Mostrar el registro sencillo del ítem

Predicting Vegetation Stratum Occupancy from Airborne LiDAR Data with Deep Learning

hal.structure.identifierLaboratoire sciences et technologies de l'information géographique [LaSTIG]
hal.structure.identifierBiodiversité, Gènes & Communautés [BioGeCo]
dc.contributor.authorKALINICHEVA, Ekaterina
hal.structure.identifierLaboratoire sciences et technologies de l'information géographique [LaSTIG]
dc.contributor.authorLANDRIEU, Loic
hal.structure.identifierLaboratoire sciences et technologies de l'information géographique [LaSTIG]
dc.contributor.authorMALLET, Clément
hal.structure.identifierLaboratoire sciences et technologies de l'information géographique [LaSTIG]
hal.structure.identifierInstitut Polytechnique de Bordeaux [Bordeaux INP]
dc.contributor.authorCHEHATA, Nesrine
dc.date.issued2022-08
dc.identifier.issn1569-8432
dc.description.abstractEnWe propose a new deep learning-based method for estimating the occupancy of vegetation strata from airborne 3D LiDAR point clouds. Our model predicts rasterized occupancy maps for three vegetation strata corresponding to lower, medium, and higher cover. Our weakly-supervised training scheme allows our network to only be supervised with vegetation occupancy values aggregated over cylindrical plots containing thousands of points which are typically easier to produce than pixel-wise or point-wise annotations. We propose to employ a deep neural network operating on 3D points, and whose prediction are projected onto rasters representing the different vegetation strata. Our method outperforms handcrafted, regression and deep learning baselines in terms of precision by up to 30%, while simultaneously providing visual and interpretable predictions. We provide an open-source implementation along with a dataset of 199 agricultural plots to train and evaluate weakly supervised occupancy regression algorithms.
dc.language.isoen
dc.publisherElsevier
dc.rights.urihttp://creativecommons.org/licenses/by/
dc.title.enPredicting Vegetation Stratum Occupancy from Airborne LiDAR Data with Deep Learning
dc.typeArticle de revue
dc.identifier.doi10.1016/j.jag.2022.102863
dc.subject.halSciences de l'environnement
dc.subject.halInformatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV]
bordeaux.journalInternational Journal of Applied Earth Observation and Geoinformation
bordeaux.page102863
bordeaux.volume112
bordeaux.peerReviewedoui
hal.identifierhal-03727656
hal.version1
hal.popularnon
hal.audienceInternationale
hal.origin.linkhttps://hal.archives-ouvertes.fr//hal-03727656v1
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=International%20Journal%20of%20Applied%20Earth%20Observation%20and%20Geoinformation&rft.date=2022-08&rft.volume=112&rft.spage=102863&rft.epage=102863&rft.eissn=1569-8432&rft.issn=1569-8432&rft.au=KALINICHEVA,%20Ekaterina&LANDRIEU,%20Loic&MALLET,%20Cl%C3%A9ment&CHEHATA,%20Nesrine&rft.genre=article


Archivos en el ítem

ArchivosTamañoFormatoVer

No hay archivos asociados a este ítem.

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem