Plant disease detection based on data fusion of hyper-spectral and multi-spectral fluorescence imaging using Kohonen maps

Moshou, Dimitrios; Bravo, C.; Oberti, R.; West, Jonathan; Bodria, L.; McCartney, Alastair; Ramón, Herman

doi:10.1016/j.rti.2005.03.003

Cited by 180 publications

(78 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The results of Vonbueren et al [38], Vega et al [39] and Honkavaara et al [40] indicated that data from UAV-based spectral cameras can be used to monitor parameters (e.g., crop height, yield, aboveground biomass and nitrogen content) of various plants, such as grass, wheat and sunflowers. However, the use of UAVs for agricultural monitoring is limited by the weight of hyperspectral imaging systems, the complexity of image processing and the cost of sensors [41,42].…”

Section: Introductionmentioning

confidence: 99%

Estimation of Winter Wheat Above-Ground Biomass Using Unmanned Aerial Vehicle-Based Snapshot Hyperspectral Sensor and Crop Height Improved Models

et al. 2017

View full text Add to dashboard Cite

Correct estimation of above-ground biomass (AGB) is necessary for accurate crop growth monitoring and yield prediction. We estimated AGB based on images obtained with a snapshot hyperspectral sensor (UHD 185 firefly, Cubert GmbH, Ulm, Baden-Württemberg, Germany) mounted on an unmanned aerial vehicle (UAV). The UHD 185 images were used to calculate the crop height and hyperspectral reflectance of winter wheat canopies from hyperspectral and panchromatic images. We constructed several single-parameter models for AGB estimation based on spectral parameters, such as specific bands, spectral indices (e.g., Ratio Vegetation Index (RVI), NDVI, Greenness Index (GI) and Wide Dynamic Range VI (WDRVI)) and crop height and several models combined with spectral parameters and crop height. Comparison with experimental results indicated that incorporating crop height into the models improved the accuracy of AGB estimations (the average AGB is 6.45 t/ha). The estimation accuracy of single-parameter models was low (crop height only: R 2 = 0.50, RMSE = 1.62 t/ha, MAE = 1.24 t/ha; R 670 only: R 2 = 0.54, RMSE = 1.55 t/ha, MAE = 1.23 t/ha; NDVI only: R 2 = 0.37, RMSE = 1.81 t/ha, MAE = 1.47 t/ha; partial least squares regression R 2 = 0.53, RMSE = 1.69, MAE = 1.20), but accuracy increased when crop height and spectral parameters were combined (partial least squares regression modeling: R 2 = 0.78, RMSE = 1.08 t/ha, MAE = 0.83 t/ha; verification: R 2 = 0.74, RMSE = 1.20 t/ha, MAE = 0.96 t/ha). Our results suggest that crop height determined from the new UAV-based snapshot hyperspectral sensor can improve AGB estimation and is advantageous for mapping applications. This new method can be used to guide agricultural management.

show abstract

Section: Introductionmentioning

confidence: 99%

Estimation of Winter Wheat Above-Ground Biomass Using Unmanned Aerial Vehicle-Based Snapshot Hyperspectral Sensor and Crop Height Improved Models

et al. 2017

View full text Add to dashboard Cite

show abstract

“…However, there are several limitations in assessment of viral diseases with traditional approach that it is often time consuming, labour intensive and erroneous as induction of similar symptoms due to several other reasons [3,6]. Remote sensing data especially reflectance found to be capable of detecting changes in the biophysical properties of plant and canopy associated with pathogens [13,21,22]. Additionally, remote sensing may provide a better means to objectively quantify disease stress than visual assessment methods, and it can be used to repeatedly collect sample measurements non-destructively and non-invasively [21,25].…”

Section: Introductionmentioning

confidence: 99%

Spectral reflectance pattern in soybean for assessing yellow mosaic disease

et al. 2013

View full text Add to dashboard Cite

Remote sensing technique is useful for monitoring large crop area at a single time point, which is otherwise not possible by visual observation alone. Yellow mosaic disease (YMD) is a serious constraint in soybean production in India. However, hardly any basic information is available for monitoring YMD by remote sensing. Present study examines spectral reflectance of soybean leaves due to Mungbean yellow mosaic India virus (MYMIV) infection in order to identify YMD sensitive spectral ratio or reflectance. Spectral reflectance measurement indicated significant (p \ 0.001) change in reflectance in the infected soybean canopy as compared to the healthy one. In the infected canopy, reflectance increased in visible region and decreased in near infra-red region of spectrum. Reflectance sensitivity analysis indicated wavelength *642, *686 and *750 nm were sensitive to YMD infection. Whereas, in yellow leaves induced due to nitrogen deficiency, the sensitive wavelength was *589 nm. Due to viral infection, a shift occurred in red and infra-red slope (called red edge) on the left in comparison to healthy one. Red edge shift was a good indicator to discriminate yellow mosaic as chlorophyll gets degraded due to MYMIV infection. Correlation of reflectance at 688 nm (R688) and spectral reflectance ratio at 750 and 445 nm (R750/R445) with the weighted mosaic index indicated that detection of yellow mosaic is possible based on these sensitive bands. Our study for the first time identifies the yellow mosaic sensitive band as R688 and R750/R445, which could be utilized to scan satellite data for monitoring YMD affected soybean cropping regions.

show abstract

“…This technique has already been developed for on-line estimation of the biomass variability in crop fields, evaluation of nitrogen status of plants and site-specific fertilisation (Bredemeier & Schmidhalter, 2003;Schächtl, Maidl, Huber, & Sticksel, 2003). The latter investigations also demonstrate the potential of LIF systems for detection of early stages of pathogen infection under field conditions (Moshou et al, 2005). The practical application of LIF in precision agriculture, however, can be problematical in that, under field conditions, different abiotic and biotic stress factors may appear at the same time.…”

Section: Introductionmentioning

confidence: 86%

Distinguishing nitrogen deficiency and fungal infection of winter wheat by laser-induced fluorescence

2006

View full text Add to dashboard Cite

One of the most important tasks in precision farming is the site-specific application of fertilisers and pesticides in heterogeneous large-area fields. For such sitespecific crop management, effective remote sensing methods for the detection of crop diseases and nutrient deficiencies are required. The aim of the present work was to compare laser-induced fluorescence (LIF) parameters from nitrogen-deficient and pathogen (rust and mildew)-infected winter wheat (Triticum aestivum L.) plants and to assess the potential of LIF to detect and discriminate between these types of stress. Both long term nitrogen deficiency and pathogen infection resulted in an increase of the ratio of fluorescence at 686 and 740 nm (F686/F740) accompanied by a reduction of leaf chlorophyll content to approximately 35 lg cm )2 . A linear negative correlation between chlorophyll content and F686/F740 ratio (r 2 = 0.78) was found for leaves with chlorophyll content ranging between 17 and 52 lg cm )2 . Since chlorophyll breakdown appeared an unspecific symptom to both nitrogen deficiency and pathogen infection, it was not possible to discriminate between these types of stress only by means of the F686/F740 ratio. Specific for the pathogen-infected leaves was a large heterogeneity in the records of their spectral parameters caused by inhomogeneous, discrete lesions of fungi infection. Nitrogen-deficient plants with homogeneous reduction in chlorophyll content showed, in contrast, more uniform readings of the spectral parameters. Thus, mildew-and rust-infected plants, grown under sufficient nitrogen fertilisation could be distinguished from those grown under reduced nitrogen supply by the higher variance of their spectral readings. The simultaneous scanning multipoint mode measurements of LIF and laser light reflection characteristics with parallel estimation of their heterogeneity is proposed for the discrimination between nitrogen deficiency and pathogen infection under field conditions.

show abstract

Plant disease detection based on data fusion of hyper-spectral and multi-spectral fluorescence imaging using Kohonen maps

Cited by 180 publications

References 12 publications

Estimation of Winter Wheat Above-Ground Biomass Using Unmanned Aerial Vehicle-Based Snapshot Hyperspectral Sensor and Crop Height Improved Models

Estimation of Winter Wheat Above-Ground Biomass Using Unmanned Aerial Vehicle-Based Snapshot Hyperspectral Sensor and Crop Height Improved Models

Spectral reflectance pattern in soybean for assessing yellow mosaic disease

Distinguishing nitrogen deficiency and fungal infection of winter wheat by laser-induced fluorescence

Contact Info

Product

Resources

About