Publikace UTB
Repozitář publikační činnosti UTB

Scouting of whiteflies in tomato greenhouse environment using deep learning

Repozitář DSpace/Manakin

Zobrazit minimální záznam


dc.title Scouting of whiteflies in tomato greenhouse environment using deep learning en
dc.contributor.author Tureček, Tomáš
dc.contributor.author Vařacha, Pavel
dc.contributor.author Turečková, Alžběta
dc.contributor.author Psota, Václav
dc.contributor.author Janků, Peter
dc.contributor.author Štěpánek, Vít
dc.contributor.author Viktorin, Adam
dc.contributor.author Šenkeřík, Roman
dc.contributor.author Jašek, Roman
dc.contributor.author Chramcov, Bronislav
dc.contributor.author Grivas, Ioannis
dc.contributor.author Komínková Oplatková, Zuzana
dc.relation.ispartof Smart Innovation, Systems and Technologies
dc.identifier.issn 2190-3018 Scopus Sources, Sherpa/RoMEO, JCR
dc.identifier.isbn 978-981-16-3348-5
dc.date.issued 2022
utb.relation.volume 245
dc.citation.spage 323
dc.citation.epage 335
dc.event.title 1st International Conference on Agriculture Digitalization and Organic Production, ADOP 2021
dc.event.location St. Petersburg
utb.event.state-en Russia
utb.event.state-cs Rusko
dc.event.sdate 2021-06-07
dc.event.edate 2021-06-09
dc.type conferenceObject
dc.language.iso en
dc.publisher Springer Science and Business Media Deutschland GmbH
dc.identifier.doi 10.1007/978-981-16-3349-2_27
dc.relation.uri https://link.springer.com/chapter/10.1007/978-981-16-3349-2_27
dc.subject automated counting en
dc.subject convolutional neural network en
dc.subject deep transfer learning en
dc.subject faster R-CNN en
dc.subject tomato greenhouse en
dc.subject whiteflies scouting en
dc.description.abstract This study shows the possibilities of how to replace tedious human labor—scouting of yellow sticky traps (YST) for whiteflies—using artificial cognitive vision, specifically the deep convolutional network (CNN), as a part of the more complex system—BERABOT. The used CNN is the Faster R-CNN trained by deep transfer learning to substitute human scouting when the low whiteflies infection phase was specifically targeted. The training was conducted on pictures taken inside the heated and lighted tomato production greenhouse of “Bezdínek Farm” in Dolni Lutyne, Czechia. Used pictures were collected in a way planned for future fully automated robotic applications in the BERABOT system. The achieved results were compared with the scouting results of a professional phytopathologist. The trained employee’s scouting results against the professional phytopathologist accomplished root-mean-square error (RMSE) equal to 4.23, while the developed CNN model was evaluated to be 5.83. The results presented here open up new frontiers for further CNN model tuning leading to the potential in substituting an employee(s) in the future and make tomato production less expensive and less human labor dependent. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. en
utb.faculty Faculty of Applied Informatics
dc.identifier.uri http://hdl.handle.net/10563/1010583
utb.identifier.obdid 43883183
utb.identifier.scopus 2-s2.0-85115131306
utb.source d-scopus
dc.date.accessioned 2021-10-08T21:13:50Z
dc.date.available 2021-10-08T21:13:50Z
dc.description.sponsorship IGA/CebiaTech/2021/001; Technology Agency of the Czech Republic, TACR: FW01010381
utb.contributor.internalauthor Tureček, Tomáš
utb.contributor.internalauthor Vařacha, Pavel
utb.contributor.internalauthor Turečková, Alžběta
utb.contributor.internalauthor Janků, Peter
utb.contributor.internalauthor Viktorin, Adam
utb.contributor.internalauthor Šenkeřík, Roman
utb.contributor.internalauthor Jašek, Roman
utb.contributor.internalauthor Chramcov, Bronislav
utb.contributor.internalauthor Komínková Oplatková, Zuzana
utb.fulltext.affiliation 1 Tomáš Tureček, Pavel Vařacha, Alžběta Turečková, Peter Janků, Adam Viktorin, Roman Šenkeřík, Roman Jašek, Bronislav Chramcov, Zuzana Komínková Oplatková 2 Václav Psota, Vít Štěpánek 3 Ioannis Grivas 1 Tomas Bata University in Zlín, nám. T. G. Masaryka 5555, 760 01 Zlín, Czechia {tturecek, varacha, tureckova, janku, viktorin, senkerik, jasek, chramcov, oplatkova}@utb.cz | http://www.utb.cz 2 NWT a.s., třída Tomáše Bati 269, 760 01 Zlín, Czechia {vaclav.psota,vit.stepanek}@nwt.cz | http://www.nwt.cz 3 University of Thessaly General Department (Lamia), Greece igrivas1@uth.gr
utb.fulltext.dates -
utb.fulltext.sponsorship This work is supported by the Technology Agency of the Czech Republic under the TREND Programme, project No. FW01010381, resources of A.I.Lab (ailab.fai.utb.cz) at the Faculty of Applied Informatics, Tomas Bata University in Zlin (TBU), and by Internal Grant Agency of TBU under the project no. IGA/CebiaTech/2021/001.
utb.scopus.affiliation Tomas Bata University in Zlín, nám. T. G. Masaryka 5555, Zlín, 760 01, Czech Republic; NWT a.s., třída Tomáše Bati 269, Zlín, 760 01, Czech Republic; General Department (Lamia), University of Thessaly, Volos, Greece
utb.fulltext.projects FW01010381
utb.fulltext.projects IGA/CebiaTech/2021/001
utb.fulltext.faculty -
utb.fulltext.ou -
Find Full text

Soubory tohoto záznamu

Zobrazit minimální záznam