A Non-Invasive Method Based on Computer Vision for Grapevine Cluster Compactness Assessment Using a Mobile Sensing Platform under Field Conditions.
Identifieur interne : 000202 ( Main/Exploration ); précédent : 000201; suivant : 000203A Non-Invasive Method Based on Computer Vision for Grapevine Cluster Compactness Assessment Using a Mobile Sensing Platform under Field Conditions.
Auteurs : Fernando Palacios [Espagne] ; Maria P. Diago [Espagne] ; Javier Tardaguila [Espagne]Source :
- Sensors (Basel, Switzerland) [ 1424-8220 ] ; 2019.
Abstract
Grapevine cluster compactness affects grape composition, fungal disease incidence, and wine quality. Thus far, cluster compactness assessment has been based on visual inspection performed by trained evaluators with very scarce application in the wine industry. The goal of this work was to develop a new, non-invasive method based on the combination of computer vision and machine learning technology for cluster compactness assessment under field conditions from on-the-go red, green, blue (RGB) image acquisition. A mobile sensing platform was used to automatically capture RGB images of grapevine canopies and fruiting zones at night using artificial illumination. Likewise, a set of 195 clusters of four red grapevine varieties of three commercial vineyards were photographed during several years one week prior to harvest. After image acquisition, cluster compactness was evaluated by a group of 15 experts in the laboratory following the International Organization of Vine and Wine (OIV) 204 standard as a reference method. The developed algorithm comprises several steps, including an initial, semi-supervised image segmentation, followed by automated cluster detection and automated compactness estimation using a Gaussian process regression model. Calibration (95 clusters were used as a training set and 100 clusters as the test set) and leave-one-out cross-validation models (LOOCV; performed on the whole 195 clusters set) were elaborated. For these, determination coefficient (R2) of 0.68 and a root mean squared error (RMSE) of 0.96 were obtained on the test set between the image-based compactness estimated values and the average of the evaluators' ratings (in the range from 1-9). Additionally, the leave-one-out cross-validation yielded a R2 of 0.70 and an RMSE of 1.11. The results show that the newly developed computer vision based method could be commercially applied by the wine industry for efficient cluster compactness estimation from RGB on-the-go image acquisition platforms in commercial vineyards.
DOI: 10.3390/s19173799
PubMed: 31480754
PubMed Central: PMC6749308
Affiliations:
Links toward previous steps (curation, corpus...)
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">A Non-Invasive Method Based on Computer Vision for Grapevine Cluster Compactness Assessment Using a Mobile Sensing Platform under Field Conditions.</title><author><name sortKey="Palacios, Fernando" sort="Palacios, Fernando" uniqKey="Palacios F" first="Fernando" last="Palacios">Fernando Palacios</name><affiliation wicri:level="2"><nlm:affiliation>Televitis Research Group, University of La Rioja, 26006 Logroño (La Rioja), Spain.</nlm:affiliation><country xml:lang="fr">Espagne</country><wicri:regionArea>Televitis Research Group, University of La Rioja, 26006 Logroño (La Rioja)</wicri:regionArea><placeName><region nuts="2" type="communauté">La Rioja</region></placeName></affiliation><affiliation wicri:level="2"><nlm:affiliation>Instituto de Ciencias de la Vid y del Vino, University of La Rioja, CSIC, Gobierno de La Rioja, 26007 Logroño, Spain.</nlm:affiliation><country xml:lang="fr">Espagne</country><wicri:regionArea>Instituto de Ciencias de la Vid y del Vino, University of La Rioja, CSIC, Gobierno de La Rioja, 26007 Logroño</wicri:regionArea><placeName><region nuts="2" type="communauté">La Rioja</region></placeName></affiliation></author><author><name sortKey="Diago, Maria P" sort="Diago, Maria P" uniqKey="Diago M" first="Maria P" last="Diago">Maria P. Diago</name><affiliation wicri:level="2"><nlm:affiliation>Televitis Research Group, University of La Rioja, 26006 Logroño (La Rioja), Spain.</nlm:affiliation><country xml:lang="fr">Espagne</country><wicri:regionArea>Televitis Research Group, University of La Rioja, 26006 Logroño (La Rioja)</wicri:regionArea><placeName><region nuts="2" type="communauté">La Rioja</region></placeName></affiliation><affiliation wicri:level="2"><nlm:affiliation>Instituto de Ciencias de la Vid y del Vino, University of La Rioja, CSIC, Gobierno de La Rioja, 26007 Logroño, Spain.</nlm:affiliation><country xml:lang="fr">Espagne</country><wicri:regionArea>Instituto de Ciencias de la Vid y del Vino, University of La Rioja, CSIC, Gobierno de La Rioja, 26007 Logroño</wicri:regionArea><placeName><region nuts="2" type="communauté">La Rioja</region></placeName></affiliation></author><author><name sortKey="Tardaguila, Javier" sort="Tardaguila, Javier" uniqKey="Tardaguila J" first="Javier" last="Tardaguila">Javier Tardaguila</name><affiliation wicri:level="2"><nlm:affiliation>Televitis Research Group, University of La Rioja, 26006 Logroño (La Rioja), Spain. javier.tardaguila@unirioja.es.</nlm:affiliation><country xml:lang="fr">Espagne</country><wicri:regionArea>Televitis Research Group, University of La Rioja, 26006 Logroño (La Rioja)</wicri:regionArea><placeName><region nuts="2" type="communauté">La Rioja</region></placeName></affiliation><affiliation wicri:level="2"><nlm:affiliation>Instituto de Ciencias de la Vid y del Vino, University of La Rioja, CSIC, Gobierno de La Rioja, 26007 Logroño, Spain. javier.tardaguila@unirioja.es.</nlm:affiliation><country xml:lang="fr">Espagne</country><wicri:regionArea>Instituto de Ciencias de la Vid y del Vino, University of La Rioja, CSIC, Gobierno de La Rioja, 26007 Logroño</wicri:regionArea><placeName><region nuts="2" type="communauté">La Rioja</region></placeName></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">PubMed</idno><date when="2019">2019</date><idno type="RBID">pubmed:31480754</idno><idno type="pmid">31480754</idno><idno type="doi">10.3390/s19173799</idno><idno type="pmc">PMC6749308</idno><idno type="wicri:Area/Main/Corpus">000141</idno><idno type="wicri:explorRef" wicri:stream="Main" wicri:step="Corpus" wicri:corpus="PubMed">000141</idno><idno type="wicri:Area/Main/Curation">000141</idno><idno type="wicri:explorRef" wicri:stream="Main" wicri:step="Curation">000141</idno><idno type="wicri:Area/Main/Exploration">000141</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">A Non-Invasive Method Based on Computer Vision for Grapevine Cluster Compactness Assessment Using a Mobile Sensing Platform under Field Conditions.</title><author><name sortKey="Palacios, Fernando" sort="Palacios, Fernando" uniqKey="Palacios F" first="Fernando" last="Palacios">Fernando Palacios</name><affiliation wicri:level="2"><nlm:affiliation>Televitis Research Group, University of La Rioja, 26006 Logroño (La Rioja), Spain.</nlm:affiliation><country xml:lang="fr">Espagne</country><wicri:regionArea>Televitis Research Group, University of La Rioja, 26006 Logroño (La Rioja)</wicri:regionArea><placeName><region nuts="2" type="communauté">La Rioja</region></placeName></affiliation><affiliation wicri:level="2"><nlm:affiliation>Instituto de Ciencias de la Vid y del Vino, University of La Rioja, CSIC, Gobierno de La Rioja, 26007 Logroño, Spain.</nlm:affiliation><country xml:lang="fr">Espagne</country><wicri:regionArea>Instituto de Ciencias de la Vid y del Vino, University of La Rioja, CSIC, Gobierno de La Rioja, 26007 Logroño</wicri:regionArea><placeName><region nuts="2" type="communauté">La Rioja</region></placeName></affiliation></author><author><name sortKey="Diago, Maria P" sort="Diago, Maria P" uniqKey="Diago M" first="Maria P" last="Diago">Maria P. Diago</name><affiliation wicri:level="2"><nlm:affiliation>Televitis Research Group, University of La Rioja, 26006 Logroño (La Rioja), Spain.</nlm:affiliation><country xml:lang="fr">Espagne</country><wicri:regionArea>Televitis Research Group, University of La Rioja, 26006 Logroño (La Rioja)</wicri:regionArea><placeName><region nuts="2" type="communauté">La Rioja</region></placeName></affiliation><affiliation wicri:level="2"><nlm:affiliation>Instituto de Ciencias de la Vid y del Vino, University of La Rioja, CSIC, Gobierno de La Rioja, 26007 Logroño, Spain.</nlm:affiliation><country xml:lang="fr">Espagne</country><wicri:regionArea>Instituto de Ciencias de la Vid y del Vino, University of La Rioja, CSIC, Gobierno de La Rioja, 26007 Logroño</wicri:regionArea><placeName><region nuts="2" type="communauté">La Rioja</region></placeName></affiliation></author><author><name sortKey="Tardaguila, Javier" sort="Tardaguila, Javier" uniqKey="Tardaguila J" first="Javier" last="Tardaguila">Javier Tardaguila</name><affiliation wicri:level="2"><nlm:affiliation>Televitis Research Group, University of La Rioja, 26006 Logroño (La Rioja), Spain. javier.tardaguila@unirioja.es.</nlm:affiliation><country xml:lang="fr">Espagne</country><wicri:regionArea>Televitis Research Group, University of La Rioja, 26006 Logroño (La Rioja)</wicri:regionArea><placeName><region nuts="2" type="communauté">La Rioja</region></placeName></affiliation><affiliation wicri:level="2"><nlm:affiliation>Instituto de Ciencias de la Vid y del Vino, University of La Rioja, CSIC, Gobierno de La Rioja, 26007 Logroño, Spain. javier.tardaguila@unirioja.es.</nlm:affiliation><country xml:lang="fr">Espagne</country><wicri:regionArea>Instituto de Ciencias de la Vid y del Vino, University of La Rioja, CSIC, Gobierno de La Rioja, 26007 Logroño</wicri:regionArea><placeName><region nuts="2" type="communauté">La Rioja</region></placeName></affiliation></author></analytic><series><title level="j">Sensors (Basel, Switzerland)</title><idno type="eISSN">1424-8220</idno><imprint><date when="2019" type="published">2019</date></imprint></series></biblStruct></sourceDesc></fileDesc><profileDesc><textClass></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Grapevine cluster compactness affects grape composition, fungal disease incidence, and wine quality. Thus far, cluster compactness assessment has been based on visual inspection performed by trained evaluators with very scarce application in the wine industry. The goal of this work was to develop a new, non-invasive method based on the combination of computer vision and machine learning technology for cluster compactness assessment under field conditions from on-the-go red, green, blue (RGB) image acquisition. A mobile sensing platform was used to automatically capture RGB images of grapevine canopies and fruiting zones at night using artificial illumination. Likewise, a set of 195 clusters of four red grapevine varieties of three commercial vineyards were photographed during several years one week prior to harvest. After image acquisition, cluster compactness was evaluated by a group of 15 experts in the laboratory following the International Organization of Vine and Wine (OIV) 204 standard as a reference method. The developed algorithm comprises several steps, including an initial, semi-supervised image segmentation, followed by automated cluster detection and automated compactness estimation using a Gaussian process regression model. Calibration (95 clusters were used as a training set and 100 clusters as the test set) and leave-one-out cross-validation models (LOOCV; performed on the whole 195 clusters set) were elaborated. For these, determination coefficient (R<sup>2</sup>) of 0.68 and a root mean squared error (RMSE) of 0.96 were obtained on the test set between the image-based compactness estimated values and the average of the evaluators' ratings (in the range from 1-9). Additionally, the leave-one-out cross-validation yielded a R<sup>2</sup> of 0.70 and an RMSE of 1.11. The results show that the newly developed computer vision based method could be commercially applied by the wine industry for efficient cluster compactness estimation from RGB on-the-go image acquisition platforms in commercial vineyards.</div></front></TEI><pubmed><MedlineCitation Status="PubMed-not-MEDLINE" Owner="NLM"><PMID Version="1">31480754</PMID><DateRevised><Year>2020</Year><Month>02</Month><Day>25</Day></DateRevised><Article PubModel="Electronic"><Journal><ISSN IssnType="Electronic">1424-8220</ISSN><JournalIssue CitedMedium="Internet"><Volume>19</Volume><Issue>17</Issue><PubDate><Year>2019</Year><Month>Sep</Month><Day>02</Day></PubDate></JournalIssue><Title>Sensors (Basel, Switzerland)</Title><ISOAbbreviation>Sensors (Basel)</ISOAbbreviation></Journal><ArticleTitle>A Non-Invasive Method Based on Computer Vision for Grapevine Cluster Compactness Assessment Using a Mobile Sensing Platform under Field Conditions.</ArticleTitle><ELocationID EIdType="pii" ValidYN="Y">E3799</ELocationID><ELocationID EIdType="doi" ValidYN="Y">10.3390/s19173799</ELocationID><Abstract><AbstractText>Grapevine cluster compactness affects grape composition, fungal disease incidence, and wine quality. Thus far, cluster compactness assessment has been based on visual inspection performed by trained evaluators with very scarce application in the wine industry. The goal of this work was to develop a new, non-invasive method based on the combination of computer vision and machine learning technology for cluster compactness assessment under field conditions from on-the-go red, green, blue (RGB) image acquisition. A mobile sensing platform was used to automatically capture RGB images of grapevine canopies and fruiting zones at night using artificial illumination. Likewise, a set of 195 clusters of four red grapevine varieties of three commercial vineyards were photographed during several years one week prior to harvest. After image acquisition, cluster compactness was evaluated by a group of 15 experts in the laboratory following the International Organization of Vine and Wine (OIV) 204 standard as a reference method. The developed algorithm comprises several steps, including an initial, semi-supervised image segmentation, followed by automated cluster detection and automated compactness estimation using a Gaussian process regression model. Calibration (95 clusters were used as a training set and 100 clusters as the test set) and leave-one-out cross-validation models (LOOCV; performed on the whole 195 clusters set) were elaborated. For these, determination coefficient (R<sup>2</sup>) of 0.68 and a root mean squared error (RMSE) of 0.96 were obtained on the test set between the image-based compactness estimated values and the average of the evaluators' ratings (in the range from 1-9). Additionally, the leave-one-out cross-validation yielded a R<sup>2</sup> of 0.70 and an RMSE of 1.11. The results show that the newly developed computer vision based method could be commercially applied by the wine industry for efficient cluster compactness estimation from RGB on-the-go image acquisition platforms in commercial vineyards.</AbstractText></Abstract><AuthorList CompleteYN="Y"><Author ValidYN="Y"><LastName>Palacios</LastName><ForeName>Fernando</ForeName><Initials>F</Initials><AffiliationInfo><Affiliation>Televitis Research Group, University of La Rioja, 26006 Logroño (La Rioja), Spain.</Affiliation></AffiliationInfo><AffiliationInfo><Affiliation>Instituto de Ciencias de la Vid y del Vino, University of La Rioja, CSIC, Gobierno de La Rioja, 26007 Logroño, Spain.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Diago</LastName><ForeName>Maria P</ForeName><Initials>MP</Initials><AffiliationInfo><Affiliation>Televitis Research Group, University of La Rioja, 26006 Logroño (La Rioja), Spain.</Affiliation></AffiliationInfo><AffiliationInfo><Affiliation>Instituto de Ciencias de la Vid y del Vino, University of La Rioja, CSIC, Gobierno de La Rioja, 26007 Logroño, Spain.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Tardaguila</LastName><ForeName>Javier</ForeName><Initials>J</Initials><AffiliationInfo><Affiliation>Televitis Research Group, University of La Rioja, 26006 Logroño (La Rioja), Spain. javier.tardaguila@unirioja.es.</Affiliation></AffiliationInfo><AffiliationInfo><Affiliation>Instituto de Ciencias de la Vid y del Vino, University of La Rioja, CSIC, Gobierno de La Rioja, 26007 Logroño, Spain. javier.tardaguila@unirioja.es.</Affiliation></AffiliationInfo></Author></AuthorList><Language>eng</Language><PublicationTypeList><PublicationType UI="D016428">Journal Article</PublicationType></PublicationTypeList><ArticleDate DateType="Electronic"><Year>2019</Year><Month>09</Month><Day>02</Day></ArticleDate></Article><MedlineJournalInfo><Country>Switzerland</Country><MedlineTA>Sensors (Basel)</MedlineTA><NlmUniqueID>101204366</NlmUniqueID><ISSNLinking>1424-8220</ISSNLinking></MedlineJournalInfo><CitationSubset>IM</CitationSubset><KeywordList Owner="NOTNLM"><Keyword MajorTopicYN="N">RGB</Keyword><Keyword MajorTopicYN="N">cluster morphology</Keyword><Keyword MajorTopicYN="N">image analysis</Keyword><Keyword MajorTopicYN="N">machine learning</Keyword><Keyword MajorTopicYN="N">non-invasive sensing technologies</Keyword><Keyword MajorTopicYN="N">precision viticulture</Keyword><Keyword MajorTopicYN="N">proximal sensing</Keyword></KeywordList><CoiStatement>The authors declare no conflict of interest.</CoiStatement></MedlineCitation><PubmedData><History><PubMedPubDate PubStatus="received"><Year>2019</Year><Month>07</Month><Day>08</Day></PubMedPubDate><PubMedPubDate PubStatus="revised"><Year>2019</Year><Month>08</Month><Day>27</Day></PubMedPubDate><PubMedPubDate PubStatus="accepted"><Year>2019</Year><Month>08</Month><Day>30</Day></PubMedPubDate><PubMedPubDate PubStatus="entrez"><Year>2019</Year><Month>9</Month><Day>5</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="pubmed"><Year>2019</Year><Month>9</Month><Day>5</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="medline"><Year>2019</Year><Month>9</Month><Day>5</Day><Hour>6</Hour><Minute>1</Minute></PubMedPubDate></History><PublicationStatus>epublish</PublicationStatus><ArticleIdList><ArticleId IdType="pubmed">31480754</ArticleId><ArticleId IdType="pii">s19173799</ArticleId><ArticleId IdType="doi">10.3390/s19173799</ArticleId><ArticleId IdType="pmc">PMC6749308</ArticleId></ArticleIdList><ReferenceList><Reference><Citation>Phytopathology. 2012 Sep;102(9):857-66</Citation><ArticleIdList><ArticleId IdType="pubmed">22881871</ArticleId></ArticleIdList></Reference><Reference><Citation>Plant Dis. 2009 Nov;93(11):1195-1201</Citation><ArticleIdList><ArticleId IdType="pubmed">30754587</ArticleId></ArticleIdList></Reference></ReferenceList></PubmedData></pubmed><affiliations><list><country><li>Espagne</li></country><region><li>La Rioja</li></region></list><tree><country name="Espagne"><region name="La Rioja"><name sortKey="Palacios, Fernando" sort="Palacios, Fernando" uniqKey="Palacios F" first="Fernando" last="Palacios">Fernando Palacios</name></region><name sortKey="Diago, Maria P" sort="Diago, Maria P" uniqKey="Diago M" first="Maria P" last="Diago">Maria P. Diago</name><name sortKey="Diago, Maria P" sort="Diago, Maria P" uniqKey="Diago M" first="Maria P" last="Diago">Maria P. Diago</name><name sortKey="Palacios, Fernando" sort="Palacios, Fernando" uniqKey="Palacios F" first="Fernando" last="Palacios">Fernando Palacios</name><name sortKey="Tardaguila, Javier" sort="Tardaguila, Javier" uniqKey="Tardaguila J" first="Javier" last="Tardaguila">Javier Tardaguila</name><name sortKey="Tardaguila, Javier" sort="Tardaguila, Javier" uniqKey="Tardaguila J" first="Javier" last="Tardaguila">Javier Tardaguila</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Bois/explor/GrapevineDiseaseV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000202 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000202 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Bois
|area= GrapevineDiseaseV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= pubmed:31480754
|texte= A Non-Invasive Method Based on Computer Vision for Grapevine Cluster Compactness Assessment Using a Mobile Sensing Platform under Field Conditions.
}}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/Main/Exploration/RBID.i -Sk "pubmed:31480754" \
| HfdSelect -Kh $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd \
| NlmPubMed2Wicri -a GrapevineDiseaseV1
| This area was generated with Dilib version V0.6.37. |  |