Automatic Grape Cluster Detection Combining YOLO Model and Remote Sensing Imagery
Precision agriculture has recently experienced significant advancements through the use of technologies such as unmanned aerial vehicles (UAVs) and satellite imagery, enabling more efficient and precise agricultural management. Yield estimation from these technologies is essential for optimizing res...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/2/243 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587561052143616 |
|---|---|
| author | Ana María Codes-Alcaraz Nicola Furnitto Giuseppe Sottosanti Sabina Failla Herminia Puerto Carmen Rocamora-Osorio Pedro Freire-García Juan Miguel Ramírez-Cuesta |
| author_facet | Ana María Codes-Alcaraz Nicola Furnitto Giuseppe Sottosanti Sabina Failla Herminia Puerto Carmen Rocamora-Osorio Pedro Freire-García Juan Miguel Ramírez-Cuesta |
| author_sort | Ana María Codes-Alcaraz |
| collection | DOAJ |
| description | Precision agriculture has recently experienced significant advancements through the use of technologies such as unmanned aerial vehicles (UAVs) and satellite imagery, enabling more efficient and precise agricultural management. Yield estimation from these technologies is essential for optimizing resource allocation, improving harvest logistics, and supporting decision-making for sustainable vineyard management. This study aimed to evaluate grape cluster numbers estimated by using YOLOv7x in combination with images obtained by UAVs from a vineyard. Additionally, the capability of several vegetation indices calculated from Sentinel-2 and PlanetScope satellites to estimate grape clusters was evaluated. The results showed that the application of the YOLOv7x model to RGB images acquired from UAVs was able to accurately predict grape cluster numbers (R<sup>2</sup> value and RMSE value of 0.64 and 0.78 clusters vine<sup>−1</sup>). On the contrary, vegetation indexes derived from Sentinel-2 and PlanetScope satellites were found not able to predict grape cluster numbers (R<sup>2</sup> lower than 0.23), probably due to the fact that these indexes are more related to vegetation vigor, which is not always related to yield parameters (e.g., cluster number). This study suggests that the combination of high-resolution UAV images, multispectral satellite images, and advanced detection models like YOLOv7x can significantly improve the accuracy of vineyard management, resulting in more efficient and sustainable agriculture. |
| format | Article |
| id | doaj-art-3b7c06b002604574a3d0acf99bc77da2 |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-3b7c06b002604574a3d0acf99bc77da22025-01-24T13:47:51ZengMDPI AGRemote Sensing2072-42922025-01-0117224310.3390/rs17020243Automatic Grape Cluster Detection Combining YOLO Model and Remote Sensing ImageryAna María Codes-Alcaraz0Nicola Furnitto1Giuseppe Sottosanti2Sabina Failla3Herminia Puerto4Carmen Rocamora-Osorio5Pedro Freire-García6Juan Miguel Ramírez-Cuesta7Centro de Investigación e Innovación Agroalimentaria y Agroambiental (CIAGRO-UMH), Miguel Hernández University, 03312 Orihuela, SpainDepartment of Agriculture, Food and Environment (Di3A), University of Catania, 95123 Catania, ItalyDepartment of Agriculture, Food and Environment (Di3A), University of Catania, 95123 Catania, ItalyDepartment of Agriculture, Food and Environment (Di3A), University of Catania, 95123 Catania, ItalyCentro de Investigación e Innovación Agroalimentaria y Agroambiental (CIAGRO-UMH), Miguel Hernández University, 03312 Orihuela, SpainCentro de Investigación e Innovación Agroalimentaria y Agroambiental (CIAGRO-UMH), Miguel Hernández University, 03312 Orihuela, SpainCentro de Investigaciones sobre Desertificación (CIDE), CSIC-UV-GVA, Carretera CV 315, km 10.7, 46113 Valencia, SpainDepartment of Agriculture, Food and Environment (Di3A), University of Catania, 95123 Catania, ItalyPrecision agriculture has recently experienced significant advancements through the use of technologies such as unmanned aerial vehicles (UAVs) and satellite imagery, enabling more efficient and precise agricultural management. Yield estimation from these technologies is essential for optimizing resource allocation, improving harvest logistics, and supporting decision-making for sustainable vineyard management. This study aimed to evaluate grape cluster numbers estimated by using YOLOv7x in combination with images obtained by UAVs from a vineyard. Additionally, the capability of several vegetation indices calculated from Sentinel-2 and PlanetScope satellites to estimate grape clusters was evaluated. The results showed that the application of the YOLOv7x model to RGB images acquired from UAVs was able to accurately predict grape cluster numbers (R<sup>2</sup> value and RMSE value of 0.64 and 0.78 clusters vine<sup>−1</sup>). On the contrary, vegetation indexes derived from Sentinel-2 and PlanetScope satellites were found not able to predict grape cluster numbers (R<sup>2</sup> lower than 0.23), probably due to the fact that these indexes are more related to vegetation vigor, which is not always related to yield parameters (e.g., cluster number). This study suggests that the combination of high-resolution UAV images, multispectral satellite images, and advanced detection models like YOLOv7x can significantly improve the accuracy of vineyard management, resulting in more efficient and sustainable agriculture.https://www.mdpi.com/2072-4292/17/2/243object detectionsentinel-2planetscopeunmanned aerial vehicleyield estimation |
| spellingShingle | Ana María Codes-Alcaraz Nicola Furnitto Giuseppe Sottosanti Sabina Failla Herminia Puerto Carmen Rocamora-Osorio Pedro Freire-García Juan Miguel Ramírez-Cuesta Automatic Grape Cluster Detection Combining YOLO Model and Remote Sensing Imagery Remote Sensing object detection sentinel-2 planetscope unmanned aerial vehicle yield estimation |
| title | Automatic Grape Cluster Detection Combining YOLO Model and Remote Sensing Imagery |
| title_full | Automatic Grape Cluster Detection Combining YOLO Model and Remote Sensing Imagery |
| title_fullStr | Automatic Grape Cluster Detection Combining YOLO Model and Remote Sensing Imagery |
| title_full_unstemmed | Automatic Grape Cluster Detection Combining YOLO Model and Remote Sensing Imagery |
| title_short | Automatic Grape Cluster Detection Combining YOLO Model and Remote Sensing Imagery |
| title_sort | automatic grape cluster detection combining yolo model and remote sensing imagery |
| topic | object detection sentinel-2 planetscope unmanned aerial vehicle yield estimation |
| url | https://www.mdpi.com/2072-4292/17/2/243 |
| work_keys_str_mv | AT anamariacodesalcaraz automaticgrapeclusterdetectioncombiningyolomodelandremotesensingimagery AT nicolafurnitto automaticgrapeclusterdetectioncombiningyolomodelandremotesensingimagery AT giuseppesottosanti automaticgrapeclusterdetectioncombiningyolomodelandremotesensingimagery AT sabinafailla automaticgrapeclusterdetectioncombiningyolomodelandremotesensingimagery AT herminiapuerto automaticgrapeclusterdetectioncombiningyolomodelandremotesensingimagery AT carmenrocamoraosorio automaticgrapeclusterdetectioncombiningyolomodelandremotesensingimagery AT pedrofreiregarcia automaticgrapeclusterdetectioncombiningyolomodelandremotesensingimagery AT juanmiguelramirezcuesta automaticgrapeclusterdetectioncombiningyolomodelandremotesensingimagery |