Estimating the Threshold of Detection on Tree Crown Defoliation Using Vegetation Indices from UAS Multispectral Imagery
Loading...
Date
2019
Authors
Otsu, Kaori
Pla, Magda
Duane, Andrea
Cardil Forradellas, Adrián
Brotons, Lluís
Other authors
Impact
Export
Share
Journal Title
Journal ISSN
Volume Title
Abstract
Periodical outbreaks of Thaumetopoea pityocampa feeding on pine needles may pose a threat to
Mediterranean coniferous forests by causing severe tree defoliation, growth reduction, and eventually
mortality. To cost–effectively monitor the temporal and spatial damages in pine–oak mixed stands
using unmanned aerial systems (UASs) for multispectral imagery, we aimed at developing a simple
thresholding classification tool for forest practitioners as an alternative method to complex classifiers
such as Random Forest. The UAS flights were performed during winter 2017–2018 over four study
areas in Catalonia, northeastern Spain. To detect defoliation and further distinguish pine species,
we conducted nested histogram thresholding analyses with four UAS-derived vegetation indices (VIs)
and evaluated classification accuracy. The normalized difference vegetation index (NDVI) and NDVI
red edge performed the best for detecting defoliation with an overall accuracy of 95% in the total
study area. For discriminating pine species, accuracy results of 93–96% were only achievable with
green NDVI in the partial study area, where the Random Forest classification combined for defoliation
and tree species resulted in 91–93%. Finally, we achieved to estimate the average thresholds of VIs for
detecting defoliation over the total area, which may be applicable across similar Mediterranean pine
stands for monitoring regional forest health on a large scale.
Citation
Journal or Serie
Drones, 2019, vol. 3, núm. 4, art. 80