Machine learning methods for precision agriculture with UAV imagery: a review

Abstract

Because of the recent development in advanced sensors, data acquisition platforms, and data analysis methods, unmanned aerial vehicle (UAV) or drone-based remote sensing has gained significant attention from precision agriculture (PA) researchers. The massive amount of raw data collected from such sensing platforms demands large-scale data processing algorithms such as machine learning and deep learning methods. Therefore, it is timely to provide a detailed survey that assimilates, categorises, and compares the performance of various machine learning and deep learning methods for PA. This paper summarises and synthesises the recent works using a general pipeline of UAV-based remote sensing for precision agriculture research. We classify the different features extracted from UAV imagery for various agriculture applications, showing the importance of each feature for the performance of the crop model and demonstrating how the multiple feature fusion can improve the models’ performance. In addition, we compare and contrast the performances of various machine learning and deep learning models for three important crop trait estimations: yield estimation, disease detection and crop classification. Furthermore, the recent trends in applications of UAVs for PA are briefly discussed in terms of their importance, and opportunities. Finally, we recite the potential challenges and suggest future avenues of research in this field