|
View: |
Part 1: Document Description
|
|
Citation |
|
|---|---|
|
Title: |
RGB Image Dataset of Urochloa Hybrids for High-Throughput Phenotyping and Artificial Intelligence Applications |
|
Identification Number: |
doi:10.7910/DVN/X4LM19 |
|
Distributor: |
Harvard Dataverse |
|
Date of Distribution: |
2024-11-13 |
|
Version: |
2 |
|
Bibliographic Citation: |
Arrechea-Castillo, Darwin Alexis; Espitia Buitrago, Paula Andrea; Florian Vargas, David Alberto; Estupinan Arboleda, Ronald David; Velazquez Hernandez, Riquelmer; Camelo Munevar, Rodrigo Andres; Cardoso Arango, Juan Andres, 2024, "RGB Image Dataset of Urochloa Hybrids for High-Throughput Phenotyping and Artificial Intelligence Applications", https://doi.org/10.7910/DVN/X4LM19, Harvard Dataverse, V2 |
|
Citation |
|
|
Title: |
RGB Image Dataset of Urochloa Hybrids for High-Throughput Phenotyping and Artificial Intelligence Applications |
|
Identification Number: |
doi:10.7910/DVN/X4LM19 |
|
Authoring Entity: |
Arrechea-Castillo, Darwin Alexis (International Center for Tropical Agriculture - CIAT) |
|
Espitia Buitrago, Paula Andrea (International Center for Tropical Agriculture - CIAT) |
|
|
Florian Vargas, David Alberto (International Center for Tropical Agriculture - CIAT) |
|
|
Estupinan Arboleda, Ronald David (International Center for Tropical Agriculture - CIAT) |
|
|
Velazquez Hernandez, Riquelmer (International Center for Tropical Agriculture - CIAT) |
|
|
Camelo Munevar, Rodrigo Andres (International Center for Tropical Agriculture - CIAT) |
|
|
Cardoso Arango, Juan Andres (International Center for Tropical Agriculture - CIAT) |
|
|
Other identifications and acknowledgements: |
PAPALOTLA GROUP |
|
Producer: |
Bioversity International and the International Center for Tropical Agriculture |
|
Date of Production: |
2024-03-01 |
|
Distributor: |
Harvard Dataverse |
|
Distributor: |
Bioversity International and the International Center for Tropical Agriculture |
|
Access Authority: |
Alliance Data Management |
|
Depositor: |
Alliance Data Management |
|
Date of Deposit: |
2024-11-08 |
|
Holdings Information: |
https://doi.org/10.7910/DVN/X4LM19 |
|
Study Scope |
|
|
Keywords: |
Agricultural Sciences, Earth and Environmental Sciences, grasses, machine learning, high-throughput phenotyping, imagery, digital image processing, tropical agriculture, Americas, Crops for Nutrition and Health |
|
Topic Classification: |
artificial intelligence, agricultural sciences, agronomy, imagery, machine learning |
|
Abstract: |
This dataset represents an extended version of a previous work, accessible at this link: https://doi.org/10.7910/DVN/U0KL6Y. An additional 139 images and a total of 24,983 new annotations have been included. Combined with the original dataset, a total of 394 images with 47,323 annotations are now available. This new dataset differs from the previous one in several key ways, primarily in the conditions and types of images captured, as well as in the expanded annotations. In the initial release, lighting conditions were carefully controlled to standardize histogram distribution across all images. The images were also captured at a fixed distance and exclusively in a nadir (top-down) view, using a single sensor in a single geographic location. For this updated dataset, variability was prioritized across all aspects. Images were taken in multiple geographic locations, including Palmira, Colombia, and Ocozocoautla de Espinosa, Mexico. Different sensors were used, including a professional Nikon D5600 camera, smartphones (such as the Realme C53 and Oppo Reno 11), and even a Phantom 4 Pro V2 drone. The capture distance varied from 1 to 3 meters, resulting in images with differing spatial resolutions. Additionally, several capture angles were employed: no longer just nadir views but also oblique and frontal angles. Raceme density per plant was also increased. In the original dataset, the plant with the highest raceme count had 851 racemes. In the updated dataset, raceme counts reach as high as 1,586 in a similar area (~1m²), nearly doubling the count. This increase leads to a much higher degree of raceme overlap. This expanded dataset is expected to provide significant benefits for deep learning applications. The enhanced variability supports the development of more robust deep learning models, better suited to handle real-world diversity and complexity. |
|
Time Period: |
2024-03-01-2024-10-26 |
|
Date of Collection: |
2024-03-01-2024-10-26 |
|
Kind of Data: |
Images |
|
Kind of Data: |
Experimental Data |
|
Kind of Data: |
Breeding Data |
|
Methodology and Processing |
|
|
Sources Statement |
|
|
Data Sources: |
Darwin Alexis Arrechea-Castillo, Paula Espitia-Buitrago, Ronald David Arboleda, Luis Miguel Hernandez, Rosa N. Jauregui, Juan Andrés Cardoso, High-resolution image dataset for the automatic classification of phenological stage and identification of racemes in Urochloa spp. hybrids, Data in Brief, Volume 57, 2024, 110928, ISSN 2352-3409, https://doi.org/10.1016/j.dib.2024.110928. |
|
Data Access |
|
|
Disclaimer: |
<p>The Alliance of Bioversity International and CIAT (hereinafter "the Alliance"), its partners, and the data authors have exercised utmost care in collecting and compiling the data. However, the data is provided "as is" without any express or implied warranty. Neither the Alliance, its partners, the data authors, nor any relevant funding agencies shall be held liable for any actual, incidental, or consequential damages arising from the use of this data.</p> <p>By utilizing the Alliance Dataverse, users explicitly acknowledge that the data may contain nonconformities, defects, or errors. No warranty is provided that the data will meet users' needs or expectations, nor that all nonconformities, defects, or errors can or will be corrected.</p> <p>Users are responsible for verifying the accuracy and suitability of the data for their intended use. It is strongly recommended that users refer to related publications as a baseline for their analysis whenever possible. This practice serves as an additional safeguard against misinterpretation of the data. Related publications are listed in the metadata section of the respective Dataverse study.</p> |
|
Other Study Description Materials |
|
|
Related Materials |
|
|
Arrechea-Castillo, D.A., Espitia-Buitrago, P., Arboleda, R.D., Hernandez, L.M., Jauregui, R.N., Cardoso, J.A., 2024. High-resolution image dataset for the automatic classification of phenological stage and identification of racemes in Urochloa spp. hybrids. Data Brief 57, 110928. https://doi.org/10.1016/j.dib.2024.110928 |
|
|
Related Studies |
|
|
Cardoso Arango, Juan Andres; Arrechea-Castillo, Darwin Alexis; Estupinan Arboleda, Ronald David; Escobar Graciano, Miller, 2024, "Top View RGB Image Dataset of Urochloa Hybrids for High-Throughput Phenotyping and Artificial Intelligence Applications", https://doi.org/10.7910/DVN/U0KL6Y, Harvard Dataverse, V2 |
|
|
Other Reference Note(s) |
|
|
Cardoso Arango, Juan Andres; Arrechea-Castillo, Darwin Alexis; Estupinan Arboleda, Ronald David; Escobar Graciano, Miller, 2024, "Top View RGB Image Dataset of Urochloa Hybrids for High-Throughput Phenotyping and Artificial Intelligence Applications", https://doi.org/10.7910/DVN/U0KL6Y, Harvard Dataverse, V2 |
|
|
Label: |
01.ReadMe_RGB_ImageDatasetOfUrochloaHybridsForHTP_and_AI_applications.txt |
|
Text: |
Information |
|
Notes: |
text/plain |
|
Label: |
02.Images.zip |
|
Text: |
Folder with images |
|
Notes: |
application/zip |
|
Label: |
03.RacemesInstances.json |
|
Text: |
JSON file |
|
Notes: |
application/json |