Using UAV images for semiautomatic detection of row-gaps in vineyards in Jelenec and Topoľčianky (Slovakia)

Abstract

The use of UAV (Unmanned Aerial Vehicles) in precision viticulture leads to a more flexible and efficient approach to vineyard management. Images from UAV help determine the condition of the vineyard. Identification of the missing roots of the vineyard in a row by semi-automatic image classification and its comparison with manual classification is a goal of the paper. This study presents a new methodology for the segmentation of vine and row gaps. RGB (Red-Green-Blue) images, multispectral images, Near-Infrared (NIR) images, and Normalized Differential Vegetation Index (NDVI) images were tested and compared with manual classification. The percentage of row gap and the accuracy of individual images were determined. Object-oriented classification of the vine and row gaps in the buffer zone of the vineyard is a core of our method. Using geostatistical methods, such as zonal and logistic regression statistics, the accuracy of individual data in buffer zones was evaluated. Areas of interest were parts of vineyards in Jelenec and Topoľčianky. Success of the method detectomg outage (compared to manual classification) was achieved by images in the RGB spectrum: 96.45% for the Jelenec vineyard and 82.61% for the Topoľčianky vineyard. By this method, we quickly determine row gaps/vine which can be used to optimize or reduce the application of fertilizers to be used only on the vine. The method can be also used by inspection authorities to reveal the actual condition of the vineyard.