Download PDFOpen PDF in browserResearch on Diagnosis Characteristics of Wheat Powdery Mildew Under Different Severity Grading StandardsEasyChair Preprint 9386 pages•Date: April 28, 2019AbstractAbstract—Wheat powdery mildew (Blumeria graminis Dc.speer) is one of the most devastating crop diseases in the globe. Thinking of economic effective and environmental protection value, early detection of the severity of wheat powdery mildew can provide important information and technical support for disease prevention. In this study, the wheat leaves infected powdery mildew were chosen as observation objects, the obtained hyperspectral imagery data was pre-processed by reflectance calculation and noise elimination. After the disease-infected samples with different severities were divided into three-levels, four-levels, and five-levels, the effects of samples classification on identification of the disease were explored. Subsequently, the Relief-F algorithm was used to screen the sensitive bands of the disease in the early and mid-late growth stages, to observe the wavelengths change of disease identification in different developmental periods. The results showed that the sensitive bands of disease detection respectively locate at 700 nm and 680 nm for the early and mid-late growth stages, and the position of sensitive wavelength moves toward the short-wave direction as the disease worsens. On the basis, Calculating the powdery mildew disease index (PMDI) and nine kinds of common vegetation indexes, to compare their effects on disease identification, the study found that when the samples were divided into four levels, the determination coefficient R2 of PMDI is the highest. For the early and mid-late infection stages, the R2 are respectively 0.763 and 0.766. Furthermore, the corresponding SVM models were established in the different developmental periods, the classification accuracy of the early growth and mid-late stage are 90.63%, 84.62% respectively. The above results show that PMDI calculated by the sensitive band screening has good effective on identifying the severity of the disease, especially there is a good potential at the early growth stage. Keyphrases: SVM, Sensitive band, Wheat powdery mildew, vegetation index
|