Grapes Ready for Picking: Investigating the Readiness of Precision Viticulture Datasets for Scene Reconstruction
Sensors · 23.10.2026 · 26 (21) · 6708
DOI: 10.3390/s26216708 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 23.10.2026. Verfasst von Michał Jan Włodarczyk und 10 weiteren Autor:innen. Beteiligte Einrichtung: Systems Research Institute, Polish Academy of Sciences, 01-447 Warsaw, Poland. Die Arbeit nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Centre for Research and Development, Japan Science and Technology Agency, Dienstleistungszentrum Ländlicher Raum.
Abstract (Originalsprache)
Public datasets of vineyard imagery were collected for detection, segmentation and disease mapping and are now proposed as a source for 3D scene reconstruction. Their documentation rarely states the properties that reconstruction depends on, such as view overlap, parallax and frame spacing, so it is unclear which can be reconstructed. This study measures that for the publicly available vineyard datasets. A structured search identifies eighteen datasets. Ten are characterized under a schema of thirty-six documented and measured properties, and only six contain overlapping views. Every sequence that registers is reconstructed with one fixed pipeline of structure from motion and 3D Gaussian splatting, giving twenty-seven reconstructions on two held-out splits. Registration is decided by the capture rather than by the dataset; novel-view quality varies as much within a dataset as between datasets; and frame spacing is the one capture property that limits reconstruction. Three preprocessing steps are tested as ablations on the failure cases. Band alignment restores registration, whereas dehazing a backlit pass and masking the chassis of a ground robot give no improvement that this study can resolve. The schema and pipeline apply to any vineyard dataset, and the results are published as an open online catalog.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Systems Research Institute, Polish Academy of Sciences, 01-447 Warsaw, Poland.
- Smart Farming Lab, Leipzig University, Grimmaische Straße 12, 04109 Leipzig, Germany.
- JSK Robotics Laboratory, University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan.
ORCID-Profile: Michał Jan Włodarczyk, Katarzyna Wasielewska-Michniewska, Przemysław Hołda, Maria Ganzha, Marcin Paprzycki, Nico Heider, Martin Schieck, Bogdan Franczyk, Tasuku Makabe, Iori Yanokura, Kei Okada
Förderung
- National Centre for Research and Development
- Japan Science and Technology Agency
- Dienstleistungszentrum Ländlicher Raum
- DRAGONS: Drones for Remote Autonomous Gathering of Plant Samples
- Polish high-performance computing infrastructure PLGrid
Zitieren
APA
Włodarczyk, M. J., Wasielewska-Michniewska, K., Hołda, P., Ganzha, M., Paprzycki, M., Heider, N., Schieck, M., Franczyk, B., Makabe, T., Yanokura, I., & Okada, K. (2026). Grapes Ready for Picking: Investigating the Readiness of Precision Viticulture Datasets for Scene Reconstruction. Sensors, 26(21), 6708. https://doi.org/10.3390/s26216708
Vancouver
Włodarczyk MJ, Wasielewska-Michniewska K, Hołda P, Ganzha M, Paprzycki M, Heider N, et al. Grapes Ready for Picking: Investigating the Readiness of Precision Viticulture Datasets for Scene Reconstruction. Sensors. 2026;26(21):6708. doi:10.3390/s26216708
BibTeX
@article{Wodarczyk2026,
author = {Włodarczyk, Michał Jan and Wasielewska-Michniewska, Katarzyna and Hołda, Przemysław and Ganzha, Maria and Paprzycki, Marcin and Heider, Nico and Schieck, Martin and Franczyk, Bogdan and Makabe, Tasuku and Yanokura, Iori and Okada, Kei},
title = {Grapes Ready for Picking: Investigating the Readiness of Precision Viticulture Datasets for Scene Reconstruction},
journal = {Sensors},
year = {2026},
volume = {26},
number = {21},
pages = {6708},
doi = {10.3390/s26216708}
}
EUVIMED