Afficher la notice abrégée

Crop stem detection and tracking for precision hoeing using deep learning

dc.rights.licenseopenen_US
hal.structure.identifierLaboratoire de l'intégration, du matériau au système [IMS]
dc.contributor.authorLAC, Louis
hal.structure.identifierLaboratoire de l'intégration, du matériau au système [IMS]
dc.contributor.authorDA COSTA, Jean-Pierre
ORCID: 0000-0003-2390-0047
IDREF: 060561459
hal.structure.identifierLaboratoire de l'intégration, du matériau au système [IMS]
dc.contributor.authorDONIAS, Marc
hal.structure.identifierLaboratoire de l'intégration, du matériau au système [IMS]
dc.contributor.authorKERESZTES, Barna
IDREF: 143373161
dc.contributor.authorBARDET, Alain
dc.date.accessioned2022-07-13T08:22:36Z
dc.date.available2022-07-13T08:22:36Z
dc.date.issued2022-01
dc.identifier.issn0168-1699en_US
dc.identifier.urioai:crossref.org:10.1016/j.compag.2021.106606
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/140461
dc.description.abstractEnDeveloping alternatives to the chemical weeding process usually carried out in vegetable crop farming is necessary in order to reach a more sustainable agriculture. However, a precise mechanical weeding requires specific sensors and advanced computer vision algorithms to process crop and weed discrimination in real-time. In this paper we propose an algorithm able to detect, locate, and track the stem position of crops in images which is suitable for precision actions in vegetable fields such as mechanical hoeing within crop rows. The algorithm is twofold: (i) a deep neural network for object detection is first used to detect crop stems in individual RGB images and then (ii) an aggregation algorithm further refines the detections taking advantage of the temporal redundancy in consecutive frames. We evaluated the pipeline on images of maize and bean crops at an early stage of development, acquired in field conditions with a camera embedded in an experimental mechanical weeding system. We reported F1-scores of respectively 94.74% and 93.82% with a location accuracy around 0.7 cm when compared with human annotation. Moreover, this pipeline can operate in real-time on an embedded computer consuming as little power as 30 W.
dc.description.sponsorshipBloc-outil et Imagerie de Précision pour le Binage Intra-rang Précoce - ANR-17-ROSE-0001en_US
dc.language.isoENen_US
dc.sourcecrossref
dc.subject.enPrecision agriculture
dc.subject.enDeep learning
dc.subject.enNeural network
dc.subject.enObject detection
dc.subject.enTracking algorithm
dc.title.enCrop stem detection and tracking for precision hoeing using deep learning
dc.typeArticle de revueen_US
dc.identifier.doi10.1016/j.compag.2021.106606en_US
dc.subject.halSciences de l'ingénieur [physics]/Traitement du signal et de l'imageen_US
bordeaux.journalComputers and Electronics in Agricultureen_US
bordeaux.page106606en_US
bordeaux.volume192en_US
bordeaux.hal.laboratoriesLaboratoire d’Intégration du Matériau au Système (IMS) - UMR 5218en_US
bordeaux.institutionUniversité de Bordeauxen_US
bordeaux.institutionBordeaux INPen_US
bordeaux.institutionCNRSen_US
bordeaux.peerReviewedouien_US
bordeaux.inpressnonen_US
bordeaux.import.sourcedissemin
hal.identifierhal-03722088
hal.version1
hal.date.transferred2022-07-13T08:22:38Z
hal.exporttrue
workflow.import.sourcedissemin
dc.rights.ccPas de Licence CCen_US
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=Computers%20and%20Electronics%20in%20Agriculture&rft.date=2022-01&rft.volume=192&rft.spage=106606&rft.epage=106606&rft.eissn=0168-1699&rft.issn=0168-1699&rft.au=LAC,%20Louis&DA%20COSTA,%20Jean-Pierre&DONIAS,%20Marc&KERESZTES,%20Barna&BARDET,%20Alain&rft.genre=article


Fichier(s) constituant ce document

FichiersTailleFormatVue

Il n'y a pas de fichiers associés à ce document.

Ce document figure dans la(les) collection(s) suivante(s)

Afficher la notice abrégée