Recent technical and jurisdictional advances, together with the availability of low-cost platforms, have facilitated the implementation of unmanned aerial vehicles (UAVs) in individual tree detection (ITD) applications. UAV-based photogrammetry or structure from motion is an example of such a low-cost technique, but requires detailed pre-flight planning in order to generate the desired 3D-products needed for ITD. In this study, we aimed to find the most optimal flight parameters (flight altitude and image overlap) and processing options (smoothing window size) for the detection of taxus trees in Belgium. Next, we tested the transferability of the developed marker-controlled segmentation algorithm by applying it to the delineation of olive trees in an orchard in Greece. We found that the processing parameters had a larger effect on the accuracy and precision of ITD than the flight parameters. In particular, a smoothing window of 3 × 3 pixels performed best (F-scores of 0.99) compared to no smoothing (F-scores between 0.88 and 0.90) or a window size of 5 (F-scores between 0.90 and 0.94). Furthermore, the results show that model transferability can still be a bottleneck as it does not capture management induced characteristics such as the typical crown shape of olive trees (F-scores between 0.55 and 0.61).
Tree canopy cover is an important forest inventory parameter and a critical component for the in-depth mapping of forest fuels. This research examines the potential of employing single-date Sentinel-2 multispectral imagery, combined with contextual spatial information, to classify areas based on their tree cover density using Random Forest classifiers. Three spatial information extraction methods are investigated for their capacity to acutely detect canopy cover: two based on Gray-Level Co-Occurrence Matrix (GLCM) features and one based on segment statistics. The research was carried out in three different biomes in Greece, in a total study area of 23,644 km2. Three tree cover classes were considered, namely, non-forest (cover < 15%), open forest (cover = 15%–70%), and closed forest (cover ≥ 70%), based on the requirements set for fuel mapping in Europe. Results indicate that the best approach identified delivers F1-scores ranging 70%–75% for all study areas, significantly improving results over the other alternatives. Overall, the synergistic use of spectral and spatial features derived from Sentinel-2 images highlights a promising approach for the generation of tree cover density information layers in Mediterranean regions, enabling the creation of additional information in support of the detailed mapping of forest fuels.
Wildland fuel distribution and characteristics are critical components for the development of a national integrated wildfire management strategy. This study presents a methodological framework for the mapping of fuels in Mediterranean ecosystems in the different levels of a new fuel hierarchical classification scheme, using a spectral–spatial approach based on Sentinel-2 timeseries and auxiliary thematic maps. Furthermore, in the context of this research, a novel approach is proposed for separating Mediterranean shrubland vegetation into three broad height categories, using Sentinel-2 images, landscape variables, and climatic data. Two areas in Greece, namely Attica and Euboea, with major wildfire events over the past 3 years were selected as the study areas. The mapping methodology was designed to consist of three complementary mapping processes, each for the identification of specific types of fuels (i.e., urban, agricultural, and vegetation). The results are validated in a two-step approach for different levels of the classification scheme. The results for the first level display an overall accuracy of 88% and kappa of 0.84, while for the second level, overall accuracy was 71.64% and kappa was 0.68. Our research demonstrates the capacity to map fuel types with promising accuracy at different depths, highlighting a viable method that can be potentially exploited for the large-scale fuel mapping of Mediterranean biomes at a national level.