A precision viticulture approach based on pure canopy pixel extraction from high resolution images acquired by a multisensor UAV platform

A. Matese, L. Pastonchi, S.F. Di Gennaro
New remote sensing technologies have provided unprecedented results in vineyard monitoring. In the last decade, Unmanned Aerial Vehicles (UAVs) have been increasingly used for remote sensing purposes in the vineyard, due to high flexibility acquisition, low operational costs and very high spatial resolution. UAVs can be equipped with a wide range of sensors useful for several applications. Numerous assessments were made using several imaging sensors with different flight times. This work describes the development of a multisensor UAV system capable of flying with three sensors simultaneously to perform different monitoring options. The system acquires high resolution images derived from multispectral NRG (NIR, red, green), thermal and RGB (red, green, blue) photographic cameras allowing the extraction of pure vine canopy pixels. This work aimed to evaluate different sources of images and processing methodologies to describe spatial variability of spectral-based and canopy-based vegetation indices within a vineyard and their relationship with production and qualitative vine parameters. A flight campaign was performed during the 2018 season in a Tuscany vineyard. After a row filtering procedure, different indices obtained from the three kinds of images were calculated and correlated to ground measurements. Better correlations were obtained using the pure vine pixels approach compared to the traditional unfiltered mosaic. This UAV multisensor platform equipped with three different sensors simultaneously was demonstrated to be a valuable tool for fast multipurpose monitoring in the vineyard.
Matese, A., Pastonchi, L. and Di Gennaro, S.F. (2021). A precision viticulture approach based on pure canopy pixel extraction from high resolution images acquired by a multisensor UAV platform. Acta Hortic. 1314, 259-268
DOI: 10.17660/ActaHortic.2021.1314.33
https://doi.org/10.17660/ActaHortic.2021.1314.33
multispectral, thermal, RGB imagery, vineyard, grapevine
English

Acta Horticulturae