Synthetic data generation methods for training neural networks in the task of segmenting the level of crop nitrogen status on UAV images of agricultural fields

Abstract

This study is devoted to the automatization of the image masks’ construction of large sized agricultural objects in precision farming tasks for training neural network methods for crop’s nitrogen status analysis using georeferenced images. The scientific direction is extremely relevant because it allows to automate and replace the manual process of data labeling, significantly reducing the cost of preparing training samples. In the paper, four new synthetic data generation methods are proposed for training neural networks aimed at UAV image segmentation by the level of crop nitrogen supply on an agricultural field. In particular, the paper gives a description of synthetic data generation algorithms based on nitrogen covering with lines, parabolas, and areas. Experiments were carried out to test and evaluate the quality of these algorithms using eight modern image segmentation methods: two classical machine learning methods (Random Forest and XGBoost), four convolutional neural network methods based on U-Net architecture, and two transformers (TransUnet and UnetR). The results showed that two algorithms based on areas gave the best accuracy for convolutional neural networks and transformers — 98–100 %. Classical machine learning methods showed very low values for all quality metrics — 27–44 %.