In ecological research, a key interest is to explore movement patterns of individual\norganisms across different spatial scales as one driver of biotic interactions. While various methods\nexist to detect and record the presence and movements of individuals in combination with UAS,\naddressing these for smaller animals, such as insects, is challenging and often fails to reveal\ninformation on potential interactions. Here, we address this gap by combining the UAS-based\ndetection of small tracers of fluorescent dyes by means of a simple experiment under field conditions\nfor the first time. We (1) excited fluorescent tracers utilizing an UV radiation source and recorded\nimages with an UAS, (2) conducted a semi-automated selection of training and test samples to\n(3) train a simple SVM classifier, allowing (4) the classification of the recorded images and (5) the\nautomated identification of individual traces. The tracer detection success significantly decreased\nwith increasing altitude, increasing distance from the UV radiation signal center, and decreasing\nsize of the fluorescent traces, including significant interactions amongst these factors. As a first\nproof-of-principle, our approach has the potential to be broadly applicable in ecological research,\nparticularly in insect monitoring.
Loading....