Unmanned aerial vehicle-based evaluation of pollination performance employing clustering image processing technique

The global decline of pollinator populations is posing a threat to agricultural productivity, increasingly forcing farmers to introduce pollinators to their fields. Selecting suitable pollinator species is critical for effective crop pollination. This study presents an efficient method for early pollination assessment, utilizing unmanned aerial vehicle (UAV) footage for reliable estimation and timely reactions. Twelve oilseed rape ( Brassica napus var. oleracea ) isolation cages with three pollinator treatments were set up, including the control with no pollinators. The trial employed UAV image acquisition, generating high-resolution RGB orthomosaics. A K-means clustering algorithm was implemented to identify oilseed rape flowers, a direct indicator of pollination performance. The percentage of detected oilseed rape flower coverage within each cage was the primary metric for performance assessment. These initial results demonstrated a negative correlation of 0.92 between estimated flower coverage and expert observations, affirming the efficacy of the proposed methodology. By integrating UAVs and clustering image processing, this research contributes to precision agriculture, offering a robust approach for evaluating pollination performance. The findings underscore the potential of advanced technology to support informed decision-making in agricultural practices, addressing the urgent need for sustainable pollination management in the face of declining pollinator populations.