Foliar Disease Detection in the Field Using Optical Sensor Fusion

The objective of this research was to detect and recognize the plant stress caused by disease in the field conditions by combining hyperspectral reflection information between 450 and 900nm and fluorescence imaging. The results can be used to develop a tractor mounted cost-effective optical device for site-specific pesticide application in order to reduce and optimize pesticide use. The work reported here used yellow rust (Puccinia striiformis) disease of winter wheat as a model system. In the field hyperspectral reflection images of healthy and infected plants were taken by an imaging spectrograph mounted at spray boom height. Leaf recognition and spectral normalization procedures were used to account for differences in canopy architecture and spectral illumination were used. A model, based on quadratic discrimination, was built, using a selected group of wavebands to differentiate diseased from healthy plants. The model could discriminate diseased from healthy crop with an error of about 10% using measurements from only three wavebands. Multispectral fluorescence images were taken on the same plants using UV-blue excitation. Through comparison of the 550 and 690 nm fluorescence images, the detection of disease was clearly possible. Fraction of pixels in one image, recognized as diseased, was set as final fluorescence disease variable and called the lesion index (LI). The lesion index was added to the pool of normalized selected reflection wavebands. This pool of observations was used in a quadratic discrimination model. The combined model improved disease discrimination compared to either the spectral model or fluorescent model and had a classification error of between 5 and 6 %. The results suggest that there is a potential for developing detection systems based on multisensor measurements that can be used in precision disease control systems for use in arable crops.

[1]  J. Gardiner.  Ministry of Agriculture and Fisheries , 1924, Nature.

[2]  J. A. Schell,et al.  Monitoring the Vernal Advancement and Retrogradation (Green Wave Effect) of Natural Vegetation. [Great Plains Corridor] , 1973 .

[3]  Carroll E. Goering,et al.  Engine and tractor power , 1985 .

[4]  B. Lorenzen,et al.  Changes in leaf spectral properties induced in barley by cereal powdery mildew , 1989 .

[5]  F. Boochs,et al.  Shape of the red edge as vitality indicator for plants , 1990 .

[6]  Gregory A. Carter,et al.  Identification of a far-red reflectance response to ectomycorrhizae in slash pine , 1992 .

[7]  Ajit K. Srivastava,et al.  Engineering Principles of Agricultural Machines , 1993 .

[8]  J. C. Price.  How unique are spectral signatures , 1994 .

[9]  Paul F. Daley,et al.  Chlorophyll fluorescence analysis and imaging in plant stress and disease , 1994 .

[11]  D. Aylor,et al.  Chlorophyll Fluorescence Induction in Leaves of Phaseolus vulgaris Infected with Bean Rust (Uromyces appendiculatus) , 1995, Plant physiology.

[12]  J. Johansson,et al.  Remote fluorescence measurements of vegetation spectrally resolved and by multi-colour fluorescence imaging , 1996 .

[13]  Francine Heisel,et al.  Fluorescence Imaging of Water and Temperature Stress in Plant Leaves , 1996 .

[14]  Francine Heisel,et al.  Detection of Nutrient Deficiencies of Maize by Laser Induced Fluorescence Imaging , 1996 .

[15]  Francine Heisel,et al.  Detection of vegetation stress via a new high resolution fluorescence imaging system , 1996 .

[16]  V. P. Polischuk,et al.  Changes in reflectance spectrum characteristic of nicotiana debneyi plant under the influence of viral infection , 1997 .

[17]  Tsuguo Okamoto,et al.  Automatic diagnosis of plant disease - Spectral reflectance of healthy and diseased leaves , 1998 .

[18]  Ismael Moya,et al.  Ultraviolet-induced fluorescence for plant monitoring: present state and prospects , 1999 .

[19]  E. U. Odigboh.  CIGR Handbook of Agricultural Engineering, Volume III Plant Production Engineering, Chapter 1 Machines for Crop Production, Parts 1.1.1-1.1.4 Human-Powered Tools and Machines , 1999 .

[20]  Walter E. Riedell,et al.  Leaf Reflectance Spectra of Cereal Aphid-Damaged Wheat , 1999 .

[21]  A. G. Rijk.  CIGR Handbook of Agricultural Engineering, Volume III Plant Production Engineering, Chapter 2 Mechanization Systems, Part 2.2 Agricultural Mechanization Strategy , 1999 .

[22]  A. A. Wanders,et al.  CIGR Handbook of Agricultural Engineering, Volume III Plant Production Engineering, Chapter 1 Machines for Crop Production, Parts 1.1.5-1.1.9 Animals , 1999 .

[23]  I. Sache.  Short-distance dispersal of wheat rust spores , 2000 .

[24]  R. J. Bryson,et al.  Assessing crop condition in real time using high resolution satellite imagery. , 2000 .

[25]  Moon S. Kim,et al.  Fluorescence techniques in agricultural applications , 2001, Optics East.

[26]  Y. R. Chen,et al.  Steady-state multispectral fluorescence imaging system for plant leaves. , 2001, Applied optics.

[27]  G. Carter,et al.  Leaf optical properties in higher plants: linking spectral characteristics to stress and chlorophyll concentration. , 2001, American journal of botany.

[28]  Bart De Ketelaere,et al.  A neural network based plant classifier , 2001 .

[29]  J. V. Stafford,et al.  Simultaneous identification of plant stresses and diseases in arable crops based on a proximal sensing system and Self-Organising Neural Networks. , 2003 .

[30]  S. Rolfe,et al.  Photosynthesis in localised regions of oat leaves infected with crown rust (Puccinia coronata): quantitative imaging of chlorophyll fluorescence , 1996, Planta.