Early-Season Stand Count Determination in Corn via Integration of Imagery from Unmanned Aerial Systems (UAS) and Supervised Learning Techniques

Autores
Varela, Sebastián; Dhodda, Pruthvidhar Reddy; Hsu, William H.; Vara Prasad, P. V.; Assefa, Yared; Peralta, Nahuel R.; Griffin, Terry; Sharda, Ajay; Ferguson, Allison; Ciampitti, Ignacio A.
Año de publicación
2018
Idioma
inglés
Tipo de recurso
documento de conferencia
Estado
versión publicada
Descripción
Corn (Zea mays L.) is one of the most sensitive crops to planting pattern and early-season uniformity. The most common method to determine number of plants is by visual inspection on the ground but this field activity becomes time-consuming, labor-intensive, biased, and may lead to less profitable decisions by farmers. The objective of this study was to develop a reliable, timely, and unbiased method for counting corn plants based on ultra-high-resolution imagery acquired from unmanned aerial systems (UAS) to automatically scout fields and applied to real field conditions. A ground sampling distance of 2.4 mm was targeted to extract information at a plant-level basis. First, an excess greenness (ExG) index was used to individualized green pixels from the background, then rows and inter-row contours were identified and extracted. A scalable training procedure was implemented using geometric descriptors as inputs of the classifier. Second, a decision tree was implemented and tested using two training modes in each site to expose the workflow to different ground conditions at the time of the aerial data acquisition. Differences in performance were due to training modes and spatial resolutions in the two sites. For an object classification task, an overall accuracy of 0.96, based on the proportion of corrected assessment of corn and non-corn objects, was obtained for local (per-site) classification, and an accuracy of 0.93 was obtained for the combined training modes. For successful model implementation, plants should have between two to three leaves when images are collected (avoiding overlapping between plants). Best workflow performance was reached at 2.4 mm resolution corresponding to 10 m of altitude (lower altitude); higher altitudes were gradually penalized. The latter was coincident with the larger number of detected green objects in the images and the effectiveness of geometry as descriptor for corn plant detection.
Sociedad Argentina de Informática e Investigación Operativa
Materia
Ciencias Informáticas
unmanned aerial system
supervised learning
corn
farm management
precision agriculture
Nivel de accesibilidad
acceso abierto
Condiciones de uso
http://creativecommons.org/licenses/by-sa/3.0/
Repositorio
SEDICI (UNLP)
Institución
Universidad Nacional de La Plata
OAI Identificador
oai:sedici.unlp.edu.ar:10915/70990

id SEDICI_ad20946431d42fdc27e0a895ba7f2b42
oai_identifier_str oai:sedici.unlp.edu.ar:10915/70990
network_acronym_str SEDICI
repository_id_str 1329
network_name_str SEDICI (UNLP)
spelling Early-Season Stand Count Determination in Corn via Integration of Imagery from Unmanned Aerial Systems (UAS) and Supervised Learning TechniquesVarela, SebastiánDhodda, Pruthvidhar ReddyHsu, William H.Vara Prasad, P. V.Assefa, YaredPeralta, Nahuel R.Griffin, TerrySharda, AjayFerguson, AllisonCiampitti, Ignacio A.Ciencias Informáticasunmanned aerial systemsupervised learningcornfarm managementprecision agricultureCorn (Zea mays L.) is one of the most sensitive crops to planting pattern and early-season uniformity. The most common method to determine number of plants is by visual inspection on the ground but this field activity becomes time-consuming, labor-intensive, biased, and may lead to less profitable decisions by farmers. The objective of this study was to develop a reliable, timely, and unbiased method for counting corn plants based on ultra-high-resolution imagery acquired from unmanned aerial systems (UAS) to automatically scout fields and applied to real field conditions. A ground sampling distance of 2.4 mm was targeted to extract information at a plant-level basis. First, an excess greenness (ExG) index was used to individualized green pixels from the background, then rows and inter-row contours were identified and extracted. A scalable training procedure was implemented using geometric descriptors as inputs of the classifier. Second, a decision tree was implemented and tested using two training modes in each site to expose the workflow to different ground conditions at the time of the aerial data acquisition. Differences in performance were due to training modes and spatial resolutions in the two sites. For an object classification task, an overall accuracy of 0.96, based on the proportion of corrected assessment of corn and non-corn objects, was obtained for local (per-site) classification, and an accuracy of 0.93 was obtained for the combined training modes. For successful model implementation, plants should have between two to three leaves when images are collected (avoiding overlapping between plants). Best workflow performance was reached at 2.4 mm resolution corresponding to 10 m of altitude (lower altitude); higher altitudes were gradually penalized. The latter was coincident with the larger number of detected green objects in the images and the effectiveness of geometry as descriptor for corn plant detection.Sociedad Argentina de Informática e Investigación Operativa2018-09info:eu-repo/semantics/conferenceObjectinfo:eu-repo/semantics/publishedVersionResumenhttp://purl.org/coar/resource_type/c_5794info:ar-repo/semantics/documentoDeConferenciaapplication/pdfhttp://sedici.unlp.edu.ar/handle/10915/70990enginfo:eu-repo/semantics/altIdentifier/url/http://47jaiio.sadio.org.ar/sites/default/files/CAI-9.pdfinfo:eu-repo/semantics/altIdentifier/issn/2525-0949info:eu-repo/semantics/reference/doi/10.3390/rs10020343info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-sa/3.0/Creative Commons Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0)reponame:SEDICI (UNLP)instname:Universidad Nacional de La Platainstacron:UNLP2025-09-29T11:11:29Zoai:sedici.unlp.edu.ar:10915/70990Institucionalhttp://sedici.unlp.edu.ar/Universidad públicaNo correspondehttp://sedici.unlp.edu.ar/oai/snrdalira@sedici.unlp.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:13292025-09-29 11:11:29.495SEDICI (UNLP) - Universidad Nacional de La Platafalse
dc.title.none.fl_str_mv Early-Season Stand Count Determination in Corn via Integration of Imagery from Unmanned Aerial Systems (UAS) and Supervised Learning Techniques
title Early-Season Stand Count Determination in Corn via Integration of Imagery from Unmanned Aerial Systems (UAS) and Supervised Learning Techniques
spellingShingle Early-Season Stand Count Determination in Corn via Integration of Imagery from Unmanned Aerial Systems (UAS) and Supervised Learning Techniques
Varela, Sebastián
Ciencias Informáticas
unmanned aerial system
supervised learning
corn
farm management
precision agriculture
title_short Early-Season Stand Count Determination in Corn via Integration of Imagery from Unmanned Aerial Systems (UAS) and Supervised Learning Techniques
title_full Early-Season Stand Count Determination in Corn via Integration of Imagery from Unmanned Aerial Systems (UAS) and Supervised Learning Techniques
title_fullStr Early-Season Stand Count Determination in Corn via Integration of Imagery from Unmanned Aerial Systems (UAS) and Supervised Learning Techniques
title_full_unstemmed Early-Season Stand Count Determination in Corn via Integration of Imagery from Unmanned Aerial Systems (UAS) and Supervised Learning Techniques
title_sort Early-Season Stand Count Determination in Corn via Integration of Imagery from Unmanned Aerial Systems (UAS) and Supervised Learning Techniques
dc.creator.none.fl_str_mv Varela, Sebastián
Dhodda, Pruthvidhar Reddy
Hsu, William H.
Vara Prasad, P. V.
Assefa, Yared
Peralta, Nahuel R.
Griffin, Terry
Sharda, Ajay
Ferguson, Allison
Ciampitti, Ignacio A.
author Varela, Sebastián
author_facet Varela, Sebastián
Dhodda, Pruthvidhar Reddy
Hsu, William H.
Vara Prasad, P. V.
Assefa, Yared
Peralta, Nahuel R.
Griffin, Terry
Sharda, Ajay
Ferguson, Allison
Ciampitti, Ignacio A.
author_role author
author2 Dhodda, Pruthvidhar Reddy
Hsu, William H.
Vara Prasad, P. V.
Assefa, Yared
Peralta, Nahuel R.
Griffin, Terry
Sharda, Ajay
Ferguson, Allison
Ciampitti, Ignacio A.
author2_role author
author
author
author
author
author
author
author
author
dc.subject.none.fl_str_mv Ciencias Informáticas
unmanned aerial system
supervised learning
corn
farm management
precision agriculture
topic Ciencias Informáticas
unmanned aerial system
supervised learning
corn
farm management
precision agriculture
dc.description.none.fl_txt_mv Corn (Zea mays L.) is one of the most sensitive crops to planting pattern and early-season uniformity. The most common method to determine number of plants is by visual inspection on the ground but this field activity becomes time-consuming, labor-intensive, biased, and may lead to less profitable decisions by farmers. The objective of this study was to develop a reliable, timely, and unbiased method for counting corn plants based on ultra-high-resolution imagery acquired from unmanned aerial systems (UAS) to automatically scout fields and applied to real field conditions. A ground sampling distance of 2.4 mm was targeted to extract information at a plant-level basis. First, an excess greenness (ExG) index was used to individualized green pixels from the background, then rows and inter-row contours were identified and extracted. A scalable training procedure was implemented using geometric descriptors as inputs of the classifier. Second, a decision tree was implemented and tested using two training modes in each site to expose the workflow to different ground conditions at the time of the aerial data acquisition. Differences in performance were due to training modes and spatial resolutions in the two sites. For an object classification task, an overall accuracy of 0.96, based on the proportion of corrected assessment of corn and non-corn objects, was obtained for local (per-site) classification, and an accuracy of 0.93 was obtained for the combined training modes. For successful model implementation, plants should have between two to three leaves when images are collected (avoiding overlapping between plants). Best workflow performance was reached at 2.4 mm resolution corresponding to 10 m of altitude (lower altitude); higher altitudes were gradually penalized. The latter was coincident with the larger number of detected green objects in the images and the effectiveness of geometry as descriptor for corn plant detection.
Sociedad Argentina de Informática e Investigación Operativa
description Corn (Zea mays L.) is one of the most sensitive crops to planting pattern and early-season uniformity. The most common method to determine number of plants is by visual inspection on the ground but this field activity becomes time-consuming, labor-intensive, biased, and may lead to less profitable decisions by farmers. The objective of this study was to develop a reliable, timely, and unbiased method for counting corn plants based on ultra-high-resolution imagery acquired from unmanned aerial systems (UAS) to automatically scout fields and applied to real field conditions. A ground sampling distance of 2.4 mm was targeted to extract information at a plant-level basis. First, an excess greenness (ExG) index was used to individualized green pixels from the background, then rows and inter-row contours were identified and extracted. A scalable training procedure was implemented using geometric descriptors as inputs of the classifier. Second, a decision tree was implemented and tested using two training modes in each site to expose the workflow to different ground conditions at the time of the aerial data acquisition. Differences in performance were due to training modes and spatial resolutions in the two sites. For an object classification task, an overall accuracy of 0.96, based on the proportion of corrected assessment of corn and non-corn objects, was obtained for local (per-site) classification, and an accuracy of 0.93 was obtained for the combined training modes. For successful model implementation, plants should have between two to three leaves when images are collected (avoiding overlapping between plants). Best workflow performance was reached at 2.4 mm resolution corresponding to 10 m of altitude (lower altitude); higher altitudes were gradually penalized. The latter was coincident with the larger number of detected green objects in the images and the effectiveness of geometry as descriptor for corn plant detection.
publishDate 2018
dc.date.none.fl_str_mv 2018-09
dc.type.none.fl_str_mv info:eu-repo/semantics/conferenceObject
info:eu-repo/semantics/publishedVersion
Resumen
http://purl.org/coar/resource_type/c_5794
info:ar-repo/semantics/documentoDeConferencia
format conferenceObject
status_str publishedVersion
dc.identifier.none.fl_str_mv http://sedici.unlp.edu.ar/handle/10915/70990
url http://sedici.unlp.edu.ar/handle/10915/70990
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/http://47jaiio.sadio.org.ar/sites/default/files/CAI-9.pdf
info:eu-repo/semantics/altIdentifier/issn/2525-0949
info:eu-repo/semantics/reference/doi/10.3390/rs10020343
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-sa/3.0/
Creative Commons Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0)
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-sa/3.0/
Creative Commons Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0)
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:SEDICI (UNLP)
instname:Universidad Nacional de La Plata
instacron:UNLP
reponame_str SEDICI (UNLP)
collection SEDICI (UNLP)
instname_str Universidad Nacional de La Plata
instacron_str UNLP
institution UNLP
repository.name.fl_str_mv SEDICI (UNLP) - Universidad Nacional de La Plata
repository.mail.fl_str_mv alira@sedici.unlp.edu.ar
_version_ 1844615984328998912
score 13.070432