Bridging Technology and Ecology: Enhancing Applicability of Deep Learning and UAV-Based Flower Recognition

Marie Schnalke ^1* Jonas Funk ¹ Andreas Wagner ^1,2

• ¹ Karlsruhe University of Applied Sciences, Karlsruhe, Germany
• ² ITWM, Fraunhofer Institute for Industrial Mathematics (FHG), Kaiserslautern, Rhineland-Palatinate, Germany

The decline of insect biomass, including pollinators, represents a significant ecological challenge, impacting both biodiversity and ecosystems. Effective monitoring of pollinator habitats, especially flower resources, is essential for addressing this issue. This study connects drone and deep learning technologies to their practical application in ecological research, providing a practical guide for biologists to apply flower recognition to Unmanned Aerial Vehicle (UAV) imagery. It focuses on simplifying the application of these technologies and facilitating access to multiple object recognition models - Faster Region-based Convolutional Neural Network (Faster R-CNN), Single-Shot-Detector (SSD), and EfficientDet. Updating an object detection toolbox to TensorFlow (TF) 2 enhanced performance and ensured compatibility with newer software packages. The three object detection models were tested on two datasets of UAV images of flower-rich grasslands, to evaluate their application potential in practice. The results showed that Faster R-CNN had the best overall performance with a precision of 89.9\% and a recall of 89\%, followed by EfficientDet, which excelled in recall but at a lower precision. Notably, EfficientDet demonstrated the lowest model complexity, making it a suitable choice for applications requiring a balance between efficiency and detection performance. Challenges remain, such as detecting flowers in dense vegetation and accounting for environmental variability.