Evaluation of an Automated Severity Classification Framework for Rice BLB at a Regional Scale Using Multispectral UAV Imagery

Rice bacterial leaf blight (BLB), caused by the bacterium Xanthomonas oryzae pv. oryzae, severely damages leaves during rice growth, leading to reduced yield or even death. This study aimed to develop an automated identification and assessment method for rice BLB based on multispectral UAV imagery to overcome the limitations of in-field inspection methods. By obtaining multispectral image data of rice fields and extracting color features (CFs), texture features (TFs), and vegetation indices (VIs) of rice canopy using image processing techniques, three algorithms, namely, Support Vector Machine (SVM), Random Forest (RF), and Back Propagation Neural Network (BPNN), were utilized to establish a monitoring model for the severity levels of rice BLB. The classification results of several models are compared, with the overall Correct Identification Rate (CIR) of the three-feature fusion classification algorithm generally higher than the other two. Among the three algorithms, the RF algorithm performs the best, with a CIR reaching 93.4% and a Kappa coefficient of 0.91. The BPNN algorithm follows, with a CIR of 82.1% and a Kappa coefficient of 0.76, showing moderate effectiveness. Lastly, the SVM algorithm performs the poorest, with a CIR of 65.1% and a Kappa coefficient of 0.54. A rice BLB large-scale detection framework based on unmanned aerial vehicle (UAV) images was designed, and a graphical user interface (GUI) was developed using Python language to achieve automated processing from image input to final recognition results, achieving good results.