Estimating the Threshold of Detection on Tree Crown Defoliation Using Vegetation Indices from UAS Multispectral Imagery

Drones

Kaori Otsu¹  Lluís Brotons¹  Adrián Cardil²  Magda Pla³  Andrea Duane³ 

[1] Centre for Ecological Research and Forestry Applications (CREAF), 08193 Cerdanyola del Vallès, Spain;Department of Crops and Forest Sciences, University of Lleida, Avenida Rovira Roure 191, 25198 Lleida, Spain;InForest JRU (CTFC–CREAF), Carretera de Sant Llorenç de Morunys Km 2, Solsona, 25280 Lleida, Spain;

关键词: unmanned aerial systems (uas);    multispectral imagery;    forest defoliation;    thaumetopoea pityocampa;    vegetation index;    thresholding analysis;   

DOI  :  10.3390/drones3040080

来源: DOAJ

【 摘 要 】

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.

【 授权许可】

Unknown