Effects of Foreground Augmentations in Synthetic Training Data on the Use of UAVs for Weed Detection
2024 (English)In: Proceedings of Machine Learning Research / [ed] Lutchyn T., Rivera A.R., Ricaud B., ML Research Press , 2024, Vol. 233Conference paper, Published paper (Refereed)
Abstract [en]
This study addresses the issue of black-grass, a herbicide-resistant weed that threatens wheat yields in Western Europe, through the use of high- resolution Unmanned Aerial Vehicles (UAVs) and synthetic data augmentation in precision agriculture. We mitigate challenges such as the need for large labeled datasets and environmental variability by employing synthetic data augmentations in training a Mask R-CNN model. Using a minimal dataset of 43 black-grass and 12 wheat field images, we achieved a 37% increase in Area Under the Curve (AUC) over the non-augmented baseline, with scaling as the most effective augmentation. The best model attained a recall of 53% at a precision of 64%, offering a promising approach for future precision agriculture applications. © NLDL 2024. All rights reserved.
Place, publisher, year, edition, pages
ML Research Press , 2024. Vol. 233
Series
Proceedings of Machine Learning Research (PMLR), E-ISSN 2640-3498 ; 233
Keywords [en]
Aircraft detection, Antennas, Large datasets, Unmanned aerial vehicles (UAV), Weed control, Aerial vehicle, Data augmentation, Herbicide resistant weeds, High resolution, Precision Agriculture, Synthetic data, Synthetic training data, Weed detection, Western Europe, Wheat yield
National Category
Computer graphics and computer vision Agricultural Science
Identifiers
URN: urn:nbn:se:bth-26100ISI: 001221156400012Scopus ID: 2-s2.0-85189301466OAI: oai:DiVA.org:bth-26100DiVA, id: diva2:1851071
Conference
5th Northern Lights Deep Learning Conference, NLDL 2024, Tromso, 9 January through 11 January 2024
2024-04-122024-04-122025-02-01Bibliographically approved