Autonomous Detection of Mouse-Ear Hawkweed Using Drones, Multispectral Imagery and Supervised Machine Learning
-
Published:2023-03-17
Issue:6
Volume:15
Page:1633
-
ISSN:2072-4292
-
Container-title:Remote Sensing
-
language:en
-
Short-container-title:Remote Sensing
Author:
Amarasingam Narmilan123ORCID, Hamilton Mark4, Kelly Jane E.5, Zheng Lihong5ORCID, Sandino Juan2ORCID, Gonzalez Felipe12ORCID, Dehaan Remy L.5, Cherry Hillary4
Affiliation:
1. School of Electrical Engineering and Robotics, Faculty of Engineering, Queensland University of Technology (QUT), 2 George Street, Brisbane City, QLD 4000, Australia 2. QUT Centre for Robotics, Queensland University of Technology, 2 George Street, Brisbane City, QLD 4000, Australia 3. Department of Biosystems Technology, Faculty of Technology, South Eastern University of Sri Lanka, University Park, Oluvil 32360, Sri Lanka 4. NSW Department of Planning and Environment, 12 Darcy Street, Parramatta, NSW 2150, Australia 5. Gulbali Institute for Agriculture Water and Environment, Charles Sturt University, Boorooma Street, Wagga Wagga, NSW 2678, Australia
Abstract
Hawkweeds (Pilosella spp.) have become a severe and rapidly invading weed in pasture lands and forest meadows of New Zealand. Detection of hawkweed infestations is essential for eradication and resource management at private and government levels. This study explores the potential of machine learning (ML) algorithms for detecting mouse-ear hawkweed (Pilosella officinarum) foliage and flowers from Unmanned Aerial Vehicle (UAV)-acquired multispectral (MS) images at various spatial resolutions. The performances of different ML algorithms, namely eXtreme Gradient Boosting (XGB), Support Vector Machine (SVM), Random Forest (RF), and K-nearest neighbours (KNN), were analysed in their capacity to detect hawkweed foliage and flowers using MS imagery. The imagery was obtained at numerous spatial resolutions from a highly infested study site located in the McKenzie Region of the South Island of New Zealand in January 2021. The spatial resolution of 0.65 cm/pixel (acquired at a flying height of 15 m above ground level) produced the highest overall testing and validation accuracy of 100% using the RF, KNN, and XGB models for detecting hawkweed flowers. In hawkweed foliage detection at the same resolution, the RF and XGB models achieved highest testing accuracy of 97%, while other models (KNN and SVM) achieved an overall model testing accuracy of 96% and 72%, respectively. The XGB model achieved the highest overall validation accuracy of 98%, while the other models (RF, KNN, and SVM) produced validation accuracies of 97%, 97%, and 80%, respectively. This proposed methodology may facilitate non-invasive detection efforts of mouse-ear hawkweed flowers and foliage in other naturalised areas, enabling land managers to optimise the use of UAV remote sensing technologies for better resource allocation.
Funder
the Australian Department of Agriculture, Fisheries and Forestry
Subject
General Earth and Planetary Sciences
Reference72 articles.
1. Luna, I.M., Fernández-Quintanilla, C., and Dorado, J. (2020). Is Pasture Cropping a Valid Weed Management Tool?. Plants, 9. 2. Cousens, R., Heydel, F., Giljohann, K., Tackenberg, O., Mesgaran, M., and Williams, N. (2012, January 8–11). Predicting the Dispersal of Hawkweeds (Hieracium aurantiacum and H. praealtum) in the Australian Alps. Proceedings of the Eighteenth Australasian Weeds Conference, Melbourne, VIC, Australia. 3. Evaluation of Sentinel-2 time-series for mapping floodplain grassland plant communities;Rapinel;Remote Sens. Environ.,2019 4. Mapping grassland plant communities using a fuzzy approach to address floristic and spectral uncertainty;Rapinel;Appl. Veg. Sci.,2018 5. De Castro, A.I., Torres-Sánchez, J., Peña, J.M., Jiménez-Brenes, F.M., Csillik, O., and López-Granados, F. (2018). An Automatic Random Forest-OBIA Algorithm for Early Weed Mapping between and within Crop Rows Using UAV Imagery. Remote Sens., 10.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|