Sward species composition estimation is a tedious one. Herbage must be collected in the field, manually separated into components, dried and weighed to estimate species composition. Deep learning approaches using neural networks have been used in previous work to propose faster and more cost efficient alternatives to this process by estimating the biomass information from a picture of an area of pasture alone. Deep learning approaches have, however, struggled to generalize to distant geographical locations and necessitated further data collection to retrain and perform optimally in different climates. In this work, we enhance the deep learning solution by reducing the need for ground-truthed (GT) images when training the neural network. We demonstrate how unsupervised contrastive learning can be used in the sward composition prediction problem and compare with the state-of-the-art on the publicly available GrassClover dataset collected in Denmark as well as a more recent dataset from Ireland where we tackle herbage mass and height estimation.
Item Type:
Conference or Workshop Item (Paper)
Event Type:
Conference
Refereed:
Yes
Uncontrolled Keywords:
biomass prediction; herbage mass prediction; unsupervised learning; clover
Grassland at the heart of circular and sustainable food systems:Proceedings of the 29th General Meeting of the European Grassland Federation.
27.
The Organising Committee of the 29th General Meeting of the European Grassland Federation, INRAE. ISBN 978-2-7380-1445-0
Publisher:
The Organising Committee of the 29th General Meeting of the European Grassland Federation, INRAE
Science Foundation Ireland (SFI) under grant numbers SFI/15/SIRG/3283 and SFI/12/RC/2289P2., Insight SFI Centre for Data Analytics, Vistamilk SFI Centre
ID Code:
27043
Deposited On:
24 Jun 2022 10:51 by
Paul Albert
. Last Modified 10 Jan 2023 15:16