Vol.:(0123456789) Precision Agriculture https://doi.org/10.1007/s11119-020-09716-4 1 3 Biophysical parameters of cofee crop estimated by UAV RGB images Luana Mendes dos Santos 1  · Gabriel Araújo e Silva Ferraz 1  · Brenon Diennevan de Souza Barbosa 1  · Adriano Valentim Diotto 2  · Diogo Tubertini Maciel 1  · Letícia Aparecida Gonçalves Xavier 1 © Springer Science+Business Media, LLC, part of Springer Nature 2020 Abstract The advance of digital agriculture combined with computational tools and Unmanned Aer- ial Vehicles (UAVs) has enabled the collection of data for reliably extracting vegetation indices and biophysical parameters derived from the Structure from Motion (SfM) algo- rithm. This work aimed to evaluate the accuracy of the photogrammetry technique using an SfM point cloud for the estimation of the height (h) and crown diameter (d) of cofee trees from aerial images obtained by UAV with an RGB (Red, Green, Blue) camera and compared the results with data measured in situ for 12 months. The experiment was carried out in a cofee plantation, Lavras, Minas Gerais, Brazil. A rotary-wing UAV was used in autonomous fight mode and coupled to a conventional camera, fying at a height of 30 m with an image overlap of 80% and a speed of 3 m/s. The images were processed using PhotoScan software, and the analyses were performed in Qgis. A correlation of 87% was obtained between the h values in the feld and h values obtained by the UAV, and there was a 95% correlation between the d values obtained in the feld and the values obtained by the UAV. It was possible to obtain signifcant estimates of the attributes, such as the h and d of cofee trees, using UAV–SfM images acquired with an RGB digital camera. Keywords Remote sensing · Tree height · Unmanned aircraft system · Structure from motion · Aerial survey Introduction The global cofee production for the 2019/2020 harvest is estimated at 10.2 million tonnes (169.3 million bags). Brazil has a signifcant share of this production, occupying the top position with a 34.2% share of the cofee production worldwide (USDA 2020). It is the * Luana Mendes dos Santos luanna_mendess@yahoo.com.br 1 Agricultural Engineering Department, Federal University of Lavras, P.O BOX 3037, Lavras, MG CEP 37200-000, Brazil 2 Department of Water Resources and Sanitation, Federal University of Lavras, P.O BOX 3037, Lavras, MG CEP 37200-000, Brazil