Updating high-resolution image dataset for the automatic classification of phenological stage and identification of racemes in Urochloa spp. hybrids with expanded images and annotations

This dataset is an expanded version of a previously published collection of high-resolution RGB images of Urochloa spp. genotypes, initially designed to facilitate automated classification of phenological stages and raceme identification in forage breeding trials. The original dataset included 2400...

Full description

Bibliographic Details
Main Authors: Arrechea-Castillo, Darwin Alexis, Espitia-Buitrago, Paula, Florian-Vargas, David, Estupinan, Ronald David, Velázquez-Hernández, Riquelmer, Ruiz-Hurtado, Andres Felipe, Hernandez, Luis Miguel, Jauregui, Rosa Noemi, Cardoso, Juan Andres
Format: Journal Article
Language:Inglés
Published: Elsevier 2025
Subjects:
Online Access:https://hdl.handle.net/10568/174759
_version_ 1855525087857344512
author Arrechea-Castillo, Darwin Alexis
Espitia-Buitrago, Paula
Florian-Vargas, David
Estupinan, Ronald David
Velázquez-Hernández, Riquelmer
Ruiz-Hurtado, Andres Felipe
Hernandez, Luis Miguel
Jauregui, Rosa Noemi
Cardoso, Juan Andres
author_browse Arrechea-Castillo, Darwin Alexis
Cardoso, Juan Andres
Espitia-Buitrago, Paula
Estupinan, Ronald David
Florian-Vargas, David
Hernandez, Luis Miguel
Jauregui, Rosa Noemi
Ruiz-Hurtado, Andres Felipe
Velázquez-Hernández, Riquelmer
author_facet Arrechea-Castillo, Darwin Alexis
Espitia-Buitrago, Paula
Florian-Vargas, David
Estupinan, Ronald David
Velázquez-Hernández, Riquelmer
Ruiz-Hurtado, Andres Felipe
Hernandez, Luis Miguel
Jauregui, Rosa Noemi
Cardoso, Juan Andres
author_sort Arrechea-Castillo, Darwin Alexis
collection Repository of Agricultural Research Outputs (CGSpace)
description This dataset is an expanded version of a previously published collection of high-resolution RGB images of Urochloa spp. genotypes, initially designed to facilitate automated classification of phenological stages and raceme identification in forage breeding trials. The original dataset included 2400 images of 200 genotypes captured under controlled conditions, supporting the development of computer vision models for High-Throughput Phenotyping (HTP). In this updated release, 139 additional images and 24,983 new annotations have been added, bringing the dataset to a total of 2539 images and 47,323 raceme annotations. This version introduces increased diversity in image-capture conditions, with data collected from two geographic locations (Palmira, Colombia, and Ocozocoautla de Espinosa, Mexico) and a range of image-capture devices, including smartphones (e.g. Realme C53 and Oppo Reno 11), a Nikon D5600 camera, and a Phantom 4 Pro V2 drone. Images now vary in perspective (nadir, high-angle, and frontal) and capture distance (1–3 meters), enhancing the dataset applicability for robust Deep Learning (DL) models. Compared to the original dataset, raceme density per plant has nearly doubled in some samples, offering higher raceme overlap for advanced instance segmentation tasks. This expanded dataset supports deeper exploration of phenotypic variation in Urochloa spp. and offers greater potential for developing adaptable models in crop phenotyping.
format Journal Article
id CGSpace174759
institution CGIAR Consortium
language Inglés
publishDate 2025
publishDateRange 2025
publishDateSort 2025
publisher Elsevier
publisherStr Elsevier
record_format dspace
spelling CGSpace1747592025-11-11T18:48:49Z Updating high-resolution image dataset for the automatic classification of phenological stage and identification of racemes in Urochloa spp. hybrids with expanded images and annotations Arrechea-Castillo, Darwin Alexis Espitia-Buitrago, Paula Florian-Vargas, David Estupinan, Ronald David Velázquez-Hernández, Riquelmer Ruiz-Hurtado, Andres Felipe Hernandez, Luis Miguel Jauregui, Rosa Noemi Cardoso, Juan Andres machine learning aprendizaje automático artificial intelligence forage inteligencia artificial grasses high-throughput phenotyping urochloa fenotipado de alto rendimiento imagery-computer vision imagen-visión por ordenador forraje datasets This dataset is an expanded version of a previously published collection of high-resolution RGB images of Urochloa spp. genotypes, initially designed to facilitate automated classification of phenological stages and raceme identification in forage breeding trials. The original dataset included 2400 images of 200 genotypes captured under controlled conditions, supporting the development of computer vision models for High-Throughput Phenotyping (HTP). In this updated release, 139 additional images and 24,983 new annotations have been added, bringing the dataset to a total of 2539 images and 47,323 raceme annotations. This version introduces increased diversity in image-capture conditions, with data collected from two geographic locations (Palmira, Colombia, and Ocozocoautla de Espinosa, Mexico) and a range of image-capture devices, including smartphones (e.g. Realme C53 and Oppo Reno 11), a Nikon D5600 camera, and a Phantom 4 Pro V2 drone. Images now vary in perspective (nadir, high-angle, and frontal) and capture distance (1–3 meters), enhancing the dataset applicability for robust Deep Learning (DL) models. Compared to the original dataset, raceme density per plant has nearly doubled in some samples, offering higher raceme overlap for advanced instance segmentation tasks. This expanded dataset supports deeper exploration of phenotypic variation in Urochloa spp. and offers greater potential for developing adaptable models in crop phenotyping. 2025-06 2025-05-21T14:55:09Z 2025-05-21T14:55:09Z Journal Article https://hdl.handle.net/10568/174759 en Open Access application/pdf Elsevier Arrechea-Castillo, D.A.; Espitia-Buitrago, P.; Florian-Vargas, D.; Estupinan, R.D.; Velázquez-Hernández, R.; Ruiz-Hurtado, A.F.; Hernandez, L.M.; Jauregui, R.N.; Cardoso, J.A. (2025) Updating high-resolution image dataset for the automatic classification of phenological stage and identification of racemes in Urochloa spp. hybrids with expanded images and annotations. Data in Brief 60: 111593. ISSN: 2352-3409
spellingShingle machine learning
aprendizaje automático
artificial intelligence
forage
inteligencia artificial
grasses
high-throughput phenotyping
urochloa
fenotipado de alto rendimiento
imagery-computer vision
imagen-visión por ordenador
forraje
datasets
Arrechea-Castillo, Darwin Alexis
Espitia-Buitrago, Paula
Florian-Vargas, David
Estupinan, Ronald David
Velázquez-Hernández, Riquelmer
Ruiz-Hurtado, Andres Felipe
Hernandez, Luis Miguel
Jauregui, Rosa Noemi
Cardoso, Juan Andres
Updating high-resolution image dataset for the automatic classification of phenological stage and identification of racemes in Urochloa spp. hybrids with expanded images and annotations
title Updating high-resolution image dataset for the automatic classification of phenological stage and identification of racemes in Urochloa spp. hybrids with expanded images and annotations
title_full Updating high-resolution image dataset for the automatic classification of phenological stage and identification of racemes in Urochloa spp. hybrids with expanded images and annotations
title_fullStr Updating high-resolution image dataset for the automatic classification of phenological stage and identification of racemes in Urochloa spp. hybrids with expanded images and annotations
title_full_unstemmed Updating high-resolution image dataset for the automatic classification of phenological stage and identification of racemes in Urochloa spp. hybrids with expanded images and annotations
title_short Updating high-resolution image dataset for the automatic classification of phenological stage and identification of racemes in Urochloa spp. hybrids with expanded images and annotations
title_sort updating high resolution image dataset for the automatic classification of phenological stage and identification of racemes in urochloa spp hybrids with expanded images and annotations
topic machine learning
aprendizaje automático
artificial intelligence
forage
inteligencia artificial
grasses
high-throughput phenotyping
urochloa
fenotipado de alto rendimiento
imagery-computer vision
imagen-visión por ordenador
forraje
datasets
url https://hdl.handle.net/10568/174759
work_keys_str_mv AT arrecheacastillodarwinalexis updatinghighresolutionimagedatasetfortheautomaticclassificationofphenologicalstageandidentificationofracemesinurochloaspphybridswithexpandedimagesandannotations
AT espitiabuitragopaula updatinghighresolutionimagedatasetfortheautomaticclassificationofphenologicalstageandidentificationofracemesinurochloaspphybridswithexpandedimagesandannotations
AT florianvargasdavid updatinghighresolutionimagedatasetfortheautomaticclassificationofphenologicalstageandidentificationofracemesinurochloaspphybridswithexpandedimagesandannotations
AT estupinanronalddavid updatinghighresolutionimagedatasetfortheautomaticclassificationofphenologicalstageandidentificationofracemesinurochloaspphybridswithexpandedimagesandannotations
AT velazquezhernandezriquelmer updatinghighresolutionimagedatasetfortheautomaticclassificationofphenologicalstageandidentificationofracemesinurochloaspphybridswithexpandedimagesandannotations
AT ruizhurtadoandresfelipe updatinghighresolutionimagedatasetfortheautomaticclassificationofphenologicalstageandidentificationofracemesinurochloaspphybridswithexpandedimagesandannotations
AT hernandezluismiguel updatinghighresolutionimagedatasetfortheautomaticclassificationofphenologicalstageandidentificationofracemesinurochloaspphybridswithexpandedimagesandannotations
AT jaureguirosanoemi updatinghighresolutionimagedatasetfortheautomaticclassificationofphenologicalstageandidentificationofracemesinurochloaspphybridswithexpandedimagesandannotations
AT cardosojuanandres updatinghighresolutionimagedatasetfortheautomaticclassificationofphenologicalstageandidentificationofracemesinurochloaspphybridswithexpandedimagesandannotations