Fusion of sensor data for the detection and differentiation of plant diseases in cucumber

Abstract

The development of plant diseases is associated with biophysical and biochemical changes in host plants. Various sensor methods have been used and assessed as alternative diagnostic tools under greenhouse conditions. Changes in photosynthetic activity, spectral reflectance and transpiration rate of diseased leaves, inoculated with Cucumber mosaic virus (CMV), Cucumber green mottle mosaic virus (CGMMV), and the powdery mildew fungus Sphaerotheca fuliginea were assessed by the use of non-invasive sensors during disease development. Spatiotemporal changes in leaf temperature related to transpiration were visualized by digital infrared thermography. The maximum temperature difference within a leaf was an appropriate parameter to differentiate between healthy and diseased plants. The photosynthetic activity of healthy and diseased cucumber plants varied as measured by chlorophyll fluorescence and compared to the actual chlorophyll content. Hyperspectral imaging data were analysed using spectral vegetation indices. The results from this study confirm that each pathogen has a characteristic influence on the physiology and vitality of cucumber plants, which can be measured by a combination of non-invasive sensors. Whereas thermography and chlorophyll fluorescence are unspecific indicators for plant diseases, hyperspectral imaging offers the potential for an identification of plant diseases. In a sensor data fusion approach, an early detection of each pathogen was possible by discriminant analysis. Although it still needs to be validated under real conditions, the combination of information from different sensors seems to be a promising tool.

Multicolor Fluorescence Imaging as a Candidate for Disease Detection in Plant Phenotyping

“…Thus, infection by huanglongbing in citrus could be detected by support vector machine classification trees (Sankaran et al, 2013) and blight diseases on tomato leaves by extreme learning machine (Xie et al, 2015) with an accuracy ranging from 70 to 100%, respectively. On the other hand, several diseases in cucurbits have been analyzed by a combination of thermal, chlorophyll fluorescence dynamics, and hyperspectral imaging (Berdugo et al, 2014). In that work, a general linear model was able to classify plants infected with two different viruses and one fungal pathogen with an accuracy of 85–100%.…”

Advanced methods of plant disease detection. A review

“…Spectral and fluorescence data were exploited to monitor winter wheat yellow rust, with greater accuracy than by using only fluorescence data (Moshou et al 2012). In Berdugo et al (2014), the joint monitoring of leaf temperature, chlorophyll fluorescence and hyperspectral vegetation indices (VIs) has provided good capabilities in identifying and distinguishing cucumber diseases (mosaic virus, green mottle mosaic virus, and powdery mildew).…”

“…,Costa et al (2007) Delalieux et al (2007),Yang et al (2007),Chen et al (2008),Naidu et al (2009),Purcell et al (2009),Grisham et al (2010),Rumpf et al (2010), Huang et al (2012), Stilwell et al (2013), Yuan et al (2014), and Zhang et al (2014) Fluorescence spectroscopy Features extraction, data mining, regression analysis, and passive fluorescence Lins et al (2009) Imaging RGB cameras Visual assessment and image analysis Smith and Dickson (1991), Nilsson (1995), Nutter and Schultz (1995), Johnson et al (2003), Seiffert and Schweizer (2005), Bock et al (2008), Camargo and Smith (2009), and Bock et al (2010) Multispectral-hyperspectral imaging SVI, ICA-PCA, image classification, feature extraction, SMA, ANN, and bio-optical vegetation parameters Delwiche and Kim (2000), Bravo et al (2003), Zhang et al (2003), Moshou et al (2004), Moshou et al (2005), Okamoto et al (2007), Blasco et al (2007), Gowen et al (2007), Huang et al (2007), Sighicelli et al (2009), Rumpf et al (2010), Bauriegel et al (2011); Hillnhütter et al (2011), Mewes et al (2011), Mirik et al (2011), Mahlein et al (2012a), Mahlein et al (2012b), Reynolds et al (2012), Wang et al (2012), Mahlein et al (2013), Mirik et al (2013), Calderón et al (2013), and Berdugo et al (2014)Thermal imaging ICA, PCA, and image classificationChaerle et al (1999Chaerle et al ( , 2003,Chaerle and Van der Straeten (2000),Oerke et al (2006),Costa et al (2013), andBerdugo et al (2014) Fluorescence imaging Features extraction, data mining, and regression analysisLichtenthaler et al (1996),Chaerle et al (2003),…”

The Use of Features from Fluorescence, Thermography, and NDVI Imaging to Detect Biotic Stress in Lettuce

“…Using laser-induced fluorescence spectroscopy, Belasque et al (2008) discriminated not only between healthy and unhealthy citrus plants but also between mechanical and biotic stresses among the unhealthy plants. Fluorescence measurements have been used to detect sugar beet leaf spot disease (Cercospora beticola) (Chaerle et al 2007a), cucumber mosaic (Cucumber mosaic virus) (Berdugo et al 2014), apple scab (Venturia inaequalis) (Belin et al 2013), and tobacco mosaic (Tobacco mosaic virus [TMV]) (Chaerle et al 2007b). Infrared thermography has been used to detect diseases.…”

“…We assume that the negative impact of the pathogen on growth is related to physiological changes that can be detected using imaging techniques. In contrast to most existing measures, detection was not performed on the scale of single leaves (Berdugo et al 2014;Chaerle et al 2007a;Daley 1995), leaf spots (Belin et al 2013;Chaerle et al 2007b;Scholes and Rolfe 2009), or canopies (Calderón et al 2013) but on the scale of whole plants. Germany).…”