Saved in:
Bibliographic Details
Main Authors: Cox, Jonathan, Heselden, James Richard, de Silva, Rajitha, Hanheide, Marc, Polvara, Riccardo
Format: Recurso digital
Language:
Published: Zenodo 2026
Online Access:https://doi.org/10.5281/zenodo.19234907
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • <p>RGB images taken from a UAV of the Riseholme vineyard in Lincoln, UK, collected across three seasons: August 2024, March 2025, and July 2025. Images are annotated in COCO Segmentation format with four instance classes: <code>pole</code>, <code>trunk</code>, <code>vine_row</code>, and <code>vineyard</code> (canopy).</p> <p>The dataset comprises three temporal subsets, each provided with train / validation / test splits:</p> <div> <div> <table> <thead> <tr> <th>Subset</th> <th>Images</th> <th>Annotations</th> </tr> </thead> <tbody> <tr> <td>Riseholme August 2024 (full resolution)</td> <td>285</td> <td>11,285</td> </tr> <tr> <td>Riseholme March 2025 (full resolution)</td> <td>287</td> <td>18,199</td> </tr> <tr> <td>Riseholme July 2025 (full resolution)</td> <td>283</td> <td>10,731</td> </tr> <tr> <td><strong>Total</strong></td> <td><strong>855</strong></td> <td><strong>40,215</strong></td> </tr> </tbody> </table> </div> <div> <div> </div> </div> <div> <div> </div> </div> </div> <p>Images were auto-oriented (EXIF stripping applied) with no augmentation. The dataset was used to train and evaluate YOLOv11 instance segmentation models for vineyard structure detection, supporting an integrated aerial-ground system for vineyard mapping and robotic row-level navigation.</p> <p>A related dataset in YOLOv11 format (covering multiple UK vineyards at various altitudes) is available at: <a title="">https://doi.org/10.5281/zenodo.15211733</a></p> <p>If this dataset is helpful, please cite the associated journal paper:<br>[to be filled in once published]</p>