Few-leaf Learning: Weed Segmentation in Grasslands

Abstract

Autonomous robotic weeding in grasslands requires robust weed segmentation. Deep learning models can provide solutions to this problem, but they need to be trained on large amounts of images, which in the case of grasslands are notoriously difficult to obtain and manually annotate. In this work we introduce Few-leaf Learning, a concept that facilitates the training of accurate weed segmentation models and can lead to easier generation of weed segmentation datasets with minimal human annotation effort. Our approach builds upon the fact that each plant species within the same field has relatively uniform visual characteristics due to similar environmental influences. Thus, we can train a field-and-day-specific weed segmentation model on synthetic training data stemming from just a handful of annotated weed leaves. We demonstrate the efficacy of our approach for different fields and for two common grassland weeds: Rumex obtusifolius (broad-leaved dock) and Cirsium vulgare (spear thistle). Our code is publicly available at https://github.com/RGring/WeedAnnotator.

Artificial Intelligence Tools and Techniques to Combat Herbicide Resistant Weeds—A Review

“…These can include operations such as flipping, cropping, rescaling, translation, rotation, etc. Alternatively, semantic segmentation of weeds, [77] proposes to randomly paste a few weed leaves in background images to generate synthetic training data of weeds in various conditions. Image patches can be sampled from multiple images and combined to generate additional training data [78].…”

Real-Time Joint-Stem Prediction for Agricultural Robots in Grasslands Using Multi-Task Learning

“…Weed detection has been widely investigated in the past decade and it has been posed as a classification problem [1][2][3][4][5][6], detection problem via bounding boxes [7][8][9][10][11], as well as segmentation problem [12][13][14][15][16]. The object detection architecture YOLO has evolved greatly over the last decade resulting in different popular variants, such as YOLOv5 [17], YOLOX [18], and YOLOv8 [19], which have been widely applied to the agricultural domain [11,[20][21][22][23].…”

RumexWeeds: A grassland dataset for agricultural robotics

“…The automated detection of R. obtusifolius L. (broad‐leaved dock) has been investigated in agricultural robotics from the early 2000s up until today (Ahmed et al, 2014; Anken et al, 2010; Binch et al, 2018; Binch & Fox, 2017; Dürr et al, 2008; Güldenring et al, 2021; Güldenring and Nalpantidis, 2021; Kounalakis et al, 2016, 2018, 2019; Lam et al, 2021; Pire et al, 2019; Schori et al, 2019; Seatovic & Winterthur, 2008; Valente et al, 2019; van Evert et al, 2009; Zhang et al, 2018). This underlines the application's relevance and the need for controlling Rumex efficiently and robustly at dairy farms.…”