Overcoming field variability: unsupervised domain adaptation for enhanced crop-weed recognition in diverse farmlands
Frontiers in Plant Science · 09.08.2023 · 14
DOI: 10.3389/fpls.2023.1234616 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Plant Science, online erschienen am 09.08.2023. Verfasst von Talha Ilyas und 4 weiteren Autor:innen. Beteiligte Einrichtung: Division of Electronics and Information Engineering, Jeonbuk National University, Jeonju-si, Republic of Korea. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea.
Abstract (Originalsprache)
Recent developments in deep learning-based automatic weeding systems have shown promise for unmanned weed eradication. However, accurately distinguishing between crops and weeds in varying field conditions remains a challenge for these systems, as performance deteriorates when applied to new or different fields due to insignificant changes in low-level statistics and a significant gap between training and test data distributions. In this study, we propose an approach based on unsupervised domain adaptation to improve crop-weed recognition in new, unseen fields. Our system addresses this issue by learning to ignore insignificant changes in low-level statistics that cause a decline in performance when applied to new data. The proposed network includes a segmentation module that produces segmentation maps using labeled (training field) data while also minimizing entropy using unlabeled (test field) data simultaneously, and a discriminator module that maximizes the confusion between extracted features from the training and test farm samples. This module uses adversarial optimization to make the segmentation network invariant to changes in the field environment. We evaluated the proposed approach on four different unseen (test) fields and found consistent improvements in performance. These results suggest that the proposed approach can effectively handle changes in new field environments during real field inference.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Division of Electronics and Information Engineering, Jeonbuk National University, Jeonju-si, Republic of Korea.
- Core Research Institute of Intelligent Robots, Jeonbuk National University, Jeonju-si, Republic of Korea.
- Production Technology Research Division, National Institute of Crop Science, Rural Development Administration, Miryang, Republic of Korea.
- Division of Electronics Engineering, Jeonbuk National University, Jeonju-si, Republic of Korea.
Förderung
- National Research Foundation of Korea
Zitieren
APA
Ilyas, T., Lee, J., Won, O., Jeong, Y., & Kim, H. (2023). Overcoming field variability: unsupervised domain adaptation for enhanced crop-weed recognition in diverse farmlands. Frontiers in Plant Science, 14. https://doi.org/10.3389/fpls.2023.1234616
Vancouver
Ilyas T, Lee J, Won O, Jeong Y, Kim H. Overcoming field variability: unsupervised domain adaptation for enhanced crop-weed recognition in diverse farmlands. Frontiers in Plant Science. 2023;14. doi:10.3389/fpls.2023.1234616
BibTeX
@article{Ilyas2023,
author = {Ilyas, Talha and Lee, Jonghoon and Won, Okjae and Jeong, Yongchae and Kim, Hyongsuk},
title = {Overcoming field variability: unsupervised domain adaptation for enhanced crop-weed recognition in diverse farmlands},
journal = {Frontiers in Plant Science},
year = {2023},
volume = {14},
doi = {10.3389/fpls.2023.1234616}
}
EUVIMED