uniqKey="Van Der Zande D" first="Dimitry" last="Van Der Zande">Dimitry Van Der Zande</name>
<affiliation wicri:level="3"><inist:fA14 i1="01"><s1>Dept. of Biosystems, M3-BIORES, Katholieke Universiteit Leuven, W. de Croylaan 34</s1>
<s2>3001 Leuven</s2>
<s3>BEL</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
<sZ>7 aut.</sZ>
</inist:fA14>
<country>Belgique</country>
<placeName><region type="province" nuts="2">Province du Brabant flamand</region>
<settlement type="town">Heverlee</settlement>
<settlement type="city">Louvain</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Verstraeten, Willem W" sort="Verstraeten, Willem W" uniqKey="Verstraeten W" first="Willem W." last="Verstraeten">Willem W. Verstraeten</name>
<affiliation wicri:level="3"><inist:fA14 i1="01"><s1>Dept. of Biosystems, M3-BIORES, Katholieke Universiteit Leuven, W. de Croylaan 34</s1>
<s2>3001 Leuven</s2>
<s3>BEL</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
<sZ>7 aut.</sZ>
</inist:fA14>
<country>Belgique</country>
<placeName><region type="province" nuts="2">Province du Brabant flamand</region>
<settlement type="town">Heverlee</settlement>
<settlement type="city">Louvain</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Coppin, Pol" sort="Coppin, Pol" uniqKey="Coppin P" first="Pol" last="Coppin">Pol Coppin</name>
<affiliation wicri:level="3"><inist:fA14 i1="01"><s1>Dept. of Biosystems, M3-BIORES, Katholieke Universiteit Leuven, W. de Croylaan 34</s1>
<s2>3001 Leuven</s2>
<s3>BEL</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
<sZ>7 aut.</sZ>
</inist:fA14>
<country>Belgique</country>
<placeName><region type="province" nuts="2">Province du Brabant flamand</region>
<settlement type="town">Heverlee</settlement>
<settlement type="city">Louvain</settlement>
</placeName>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">09-0440662</idno>
<date when="2009">2009</date>
<idno type="stanalyst">PASCAL 09-0440662 INIST</idno>
<idno type="RBID">Pascal:09-0440662</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000292</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000711</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000288</idno>
<idno type="wicri:doubleKey">0034-4257:2009:Somers B:nonlinear:hyperspectral:mixture</idno>
<idno type="wicri:Area/Main/Merge">001F89</idno>
<idno type="wicri:Area/Main/Curation">001F39</idno>
<idno type="wicri:Area/Main/Exploration">001F39</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Nonlinear Hyperspectral Mixture Analysis for tree cover estimates in orchards</title>
<author><name sortKey="Somers, Ben" sort="Somers, Ben" uniqKey="Somers B" first="Ben" last="Somers">Ben Somers</name>
<affiliation wicri:level="3"><inist:fA14 i1="01"><s1>Dept. of Biosystems, M3-BIORES, Katholieke Universiteit Leuven, W. de Croylaan 34</s1>
<s2>3001 Leuven</s2>
<s3>BEL</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
<sZ>7 aut.</sZ>
</inist:fA14>
<country>Belgique</country>
<placeName><region type="province" nuts="2">Province du Brabant flamand</region>
<settlement type="town">Heverlee</settlement>
<settlement type="city">Louvain</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Cools, Kenneth" sort="Cools, Kenneth" uniqKey="Cools K" first="Kenneth" last="Cools">Kenneth Cools</name>
<affiliation wicri:level="3"><inist:fA14 i1="01"><s1>Dept. of Biosystems, M3-BIORES, Katholieke Universiteit Leuven, W. de Croylaan 34</s1>
<s2>3001 Leuven</s2>
<s3>BEL</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
<sZ>7 aut.</sZ>
</inist:fA14>
<country>Belgique</country>
<placeName><region type="province" nuts="2">Province du Brabant flamand</region>
<settlement type="town">Heverlee</settlement>
<settlement type="city">Louvain</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Delalieux, Stephanie" sort="Delalieux, Stephanie" uniqKey="Delalieux S" first="Stephanie" last="Delalieux">Stephanie Delalieux</name>
<affiliation wicri:level="3"><inist:fA14 i1="01"><s1>Dept. of Biosystems, M3-BIORES, Katholieke Universiteit Leuven, W. de Croylaan 34</s1>
<s2>3001 Leuven</s2>
<s3>BEL</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
<sZ>7 aut.</sZ>
</inist:fA14>
<country>Belgique</country>
<placeName><region type="province" nuts="2">Province du Brabant flamand</region>
<settlement type="town">Heverlee</settlement>
<settlement type="city">Louvain</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Stuckens, Jan" sort="Stuckens, Jan" uniqKey="Stuckens J" first="Jan" last="Stuckens">Jan Stuckens</name>
<affiliation wicri:level="3"><inist:fA14 i1="01"><s1>Dept. of Biosystems, M3-BIORES, Katholieke Universiteit Leuven, W. de Croylaan 34</s1>
<s2>3001 Leuven</s2>
<s3>BEL</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
<sZ>7 aut.</sZ>
</inist:fA14>
<country>Belgique</country>
<placeName><region type="province" nuts="2">Province du Brabant flamand</region>
<settlement type="town">Heverlee</settlement>
<settlement type="city">Louvain</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Van Der Zande, Dimitry" sort="Van Der Zande, Dimitry" uniqKey="Van Der Zande D" first="Dimitry" last="Van Der Zande">Dimitry Van Der Zande</name>
<affiliation wicri:level="3"><inist:fA14 i1="01"><s1>Dept. of Biosystems, M3-BIORES, Katholieke Universiteit Leuven, W. de Croylaan 34</s1>
<s2>3001 Leuven</s2>
<s3>BEL</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
<sZ>7 aut.</sZ>
</inist:fA14>
<country>Belgique</country>
<placeName><region type="province" nuts="2">Province du Brabant flamand</region>
<settlement type="town">Heverlee</settlement>
<settlement type="city">Louvain</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Verstraeten, Willem W" sort="Verstraeten, Willem W" uniqKey="Verstraeten W" first="Willem W." last="Verstraeten">Willem W. Verstraeten</name>
<affiliation wicri:level="3"><inist:fA14 i1="01"><s1>Dept. of Biosystems, M3-BIORES, Katholieke Universiteit Leuven, W. de Croylaan 34</s1>
<s2>3001 Leuven</s2>
<s3>BEL</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
<sZ>7 aut.</sZ>
</inist:fA14>
<country>Belgique</country>
<placeName><region type="province" nuts="2">Province du Brabant flamand</region>
<settlement type="town">Heverlee</settlement>
<settlement type="city">Louvain</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Coppin, Pol" sort="Coppin, Pol" uniqKey="Coppin P" first="Pol" last="Coppin">Pol Coppin</name>
<affiliation wicri:level="3"><inist:fA14 i1="01"><s1>Dept. of Biosystems, M3-BIORES, Katholieke Universiteit Leuven, W. de Croylaan 34</s1>
<s2>3001 Leuven</s2>
<s3>BEL</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>6 aut.</sZ>
<sZ>7 aut.</sZ>
</inist:fA14>
<country>Belgique</country>
<placeName><region type="province" nuts="2">Province du Brabant flamand</region>
<settlement type="town">Heverlee</settlement>
<settlement type="city">Louvain</settlement>
</placeName>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">Remote sensing of environment</title>
<title level="j" type="abbreviated">Remote sens. environ.</title>
<idno type="ISSN">0034-4257</idno>
<imprint><date when="2009">2009</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">Remote sensing of environment</title>
<title level="j" type="abbreviated">Remote sens. environ.</title>
<idno type="ISSN">0034-4257</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Citrus sinensis</term>
<term>Conceptual analysis</term>
<term>Hyperspectral characteristic</term>
<term>Information</term>
<term>Multiple scattering</term>
<term>Nonlinearity</term>
<term>Orchard</term>
<term>Pixel</term>
<term>in situ</term>
<term>management</term>
<term>mixing</term>
<term>monitoring</term>
<term>physical properties</term>
<term>remote sensing</term>
<term>spatiotemporal variations</term>
<term>testing</term>
<term>trees</term>
<term>vegetation</term>
<term>wave scattering</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Non linéarité</term>
<term>Caractéristique hyperspectrale</term>
<term>Végétation</term>
<term>Analyse conceptuelle</term>
<term>Arbre</term>
<term>Verger</term>
<term>Surveillance</term>
<term>Variation spatiotemporelle</term>
<term>Information</term>
<term>Gestion</term>
<term>Mixage</term>
<term>Expérimentation</term>
<term>Diffusion multiple</term>
<term>In situ</term>
<term>Pixel</term>
<term>Citrus sinensis</term>
<term>Propriété physique</term>
<term>Télédétection hyperspectrale</term>
<term>Télédétection</term>
<term>Diffusion onde</term>
</keywords>
<keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Arbre</term>
<term>Verger</term>
<term>Information</term>
<term>Gestion</term>
<term>Télédétection</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Accurate monitoring of spatial and temporal variation in tree cover provides essential information for steering management practices in orchards. In this light, the present study investigates the potential of Hyperspectral Mixture Analysis. Specific focus lies on a thorough study of non-linear mixing effects caused by multiple photon scattering. In a series of experiments the importance of multiple scattering is demonstrated while a novel conceptual Nonlinear Spectral Mixture Analysis approach is presented and successfully tested on in situ measured mixed pixels in Citrus sinensis L. orchards. The rationale behind the approach is the redistribution of nonlinear fractions (i.e., virtual fractions) among the actual physical ground cover entities (e.g., tree, soil). These 'virtual' fractions, which account for the extent and nature of multiple photon scattering only have a physical meaning at the spectral level but cannot be interpreted as an actual physical part of the ground cover. Results illustrate that the effect of multiple scattering on Spectral Mixture Analysis is significant as the linear approach provides a mean relative root mean square error (RMSE) for tree cover fraction estimates of 27%. While traditional nonlinear approaches only slightly reduce this error (RMSE=23%), important improvements are obtained for the novel Nonlinear Spectral Mixture Analysis approach (RMSE = 12%).</div>
</front>
</TEI>
<affiliations><list><country><li>Belgique</li>
</country>
<region><li>Province du Brabant flamand</li>
</region>
<settlement><li>Heverlee</li>
<li>Louvain</li>
</settlement>
</list>
<tree><country name="Belgique"><region name="Province du Brabant flamand"><name sortKey="Somers, Ben" sort="Somers, Ben" uniqKey="Somers B" first="Ben" last="Somers">Ben Somers</name>
</region>
<name sortKey="Cools, Kenneth" sort="Cools, Kenneth" uniqKey="Cools K" first="Kenneth" last="Cools">Kenneth Cools</name>
<name sortKey="Coppin, Pol" sort="Coppin, Pol" uniqKey="Coppin P" first="Pol" last="Coppin">Pol Coppin</name>
<name sortKey="Delalieux, Stephanie" sort="Delalieux, Stephanie" uniqKey="Delalieux S" first="Stephanie" last="Delalieux">Stephanie Delalieux</name>
<name sortKey="Stuckens, Jan" sort="Stuckens, Jan" uniqKey="Stuckens J" first="Jan" last="Stuckens">Jan Stuckens</name>
<name sortKey="Van Der Zande, Dimitry" sort="Van Der Zande, Dimitry" uniqKey="Van Der Zande D" first="Dimitry" last="Van Der Zande">Dimitry Van Der Zande</name>
<name sortKey="Verstraeten, Willem W" sort="Verstraeten, Willem W" uniqKey="Verstraeten W" first="Willem W." last="Verstraeten">Willem W. Verstraeten</name>
</country>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Bois/explor/OrangerV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 001F39 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001F39 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Bois |area= OrangerV1 |flux= Main |étape= Exploration |type= RBID |clé= Pascal:09-0440662 |texte= Nonlinear Hyperspectral Mixture Analysis for tree cover estimates in orchards }}
This area was generated with Dilib version V0.6.25. |