Monitoring of Wheat Fusarium Head Blight on Spectral and Textural Analysis of UAV Multispectral Imagery

Crop disease identification and monitoring is an important research topic in smart agriculture. In particular, it a prerequisite for detection the mapping of infected areas. Wheat fusarium head blight (FHB) serious threat to quality yield wheat, so rapid wheat FHB important. This study proposed method based on unmanned aerial vehicle (UAV) low-altitude remote sensing multispectral imaging technology combined with spectral textural analysis monitor FHB. First, imagery population was collected by UAV. Second, 10 vegetation indices (VIs)were extracted from imagery. addition, three types (TIs), including normalized difference texture index (NDTI), (DTI), ratio (RTI) were subsequent modeling. Finally, VIs, TIs, VIs TIs integrated as input features, k-nearest neighbor (KNN), particle swarm optimization support vector machine (PSO-SVM), XGBoost used construct models. The results showed that algorithm fusion features has highest performance accuracy F1 score test set being 93.63% 92.93%, respectively. provides new approach nondestructive