Detection of Wheat Powdery Mildew by Differentiating Background Factors using Hyperspectral Imaging

Abstract

Accurate assessment of crop disease severities is the key for precision application of pesticides to prevent disease infestation. In-situ hyperspectral imaging technology can provide high-resolution imagery with spectra for rapid identification of crop disease and determining disease infestation trend. In this study a hyperspectral imager was used to detect wheat powdery mildew with considering the impacts of wheat ears and the leaves under shadow to identify infected and healthy plant leaves. Through comparing the spectral differences between wheat ears and shadowed, healthy and infected plant leaves, 23 sensitive bands were chosen to distinguish different background targets. Five vegetation indices (VIs) and three red edge parameters were calculated based on screened sensitive bands. Then, 40 identification features were determined to distinguish different background factors and disease severities. Moreover, the classification and regression tree (CRT) was utilized to develop the prediction model of wheat powdery mildew. The identification accuracy was assessed by cross-validation with the accuracies that shadowed leaves can be perfectly recognized while the healthy and infected leaves, wheat ears could be identified with the rates of 98.4, 98.4 and 80.8%, respectively. For identification of different disease severities, the healthy leaves have the highest accuracy with 99.2%, while moderately and mildly infected leaves were determined as 88.2 and 87.8%, respectively. In overall, it was found that wheat ears could affect identification accuracy of wheat powdery mildew. At the same time, in order to provide guidance for application of pesticides, improved accuracy for detecting mildly infected disease is expected.

Identification of Wheat Yellow Rust Using Optimal Three-Band Spectral Indices in Different Growth Stages

“…The final symptom is dry leaf [4,24]. The disease reduces plant vigor and may cause it to become withered or die [25]. The canopy growth status changes during the growth period, and may result in an inconsistent relationship between the vegetation index and the status of yellow rust at different growth stages.…”

Estimating the severity of apple mosaic disease with hyperspectral images

“…By comparison, hyperspectral imagers address these limitations through their photography function. The pure spectra of leaf regions with different disease severities can be precisely extracted from hyperspectral images [36,37] , and the disease distribution can be mapped using image recognition and classification techniques [23] . With these advantages, hyperspectral imagers are considered suitable instruments for studying plant diseases at the leaf and canopy scales.…”

Hyperspectral imaging for early detection of foliar fungal diseases on small grain cereals: a minireview

“…Infection of plants by wheat powdery mildew (caused by Blumeria graminis f. sp. tritici) was studied by Zhang et al (2016) using hyperspectral imaging analysis to detect the effect of differentiating background (shadows) on the effectiveness of identification of infected and healthy plant leaves. Five different vegetation indices and classification and regression trees were used to analyze the data.…”

“…Five different vegetation indices and classification and regression trees were used to analyze the data. Healthy leaves were identified with the highest accuracy of 99.2%, while infected leaves were determined with an accuracy of 88.2% and 87.8%, respectively (Zhang et al, 2016). In another study of powdery mildew, a hyperspectral imaging dataset and machine learning algorithms were used (Zhao et al, 2020).…”