Remote sensing detection algorithm for apple fire blight based on UAV multispectral image

Abstract

Apple fire blight is a common disease that seriously damages the growth of apple trees. It is urgent to detect the severity difference and spatial distribution of its infection in time and accurately. In this study, we used the DJI Matrice 200 multi-rotor UAV equipped with the MicaSense RedEdge-M multispectral camera to obtain the multispectral images of apple tree canopies. Then, based on the Minimum Redundancy Maximum Relevance (mRMR) algorithm, we selected the Ratio Vegetation Index (RVI), Anthocyanin Reflectance Index (ARI) and Triangular Vegetation Index (TVI) from 20 candidate vegetation indices as the optimal feature combinations. And then we use the isolation forest (iForest) algorithm to detect the abnormal values. The samples with the abnormal values removed were used as input to construct apple fire blight detection models using decision trees, Random Forest (RF) and Support Vector Machine (SVM) classification algorithms, respectively. The results show that the overall accuracy of the RF model reaches 94.0%, which is 6.0% and 10.0% higher than the SVM model and the decision tree model, respectively. The Kappa coefficient of the RF model is 0.904, which is the highest among all models, and the omission error and commission error are also the smallest. For healthy samples, slightly infected samples and seriously infected samples, the omission error and commission error were 0, 7.69%, 13.34%, 7.14% and 9.09%, 0, respectively. The research results prove the feasibility of UAV multi-spectral remote sensing images to detect apple fire blight.