Dataset: Forage grasses in crop fields from ultra-high spatial resolution UAV-based imagery
This dataset contains orthomosaics and individual Regions of Interest (ROIs) of forage grasses in crop fields from experimental trials of CIAT’s tropical forages breeding program; and annotations in Common Objects in Context (COCO) format derived from that data. The ROIs were manually annotated on U...
| Main Authors: | , , , , |
|---|---|
| Format: | Conjunto de datos |
| Language: | Inglés |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10568/174405 |
| _version_ | 1855530414252228608 |
|---|---|
| author | Cardoso Arango, Juan Andres Jauregui, Rosa Noemi Camelo-Munevar, Rodrigo Andres Ruiz-Hurtado, Andres Felipe Arrechea-Castillo, Darwin Alexis |
| author_browse | Arrechea-Castillo, Darwin Alexis Camelo-Munevar, Rodrigo Andres Cardoso Arango, Juan Andres Jauregui, Rosa Noemi Ruiz-Hurtado, Andres Felipe |
| author_facet | Cardoso Arango, Juan Andres Jauregui, Rosa Noemi Camelo-Munevar, Rodrigo Andres Ruiz-Hurtado, Andres Felipe Arrechea-Castillo, Darwin Alexis |
| author_sort | Cardoso Arango, Juan Andres |
| collection | Repository of Agricultural Research Outputs (CGSpace) |
| description | This dataset contains orthomosaics and individual Regions of Interest (ROIs) of forage grasses in crop fields from experimental trials of CIAT’s tropical forages breeding program; and annotations in Common Objects in Context (COCO) format derived from that data. The ROIs were manually annotated on UAV imagery and exported in common objects in context (COCO) format compatible with different machine learning models and architectures. 9,554 ROIs in the geospatial data and 12,365 annotations of forage grasses in COCO format.
Methodology: The dataset was generated through a multi-step process beginning with data acquisition of forages crop fields via UAV flights (DJI Phantom 4 Multispectral drone) with RTK determining the geolocation. These images were processed in Agisoft Metashape to generate georeferenced orthomosaics as raster files. Manual annotation of forage grasses ROIs was performed in QGIS and the geospatial data for 8 different orthomosaics was later converted to COCO format using custom python scripting. To ensure compatibility witch COCO standards and optimize training efficiency, the large orthomosaics where clipped to the annotations’ extents with additional 1% spatial buffer and split into tiles with a maximum dimension close to 1024 pixels for the larger side and 25% overlap. |
| format | Conjunto de datos |
| id | CGSpace174405 |
| institution | CGIAR Consortium |
| language | Inglés |
| publishDate | 2025 |
| publishDateRange | 2025 |
| publishDateSort | 2025 |
| record_format | dspace |
| spelling | CGSpace1744052025-05-02T00:59:18Z Dataset: Forage grasses in crop fields from ultra-high spatial resolution UAV-based imagery Cardoso Arango, Juan Andres Jauregui, Rosa Noemi Camelo-Munevar, Rodrigo Andres Ruiz-Hurtado, Andres Felipe Arrechea-Castillo, Darwin Alexis machine learning unmanned aerial vehicles imagery feed crops This dataset contains orthomosaics and individual Regions of Interest (ROIs) of forage grasses in crop fields from experimental trials of CIAT’s tropical forages breeding program; and annotations in Common Objects in Context (COCO) format derived from that data. The ROIs were manually annotated on UAV imagery and exported in common objects in context (COCO) format compatible with different machine learning models and architectures. 9,554 ROIs in the geospatial data and 12,365 annotations of forage grasses in COCO format. Methodology: The dataset was generated through a multi-step process beginning with data acquisition of forages crop fields via UAV flights (DJI Phantom 4 Multispectral drone) with RTK determining the geolocation. These images were processed in Agisoft Metashape to generate georeferenced orthomosaics as raster files. Manual annotation of forage grasses ROIs was performed in QGIS and the geospatial data for 8 different orthomosaics was later converted to COCO format using custom python scripting. To ensure compatibility witch COCO standards and optimize training efficiency, the large orthomosaics where clipped to the annotations’ extents with additional 1% spatial buffer and split into tiles with a maximum dimension close to 1024 pixels for the larger side and 25% overlap. 2025 2025-05-02T00:58:46Z 2025-05-02T00:58:46Z Dataset https://hdl.handle.net/10568/174405 en Open Access Cardoso Arango, J.A.; Jauregui, R.N.; Camelo-Munevar, R.A.; Ruiz-Hurtado, A.F.; Arrechea-Castillo, D.A. (2025) Dataset: Forage grasses in crop fields from ultra-high spatial resolution UAV-based imagery. https://doi.org/10.7910/DVN/DBGUFW |
| spellingShingle | machine learning unmanned aerial vehicles imagery feed crops Cardoso Arango, Juan Andres Jauregui, Rosa Noemi Camelo-Munevar, Rodrigo Andres Ruiz-Hurtado, Andres Felipe Arrechea-Castillo, Darwin Alexis Dataset: Forage grasses in crop fields from ultra-high spatial resolution UAV-based imagery |
| title | Dataset: Forage grasses in crop fields from ultra-high spatial resolution UAV-based imagery |
| title_full | Dataset: Forage grasses in crop fields from ultra-high spatial resolution UAV-based imagery |
| title_fullStr | Dataset: Forage grasses in crop fields from ultra-high spatial resolution UAV-based imagery |
| title_full_unstemmed | Dataset: Forage grasses in crop fields from ultra-high spatial resolution UAV-based imagery |
| title_short | Dataset: Forage grasses in crop fields from ultra-high spatial resolution UAV-based imagery |
| title_sort | dataset forage grasses in crop fields from ultra high spatial resolution uav based imagery |
| topic | machine learning unmanned aerial vehicles imagery feed crops |
| url | https://hdl.handle.net/10568/174405 |
| work_keys_str_mv | AT cardosoarangojuanandres datasetforagegrassesincropfieldsfromultrahighspatialresolutionuavbasedimagery AT jaureguirosanoemi datasetforagegrassesincropfieldsfromultrahighspatialresolutionuavbasedimagery AT camelomunevarrodrigoandres datasetforagegrassesincropfieldsfromultrahighspatialresolutionuavbasedimagery AT ruizhurtadoandresfelipe datasetforagegrassesincropfieldsfromultrahighspatialresolutionuavbasedimagery AT arrecheacastillodarwinalexis datasetforagegrassesincropfieldsfromultrahighspatialresolutionuavbasedimagery |