TY - GEN
T1 - A Machine Learning Approach to Detect Dead Trees Caused by Longhorned Borer in Eucalyptus Stands Using UAV Imagery
AU - Duarte, André
AU - Borralho, Nuno
AU - Caetano, Mário
N1 - info:eu-repo/grantAgreement/EC/H2020/776045/EU#
Duarte, A., Borralho, N., & Caetano, M. (2021). A Machine Learning Approach to Detect Dead Trees Caused by Longhorned Borer in Eucalyptus Stands Using UAV Imagery. In IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium: Proceedings, 12 – 16 July, 2021 Virtual Symposium, Brussels, Belgium (pp. 5818-5821). IEEE. https://doi.org/10.1109/IGARSS47720.2021.9554947 -----------------
Funding Information:
We would like to thank Terradrone and all colleagues of the RAIZ team. The presented work was also carried out with a research project financed by the MySustainableForest project, which has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 776045.
Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - Pest damages in eucalyptus plantations cause significant economic losses for the pulp and paper industry. Longhorned borers (ELB) outbreaks induce mortality in eucalyptus stands. In this study, multispectral imagery was obtained from unmanned aerial vehicles. We attempt to improve the classification process done in previous work. The local maxima of sliding a window and the Large-Scale Mean-Shift segmentation (LSMS) were applied to extract tree crows. Subsequently, the mean of spectral bands and twelve vegetation indices were calculated to characterize each segment. To classify tree canopies into dead and healthy trees, supervised machine learning using Random Forest (RF) and Support Vector Machine (SVM) were applied. The overall accuracy of Random Forests was 98.35% and Support Vector Machine of 97.7%. We concluded that SVM did not perform better than RF. Moreover, adding new vegetation indices in the classification process did not increase accuracy.
AB - Pest damages in eucalyptus plantations cause significant economic losses for the pulp and paper industry. Longhorned borers (ELB) outbreaks induce mortality in eucalyptus stands. In this study, multispectral imagery was obtained from unmanned aerial vehicles. We attempt to improve the classification process done in previous work. The local maxima of sliding a window and the Large-Scale Mean-Shift segmentation (LSMS) were applied to extract tree crows. Subsequently, the mean of spectral bands and twelve vegetation indices were calculated to characterize each segment. To classify tree canopies into dead and healthy trees, supervised machine learning using Random Forest (RF) and Support Vector Machine (SVM) were applied. The overall accuracy of Random Forests was 98.35% and Support Vector Machine of 97.7%. We concluded that SVM did not perform better than RF. Moreover, adding new vegetation indices in the classification process did not increase accuracy.
KW - Eucalyptus stands
KW - Longhorned borer (ELB)
KW - machine learning
KW - unmanned aerial vehicles (UAV)
UR - http://www.scopus.com/inward/record.url?scp=85129825209&partnerID=8YFLogxK
U2 - 10.1109/IGARSS47720.2021.9554947
DO - 10.1109/IGARSS47720.2021.9554947
M3 - Conference contribution
AN - SCOPUS:85129825209
SN - 978-1-6654-0369-6
SP - 5818
EP - 5821
BT - IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium
PB - IEEE
T2 - 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021
Y2 - 12 July 2021 through 16 July 2021
ER -