Aim of study: The study aims to analyse the potential use of lowcost unmanned aerial vehicle (UAV) imagery for the estimation of Pinus pinea L. variables at the individual tree level (position, tree height and crown diameter).Area of study: This study was conducted under the PINEA project focused on 16 ha of umbrella pine afforestation (Portugal) subjected to different treatments.Material and methods: The workflow involved: a) image acquisition with consumer-grade cameras on board an UAV; b) orthomosaic and digital surface model (DSM) generation using structure-from-motion (SfM) image reconstruction; and c) automatic individual tree segmentation by using a mixed pixel-and region-based algorithm.Main results: The results of individual tree segmentation (position, height and crown diameter) were validated using field measurements from 3 inventory plots in the study area. All the trees of the plots were correctly detected. The RMSE values for the predicted heights and crown widths were 0.45 m and 0.63 m, respectively.Research highlights: The results demonstrate that tree variables can be automatically extracted from high resolution imagery. We highlight the use of UAV as a fast, reliable and cost-effective technique for small scale applications.

Eucalyptus Longhorned Borers (ELB) are some of the most destructive pests in regions with Mediterranean climate. Low rainfall and extended dry summers cause stress in eucalyptus trees and facilitate ELB infestation. Due to the difficulty of monitoring the stands by traditional methods, remote sensing arises as an invaluable tool. The main goal of this study was to demonstrate the accuracy of unmanned aerial vehicle (UAV) multispectral imagery for detection and quantification of ELB damages in eucalyptus stands. To detect spatial damage, Otsu thresholding analysis was conducted with five imagery-derived vegetation indices (VIs) and classification accuracy was assessed. Treetops were calculated using the local maxima filter of a sliding window algorithm. Subsequently, large-scale mean-shift segmentation was performed to extract the crowns, and these were classified with random forest (RF). Forest density maps were produced with data obtained from RF classification. The normalized difference vegetation index (NDVI) presented the highest overall accuracy at 98.2% and 0.96 Kappa value. Random forest classification resulted in 98.5% accuracy and 0.94 Kappa value. The Otsu thresholding and random forest classification can be used by forest managers to assess the infestation. The aggregation of data offered by forest density maps can be a simple tool for supporting pest management.