EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Classification of Grapevine Varieties Using UAV Hyperspectral Imaging

Alfonso López, Carlos J. Ogayar, Francisco R. Feito, Joaquim J. Sousa

Remote Sensing · 10.06.2024 · 16 (12) · 2103

DOI: 10.3390/rs16122103 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 10.06.2024. Verfasst von Alfonso López und 3 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 80 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Spanish Ministry of Science, Innovation and Universities, University of Trás-os Montes e Alto Douro, MCIN/AEI/10.13039/501100011033/.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Classifying grapevine varieties is crucial in precision viticulture, as it allows for accurate estimation of vineyard row growth for different varieties and ensures authenticity in the wine industry. This task can be performed with time-consuming destructive methods, including data collection and analysis in the laboratory. In contrast, unmanned aerial vehicles (UAVs) offer a markedly more efficient and less restrictive method for gathering hyperspectral data, even though they may yield data with higher levels of noise. Therefore, the first task is the processing of these data to correct and downsample large amounts of data. In addition, the hyperspectral signatures of grape varieties are very similar. In this study, we propose the use of a convolutional neural network (CNN) to classify seventeen different varieties of red and white grape cultivars. Instead of classifying individual samples, our approach involves processing samples alongside their surrounding neighborhood for enhanced accuracy. The extraction of spatial and spectral features is addressed with (1) a spatial attention layer and (2) inception blocks. The pipeline goes from data preparation to dataset elaboration, finishing with the training phase. The fitted model is evaluated in terms of response time, accuracy and data separability and is compared with other state-of-the-art CNNs for classifying hyperspectral data. Our network was proven to be much more lightweight by using a limited number of input bands (40) and a reduced number of trainable weights (560 k parameters). Hence, it reduced training time (1 h on average) over the collected hyperspectral dataset. In contrast, other state-of-the-art research requires large networks with several million parameters that require hours to be trained. Despite this, the evaluated metrics showed much better results for our network (approximately 99% overall accuracy), in comparison with previous works barely achieving 81% OA over UAV imagery. This notable OA was similarly observed over satellite data. These results demonstrate the efficiency and robustness of our proposed method across different hyperspectral data sources.

Förderung

  • Spanish Ministry of Science, Innovation and Universities
  • University of Trás-os Montes e Alto Douro
  • MCIN/AEI/10.13039/501100011033/
  • DATI—Digital Agriculture Technologies for Irrigation Efficiency
  • PRIMA—Partnership for Research and Innovation in the Mediterranean Area (Research and Innovation activities)
  • states participating in the PRIMA partnership
  • European Union through Horizon 2020

Zitieren

APA

López, A., Ogayar, C. J., Feito, F. R., & Sousa, J. J. (2024). Classification of Grapevine Varieties Using UAV Hyperspectral Imaging. Remote Sensing, 16(12), 2103. https://doi.org/10.3390/rs16122103

Vancouver

López A, Ogayar CJ, Feito FR, Sousa JJ. Classification of Grapevine Varieties Using UAV Hyperspectral Imaging. Remote Sensing. 2024;16(12):2103. doi:10.3390/rs16122103

BibTeX
@article{Lpez2024,
  author = {López, Alfonso and Ogayar, Carlos J. and Feito, Francisco R. and Sousa, Joaquim J.},
  title = {Classification of Grapevine Varieties Using UAV Hyperspectral Imaging},
  journal = {Remote Sensing},
  year = {2024},
  volume = {16},
  number = {12},
  pages = {2103},
  doi = {10.3390/rs16122103}
}
Kostenlos starten →