Spectral characteristics of rice plants at various levels of infestation by the brown planthopper, Nilaparvata lugens (Stål), (Homoptera:Delphacidae), in the early grain-filling stage were measured and analyzed using a spectroradiometer. Plant damage was classified into six scales, i.e., 0 (CK), 1, 3, 5, 7 and 9, based on the scale of infestation displayed on the surfaces of plant parts. Results showed that mean curves of reflectance spectra (350 - 1800 nm) from different scales of insect infestation were clearly differentiated, especially in the region of 737 - 925 nm, where reflectance was in the order of severity. There were significant differences in reflectance among infestations at wavelengths of 755 and 890 nm particularly. Spectral parameters such as the normalized difference vegetation index (NDVI) and cumulative reflectance may also be used to discriminate levels of infestation. Twelve wavelengths from apparent peaks and valleys of individual spectra were selected as characteristic wavelengths making up the spectral signature of each infestation.
"In recent years, there has been an increasing use of machine vision and learning approaches in the domain of agriculture applied towards detecting and classifying various diseases on trees and fruits   . Major citrus diseases such as citrus canker (Xanthomonas axonopodis pv. "
[Show abstract][Hide abstract] ABSTRACT: We have used fluorescence imaging spectroscopy to investigate Huanglongbing disease in USA and Brazil. Texture features were extracted and used as input into classifier. Results show differences between leaves collected in Brazil and USA.
"foliage had lower reflectance despite having 50% lower chloro - phyll concentration than uninfested plants . While there is variability with respect to reflectance pattern of infested plants in the visible region , reflectance of infested plants in the NIR was previously observed to be , without exception , uniformly lower than uninfested plants ( Yang et al . 2001 , 2007 ; Kumar et al . 2010 ; Prabhakar et al . 2011 ) . Lower reflectance of infested plants in the NIR region ( 740 – 925 nm ) compared with uninfested plants can be ascribed to curling , shrinking and wilting of leaves due to BPH damage that might have led to scattering instead of reflectance of incident radiation , thereby resulting"
[Show abstract][Hide abstract] ABSTRACT: Hyperspectral remote sensing was used to detect stress on potted rice plants caused by the Brown Planthopper (BPH), Nila-parvata lugens (Sta l). BPH damage influenced reflectance of rice plants compared to uninfested plants in the visible and near-infrared regions of the electromagnetic spectrum. Correlations between plant reflectance and BPH damage, when plot-ted against wavelengths, enabled us to identify four sensitive wavelengths, at 1986, 665, 1792 and 500 nm, in relation to BPH stress on rice plants. Based on rice plant reflectance corresponding to the sensitive wavelengths, three hyperspectral indices were developed. The BPH damage showed a positive association with normalized pigment chlorophyll index, and a negative relationship with normalized difference vegetation index and soil adjusted vegetation index. Using rice plant reflectance corresponding to the sensitive wavelengths, a multiple-linear regression model was developed and validated, which would facilitate assessment of BPH damage based on rice plant reflectance, thereby ensuring prompt forewarning to stakeholders.
International Journal of Pest Management 06/2013; 59(3). DOI:10.1080/09670874.2013.808780 · 0.96 Impact Factor
"In recent years, there has been an increasing use of machine vision and learning approaches in the domain of agriculture applied towards detecting and classifying various diseases on trees and fruits   . Such techniques need to be developed for sustainable agriculture and to prevent great economic losses. "
[Show abstract][Hide abstract] ABSTRACT: The overall objective of this work was to develop and evaluate computer vision and machine learning technique for classification of Huanglongbing-(HLB)-infected and healthy leaves using fluorescence imaging spectroscopy. The fluorescence images were segmented using normalized graph cut, and texture features were extracted from the segmented images using cooccurrence matrix. The extracted features were used as an input into the classifier, support vector machine (SVM). The classification results were evaluated based on classification accuracies and number of false positives and false negatives. The results indicated that the SVM could classify HLB-infected leaf fluorescence intensities with up to 90% classification accuracy. Though the fluorescence intensities from leaves collected in Brazil and the USA were different, the method shows potential for detecting HLB.
Journal of Spectroscopy 11/2012; 2013(3). DOI:10.1155/2013/841738 · 0.54 Impact Factor
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.