A survey on deep learning in UAV imagery for precision agriculture and wild flora monitoring: Datasets, models and challenges

Machine learning is the state of the art for many recurring tasks in several heterogeneous domains. In the last decade, it has been also widely used in Precision Agriculture (PA) and Wild Flora Monitoring (WFM) to address a set of problems with a big impact on economy, society and academia, heralding a paradigm shift across the industry and academia. Many applications in those fields involve image processing and computer vision stages. Remote sensing devices are very popular choice for image acquisition in this context, and in particular, Unmanned Aerial Vehicles (UAVs) offer a good tradeoff between cost and area coverage. For these reasons, research literature is rich of works that face problems in Precision Agriculture and Wild Flora Monitoring domains with machine learning/computer vision methods applied to UAV imagery. In this work, we review this literature, with a special focus on algorithms, model sizing, dataset characteristics and innovative technical solutions presented in many domain-specific models, providing the reader with an overview of the research trend in recent years.