Enhancing Precision Agriculture: UAV-Based Detection and Management of Giant Hogweed

Abstract

Invasive plant species, such as Heracleum mantegazzianum (Giant Hogweed), pose significant ecological and economic threats worldwide. Traditional detection methods are often limited by seasonal constraints and high costs, hindering timely and effective management. This study proposes an innovative approach to enhance precision agriculture by leveraging Unmanned Aerial Vehicles (UAVs) and deep learning for the early detection and management of Giant Hogweed. We investigate the application of two state-of-the-art deep learning architectures (YOLOv9 and RT-DETR) to analyze high-resolution UAV imagery. The models were trained on an augmented dataset and fine-tuned to optimize performance. Additionally, the integration of the NVIDIA Jetson Orin platform enables real-time detection, facilitating timely interventions for invasive species management. The results demonstrate the potential of combining UAV technology with deep learning for scalable, cost-effective environmental monitoring. This research contributes to advancing precision agriculture and provides a foundation for future innovations in ecological preservation and invasive species control.

Abstract from the paper’s OpenAlex record; open copy licensed cc-by-nc-nd. Read at the source ↗

The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.