2019 · 21 citations · 5 references
AgriculturePlant PathologyPlant SciencesCrop SensingPlant Disease DiagnosisRemote SensingDisease DetectionFungal DiagnosticsFungal IdentificationHyperspectral ImagingMultispectral ImagingSymptom RecognitionDifferentiationHyperspectral ClassificationHyperspectral Disease DetectionHyperspectral Image ProcessingHyperspectral SensorsPlant Fungal DiseaseScab DiseasesWater Absorption
The aim of our study is to examine the potential of SWIR hyperspectral imaging to early detect apple scab infection. Close range hyperspectral images of healthy and infected leaves were acquired daily under laboratory conditions from 2 days to 11 days after inoculation using a push-broom SWIR camera. A PLS-DA classification model was built at the advanced infection stage D11 and was applied on the infected and healthy leaves images acquired at others infection stages. This study showed that good predictions can be achieved when classifying infected leaf regions based on hyperspectral data using PLS-DA. Results suggest that the spectral domain between 1000 - 2500 nm is suited to early differentiation between infected and healthy leaves. At early infection stages, the water absorption band at 1940 nm has the major discriminatory effect.
5
Partial least squares for discrimination
Matthew L Barker, William S. Rayens · Journal of Chemometrics · 2003 · 2.8K citations
Minghua Zhang, Zhihao Qin, Xue Liu et al. · International Journal of Applied Earth Observation and Geoinformation · 2003 · 251 citations
Stephanie Delalieux, Jan van Aardt, Wannes Keulemans et al. · European Journal of Agronomy · 2007 · 227 citations