Combining a Standardized Growth Class Assessment, UAV Sensor Data, GIS Processing, and Machine Learning Classification to Derive a Correlation with the Vigour and Canopy Volume of Grapevines
Sensors · 13.01.2025 · 25 (2) · 431
DOI: 10.3390/s25020431 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 13.01.2025. Verfasst von Ronald P Dillner und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Viticulture and Oenology, DLR (Dienstleistungszentrum Ländlicher Raum) Mosel/Steillagenzentrum, Gartenstraße 18, 54470 Bernkastel-Kues,…. Hauptthemen laut MEDLINE: Vitis, Machine Learning, Geographic Information Systems, Unmanned Aerial Devices. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 147 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: BAV (Bundesmininsterium für Verkehr und Digitale Infrastruktur), German BMDV (Bundesministerium für Digitales und Verkehr).
Abstract (Originalsprache)
Assessing vines’ vigour is essential for vineyard management and automatization of viticulture machines, including shaking adjustments of berry harvesters during grape harvest or leaf pruning applications. To address these problems, based on a standardized growth class assessment, labeled ground truth data of precisely located grapevines were predicted with specifically selected Machine Learning (ML) classifiers (Random Forest Classifier (RFC), Support Vector Machines (SVM)), utilizing multispectral UAV (Unmanned Aerial Vehicle) sensor data. The input features for ML model training comprise spectral, structural, and texture feature types generated from multispectral orthomosaics (spectral features), Digital Terrain and Surface Models (DTM/DSM- structural features), and Gray-Level Co-occurrence Matrix (GLCM) calculations (texture features). The specific features were selected based on extensive literature research, including especially the fields of precision agri- and viticulture. To integrate only vine canopy-exclusive features into ML classifications, different feature types were extracted and spatially aggregated (zonal statistics), based on a combined pixel- and object-based image-segmentation-technique-created vine row mask around each single grapevine position. The extracted canopy features were progressively grouped into seven input feature groups for model training. Model overall performance metrics were optimized with grid search-based hyperparameter tuning and repeated-k-fold-cross-validation. Finally, ML-based growth class prediction results were extensively discussed and evaluated for overall (accuracy, f1-weighted) and growth class specific- classification metrics (accuracy, user- and producer accuracy).
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Viticulture and Oenology, DLR (Dienstleistungszentrum Ländlicher Raum) Mosel/Steillagenzentrum, Gartenstraße 18, 54470 Bernkastel-Kues, Germany.
- Department of Computer Science, University of Koblenz, Universitätsstraße 1, 56070 Koblenz, Germany.
- Department of Environmental Remote Sensing and Geoinformatics, Trier University, Universitätsring 15, 54296 Trier, Germany.
ORCID-Profile: Maria A Wimmer, Rebecca Retzlaff
Förderung
- BAV (Bundesmininsterium für Verkehr und Digitale Infrastruktur)
- German BMDV (Bundesministerium für Digitales und Verkehr)
Zitieren
APA
Dillner, R. P., Wimmer, M. A., Porten, M., Udelhoven, T., & Retzlaff, R. (2025). Combining a Standardized Growth Class Assessment, UAV Sensor Data, GIS Processing, and Machine Learning Classification to Derive a Correlation with the Vigour and Canopy Volume of Grapevines. Sensors, 25(2), 431. https://doi.org/10.3390/s25020431
Vancouver
Dillner RP, Wimmer MA, Porten M, Udelhoven T, Retzlaff R. Combining a Standardized Growth Class Assessment, UAV Sensor Data, GIS Processing, and Machine Learning Classification to Derive a Correlation with the Vigour and Canopy Volume of Grapevines. Sensors. 2025;25(2):431. doi:10.3390/s25020431
BibTeX
@article{Dillner2025,
author = {Dillner, Ronald P and Wimmer, Maria A and Porten, Matthias and Udelhoven, Thomas and Retzlaff, Rebecca},
title = {Combining a Standardized Growth Class Assessment, UAV Sensor Data, GIS Processing, and Machine Learning Classification to Derive a Correlation with the Vigour and Canopy Volume of Grapevines},
journal = {Sensors},
year = {2025},
volume = {25},
number = {2},
pages = {431},
doi = {10.3390/s25020431}
}
EUVIMED