Seeing the Green from Above: A Review of Remote Sensing Techniques for Vegetation Cover Discrimination

This review synthesizes recent regional applications of satellite, unmanned aerial vehicle (UAV), and hyperspectral/spectroradiometric remote sensing for vegetation cover discrimination, including crop and natural vegetation discrimination, plant disease and pest detection, and yield assessment. The reviewed evidence demonstrates complementary rather than universally superior capabilities among sensing platforms. Satellite observations provide repeated large-area monitoring but remain constrained by spatial resolution, cloud interference, and spectral mixing, whereas UAVs offer very-high-resolution and flexible field-scale observations at the expense of spatial coverage and greater acquisition and processing requirements. Hyperspectral and spectroradiometric approaches provide detailed spectral information for distinguishing subtle vegetation differences, but are limited by data complexity and operational scalability. The quantitative results reported in the reviewed studies illustrate this variability: satellite-based crop discrimination achieved approximately 90% overall accuracy with QuickBird and 81% overall accuracy (κ = 0.74) with Sentinel-2 at a 10 m resolution, while a UAV hyperspectral vegetation classification study achieved 94.5% accuracy. However, these values are not directly comparable because the vegetation targets, sensors, acquisition conditions, and analytical methods differed among studies. Recent evidence also indicates that the phenological timing, spectral band selection, spatial resolution, and representative training data strongly influence the discrimination performance, while the transfer of disease detection models from controlled experiments to operational field conditions remains a major challenge. By integrating evidence from satellite, UAV, and ground-based spectroradiometric approaches, this review provides a comprehensive framework for understanding the complementary capabilities of these technologies for vegetation cover discrimination and highlights their importance for improving vegetation monitoring, precision agriculture, and sustainable ecosystem management.