Unsupervised Generation of Labeled Training Images for Crop-Weed Segmentation in New Fields and on Different Robotic Platforms

Agricultural robots have the potential to improve the efficiency and sustainability of existing agricultural practices. Most autonomous agricultural robots rely on machine vision systems. Such systems, however, often perform worse in new fields or when the robotic platforms change. While we can alleviate the performance degradation by manually labeling more data obtained in the new setup, this procedure is labor and cost-intensive. Therefore, we propose an approach to improve the performance of machine vision systems for new fields and different robotic platforms without additional manual labeling. In an unsupervised manner, our approach can generate images and corresponding labels to train machine vision systems. We use StyleGAN2 to generate images that appear like they are from desired new field or robotic platform. Additionally, we propose a label refinement method to generate labels corresponding to the generated images. We show that our approach can improve the performance of the crop-weed segmentation task in new fields and on different robotic platforms without additional manual labeling.

Automated summary

Agricultural robots have the potential to improve efficiency and sustainability in agriculture. However, machine vision systems used by these robots often perform poorly in new fields or with different robotic platforms. To address this, we propose an approach that can improve the performance without additional manual labeling.