Automatic detection of xylella fastidiosa in aerial hyperspectral and thermal data

Xylella fastidiosa (Xf) is a plant pathogen affecting olives trees, which has been identified as the bacterium responsible of a devastating landscape transformation in Apulia Region (Italy) from 2013. Actually, it has been found to affect 679 plant species worldwide, such as almond, vine and citrus. In this paper, experimental results concerning the automatic detection of trees infected by Xf from very high resolution hyperspectral and thermal images are shown. First of all, a set of vegetation indices and plant physiological traits related to rapid changes in photosynthetic pigments and leaf processes were computed from hyperspectral data. This information together with thermal data has been used as input to a RUSBoost classifier. Trees in training and test data set were labelled by performing quantitative real timePolymerase-Chain-Reaction (qPCR) assays. Encouraging experimental results have been obtained, with Overall Accuracies greater than 90%, also when a reduced set of features is used as input for RUSBoost.