Detection and segmentation of vine canopy in ultra-high spatial resolution RGB imagery obtained from unmanned aerial vehicle (UAV) :a case study in a commercial vineyard

Autores
Poblete Echeverria, Carlos; Olmedo, Guillermo Federico; Ingram, Ben; Bardeen, Matthew
Año de publicación
2017
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
The use of Unmanned Aerial Vehicles (UAVs) in viticulture permits the capture of aerial Red-Green-Blue (RGB) images with an ultra-high spatial resolution. Recent studies have demonstrated that RGB images can be used to monitor spatial variability of vine biophysical parameters. However, for estimating these parameters, accurate and automated segmentation methods are required to extract relevant information from RGB images. Manual segmentation of aerial images is a laborious and time-consuming process. Traditional classification methods have shown satisfactory results in the segmentation of RGB images for diverse applications and surfaces,however, in the case of commercial vineyards, it is necessary to consider some particularities inherent to canopy size in the vertical trellis systems (VSP) such as shadow effect and different soil conditions in inter-rows (mixed information of soil and weeds). Therefore, the objective of this study was to compare the performance of four classification methods (K-means, Artificial Neural Networks (ANN), Random Forest (RForest) and Spectral Indices (SI)) to detect canopy in a vineyard trained on VSP. Six flights were carried out from post-flowering to harvest in a commercial vineyard cv. Carménère using a low-cost UAV equipped with a conventional RGB camera. The results show that the ANN and the simple SI method complemented with the Otsu method for thresholding presented the best performance for the detection of the vine canopy with high overall accuracy values for all study days. Spectral indices presented the best performance in the detection of Plant class (Vine canopy) with an overall accuracy of around 0.99. However, considering the performance pixel by pixel, the Spectral indices are not able to discriminate between Soil and Shadow class. The best performance in the classification of three classes (Plant, Soil, and Shadow) of vineyard RGB images, was obtained when the SI values were used as input data in trained methods (ANN and RForest), reaching overall accuracy values around 0.98 with high sensitivity values for the three classes.
EEA Mendoza
Fil: Poblete Echeverria, Carlos. Pontificia Universidad Católica de Valparaíso. Escuela de Agronomía; Chile. Stellenbosch University. Faculty of AgriSciences. Department of Viticulture and Oenology; Sudáfrica
Fil: Olmedo, Guillermo Federico. Instituto Nacional de Tecnología Agropecuaria (INTA). Estación Experimental Agropecuaria Mendoza; Argentina
Fil: Ingram, Ben. Universidad de Talca. Facultad de Ingeniería; Chile
Fil: Bardeen, Matthew. Universidad de Talca. Facultad de Ingeniería; Chile
Fuente
Remote sensing 9 (3) : 268. (March 2017)
Materia
Agricultura de Precisión
Viticultura
Teledetección
Análisis de Imágenes
Viticulture
Precision Agriculture
Remote Sensing
Image Analysis
Nivel de accesibilidad
acceso abierto
Condiciones de uso
http://creativecommons.org/licenses/by-nc-sa/4.0/
Repositorio
INTA Digital (INTA)
Institución
Instituto Nacional de Tecnología Agropecuaria
OAI Identificador
oai:localhost:20.500.12123/1402

id INTADig_2a5454382d98816b106e86d3ad2bbb65
oai_identifier_str oai:localhost:20.500.12123/1402
network_acronym_str INTADig
repository_id_str l
network_name_str INTA Digital (INTA)
spelling Detection and segmentation of vine canopy in ultra-high spatial resolution RGB imagery obtained from unmanned aerial vehicle (UAV) :a case study in a commercial vineyardPoblete Echeverria, CarlosOlmedo, Guillermo FedericoIngram, BenBardeen, MatthewAgricultura de PrecisiónViticulturaTeledetecciónAnálisis de ImágenesViticulturePrecision AgricultureRemote SensingImage AnalysisThe use of Unmanned Aerial Vehicles (UAVs) in viticulture permits the capture of aerial Red-Green-Blue (RGB) images with an ultra-high spatial resolution. Recent studies have demonstrated that RGB images can be used to monitor spatial variability of vine biophysical parameters. However, for estimating these parameters, accurate and automated segmentation methods are required to extract relevant information from RGB images. Manual segmentation of aerial images is a laborious and time-consuming process. Traditional classification methods have shown satisfactory results in the segmentation of RGB images for diverse applications and surfaces,however, in the case of commercial vineyards, it is necessary to consider some particularities inherent to canopy size in the vertical trellis systems (VSP) such as shadow effect and different soil conditions in inter-rows (mixed information of soil and weeds). Therefore, the objective of this study was to compare the performance of four classification methods (K-means, Artificial Neural Networks (ANN), Random Forest (RForest) and Spectral Indices (SI)) to detect canopy in a vineyard trained on VSP. Six flights were carried out from post-flowering to harvest in a commercial vineyard cv. Carménère using a low-cost UAV equipped with a conventional RGB camera. The results show that the ANN and the simple SI method complemented with the Otsu method for thresholding presented the best performance for the detection of the vine canopy with high overall accuracy values for all study days. Spectral indices presented the best performance in the detection of Plant class (Vine canopy) with an overall accuracy of around 0.99. However, considering the performance pixel by pixel, the Spectral indices are not able to discriminate between Soil and Shadow class. The best performance in the classification of three classes (Plant, Soil, and Shadow) of vineyard RGB images, was obtained when the SI values were used as input data in trained methods (ANN and RForest), reaching overall accuracy values around 0.98 with high sensitivity values for the three classes.EEA MendozaFil: Poblete Echeverria, Carlos. Pontificia Universidad Católica de Valparaíso. Escuela de Agronomía; Chile. Stellenbosch University. Faculty of AgriSciences. Department of Viticulture and Oenology; SudáfricaFil: Olmedo, Guillermo Federico. Instituto Nacional de Tecnología Agropecuaria (INTA). Estación Experimental Agropecuaria Mendoza; ArgentinaFil: Ingram, Ben. Universidad de Talca. Facultad de Ingeniería; ChileFil: Bardeen, Matthew. Universidad de Talca. Facultad de Ingeniería; Chile2017-10-04T13:36:36Z2017-10-04T13:36:36Z2017info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfhttp://hdl.handle.net/20.500.12123/1402http://mdpi.com/2072-4292/9/3/2682072-4292https://doi.org/10.3390/rs9030268Remote sensing 9 (3) : 268. (March 2017)reponame:INTA Digital (INTA)instname:Instituto Nacional de Tecnología Agropecuariaenginfo:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc-sa/4.0/Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)2025-09-29T13:44:12Zoai:localhost:20.500.12123/1402instacron:INTAInstitucionalhttp://repositorio.inta.gob.ar/Organismo científico-tecnológicoNo correspondehttp://repositorio.inta.gob.ar/oai/requesttripaldi.nicolas@inta.gob.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:l2025-09-29 13:44:12.341INTA Digital (INTA) - Instituto Nacional de Tecnología Agropecuariafalse
dc.title.none.fl_str_mv Detection and segmentation of vine canopy in ultra-high spatial resolution RGB imagery obtained from unmanned aerial vehicle (UAV) :a case study in a commercial vineyard
title Detection and segmentation of vine canopy in ultra-high spatial resolution RGB imagery obtained from unmanned aerial vehicle (UAV) :a case study in a commercial vineyard
spellingShingle Detection and segmentation of vine canopy in ultra-high spatial resolution RGB imagery obtained from unmanned aerial vehicle (UAV) :a case study in a commercial vineyard
Poblete Echeverria, Carlos
Agricultura de Precisión
Viticultura
Teledetección
Análisis de Imágenes
Viticulture
Precision Agriculture
Remote Sensing
Image Analysis
title_short Detection and segmentation of vine canopy in ultra-high spatial resolution RGB imagery obtained from unmanned aerial vehicle (UAV) :a case study in a commercial vineyard
title_full Detection and segmentation of vine canopy in ultra-high spatial resolution RGB imagery obtained from unmanned aerial vehicle (UAV) :a case study in a commercial vineyard
title_fullStr Detection and segmentation of vine canopy in ultra-high spatial resolution RGB imagery obtained from unmanned aerial vehicle (UAV) :a case study in a commercial vineyard
title_full_unstemmed Detection and segmentation of vine canopy in ultra-high spatial resolution RGB imagery obtained from unmanned aerial vehicle (UAV) :a case study in a commercial vineyard
title_sort Detection and segmentation of vine canopy in ultra-high spatial resolution RGB imagery obtained from unmanned aerial vehicle (UAV) :a case study in a commercial vineyard
dc.creator.none.fl_str_mv Poblete Echeverria, Carlos
Olmedo, Guillermo Federico
Ingram, Ben
Bardeen, Matthew
author Poblete Echeverria, Carlos
author_facet Poblete Echeverria, Carlos
Olmedo, Guillermo Federico
Ingram, Ben
Bardeen, Matthew
author_role author
author2 Olmedo, Guillermo Federico
Ingram, Ben
Bardeen, Matthew
author2_role author
author
author
dc.subject.none.fl_str_mv Agricultura de Precisión
Viticultura
Teledetección
Análisis de Imágenes
Viticulture
Precision Agriculture
Remote Sensing
Image Analysis
topic Agricultura de Precisión
Viticultura
Teledetección
Análisis de Imágenes
Viticulture
Precision Agriculture
Remote Sensing
Image Analysis
dc.description.none.fl_txt_mv The use of Unmanned Aerial Vehicles (UAVs) in viticulture permits the capture of aerial Red-Green-Blue (RGB) images with an ultra-high spatial resolution. Recent studies have demonstrated that RGB images can be used to monitor spatial variability of vine biophysical parameters. However, for estimating these parameters, accurate and automated segmentation methods are required to extract relevant information from RGB images. Manual segmentation of aerial images is a laborious and time-consuming process. Traditional classification methods have shown satisfactory results in the segmentation of RGB images for diverse applications and surfaces,however, in the case of commercial vineyards, it is necessary to consider some particularities inherent to canopy size in the vertical trellis systems (VSP) such as shadow effect and different soil conditions in inter-rows (mixed information of soil and weeds). Therefore, the objective of this study was to compare the performance of four classification methods (K-means, Artificial Neural Networks (ANN), Random Forest (RForest) and Spectral Indices (SI)) to detect canopy in a vineyard trained on VSP. Six flights were carried out from post-flowering to harvest in a commercial vineyard cv. Carménère using a low-cost UAV equipped with a conventional RGB camera. The results show that the ANN and the simple SI method complemented with the Otsu method for thresholding presented the best performance for the detection of the vine canopy with high overall accuracy values for all study days. Spectral indices presented the best performance in the detection of Plant class (Vine canopy) with an overall accuracy of around 0.99. However, considering the performance pixel by pixel, the Spectral indices are not able to discriminate between Soil and Shadow class. The best performance in the classification of three classes (Plant, Soil, and Shadow) of vineyard RGB images, was obtained when the SI values were used as input data in trained methods (ANN and RForest), reaching overall accuracy values around 0.98 with high sensitivity values for the three classes.
EEA Mendoza
Fil: Poblete Echeverria, Carlos. Pontificia Universidad Católica de Valparaíso. Escuela de Agronomía; Chile. Stellenbosch University. Faculty of AgriSciences. Department of Viticulture and Oenology; Sudáfrica
Fil: Olmedo, Guillermo Federico. Instituto Nacional de Tecnología Agropecuaria (INTA). Estación Experimental Agropecuaria Mendoza; Argentina
Fil: Ingram, Ben. Universidad de Talca. Facultad de Ingeniería; Chile
Fil: Bardeen, Matthew. Universidad de Talca. Facultad de Ingeniería; Chile
description The use of Unmanned Aerial Vehicles (UAVs) in viticulture permits the capture of aerial Red-Green-Blue (RGB) images with an ultra-high spatial resolution. Recent studies have demonstrated that RGB images can be used to monitor spatial variability of vine biophysical parameters. However, for estimating these parameters, accurate and automated segmentation methods are required to extract relevant information from RGB images. Manual segmentation of aerial images is a laborious and time-consuming process. Traditional classification methods have shown satisfactory results in the segmentation of RGB images for diverse applications and surfaces,however, in the case of commercial vineyards, it is necessary to consider some particularities inherent to canopy size in the vertical trellis systems (VSP) such as shadow effect and different soil conditions in inter-rows (mixed information of soil and weeds). Therefore, the objective of this study was to compare the performance of four classification methods (K-means, Artificial Neural Networks (ANN), Random Forest (RForest) and Spectral Indices (SI)) to detect canopy in a vineyard trained on VSP. Six flights were carried out from post-flowering to harvest in a commercial vineyard cv. Carménère using a low-cost UAV equipped with a conventional RGB camera. The results show that the ANN and the simple SI method complemented with the Otsu method for thresholding presented the best performance for the detection of the vine canopy with high overall accuracy values for all study days. Spectral indices presented the best performance in the detection of Plant class (Vine canopy) with an overall accuracy of around 0.99. However, considering the performance pixel by pixel, the Spectral indices are not able to discriminate between Soil and Shadow class. The best performance in the classification of three classes (Plant, Soil, and Shadow) of vineyard RGB images, was obtained when the SI values were used as input data in trained methods (ANN and RForest), reaching overall accuracy values around 0.98 with high sensitivity values for the three classes.
publishDate 2017
dc.date.none.fl_str_mv 2017-10-04T13:36:36Z
2017-10-04T13:36:36Z
2017
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/20.500.12123/1402
http://mdpi.com/2072-4292/9/3/268
2072-4292
https://doi.org/10.3390/rs9030268
url http://hdl.handle.net/20.500.12123/1402
http://mdpi.com/2072-4292/9/3/268
https://doi.org/10.3390/rs9030268
identifier_str_mv 2072-4292
dc.language.none.fl_str_mv eng
language eng
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-nc-sa/4.0/
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc-sa/4.0/
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv Remote sensing 9 (3) : 268. (March 2017)
reponame:INTA Digital (INTA)
instname:Instituto Nacional de Tecnología Agropecuaria
reponame_str INTA Digital (INTA)
collection INTA Digital (INTA)
instname_str Instituto Nacional de Tecnología Agropecuaria
repository.name.fl_str_mv INTA Digital (INTA) - Instituto Nacional de Tecnología Agropecuaria
repository.mail.fl_str_mv tripaldi.nicolas@inta.gob.ar
_version_ 1844619118074920960
score 12.559606