Hybrid Segmentation - Artificial Neural Network Classification of High Resolution Hyperspectral Imagery for Site-Specific Herbicide Management in Agriculture

Site-Specific Herbicide Management (SSHM) in Precision Agriculture (PA) requires weed detection in crop fields for directed herbicide application instead of spraying entire fields. This has significant economic and environmental advantages for improved agricultural practices that are essential given forecast increases in global population and food production needs. In this study, a new hybrid segmentation - Artificial Neural Network (HS-ANN) method was compared to standard Maximum Likelihood Classification (MLC) for improving crop/weed species discrimination in SSHM/PA. Very high spatial resolution (1.25 mm) ground-based hyperspectral image data were acquired over field plots of canola, pea, and wheat crops seeded with two weed species (redroot pigweed, wild oat) in southern Alberta, Canada. The very high spatial and spectral resolution image data required development of a simple yet efficient vegetation index (Modified Chlorophyll Absorption in Reflectance Index (MCARI)) threshold segmentation to separate vegetation from soil for classification. The HSANN consistently outperformed MLC in both single date and multi-temporal classifications. Higher class accuracies were obtained with multi-temporally trained ANNs (84 to 92 percent overall), with improvements up to 31 percent over MLC. With advancements in imaging technology and computer processing speed, this HS-ANN method may constitute a viable farm option for real-time detection and mapping of weed species for SSHM in agriculture.

[1]  A. J. S. McDonald,et al.  Weed and crop discrimination using image analysis and artificial intelligence methods , 2003 .

[2]  J. Key,et al.  Classification of merged AVHRR and SMMR Arctic data with neural networks , 1989 .

[3]  F ROSENBLATT,et al.  The perceptron: a probabilistic model for information storage and organization in the brain. , 1958, Psychological review.

[4]  S. McGinn,et al.  Neural network models to predict the maturity of spring wheat in western Canada , 2002 .

[5]  Chun-Chieh Yang,et al.  Development of a herbicide application map using artificial neural networks and fuzzy logic , 2003 .

[6]  Scott D. Noble,et al.  ANALYSIS OF CROP AND WEED LEAF DIFFUSE REFLECTANCE SPECTRA , 2005 .

[7]  M. Ivimey.  Annual report , 1958, IRE Transactions on Engineering Writing and Speech.

[8]  Shunlin Liang,et al.  Remote Sensing of Weed Canopies , 2002 .

[9]  Jon Atli Benediktsson,et al.  Neural Network Approaches Versus Statistical Methods in Classification of Multisource Remote Sensing Data , 1989, 12th Canadian Symposium on Remote Sensing Geoscience and Remote Sensing Symposium,.

[10]  John R. Miller,et al.  Integrated narrow-band vegetation indices for prediction of crop chlorophyll content for application to precision agriculture , 2002 .

[11]  J. V. Stafford,et al.  Potential for automatic weed detection and selective herbicide application , 1991 .

[12]  D. Peddle,et al.  Spectral mixture analysis of agricultural crops: Endmember validation and biophysical estimation in potato plots , 2005 .

[13]  Jin-Young Jeong,et al.  AE—Automation and Emerging Technologies: Weed–plant Discrimination by Machine Vision and Artificial Neural Network , 2002 .

[14]  Robert E. Blackshaw,et al.  Reduced herbicide doses in field crops: A review , 2006 .

[15]  A. Smith,et al.  Weed–Crop Discrimination Using Remote Sensing: A Detached Leaf Experiment1 , 2003, Weed Technology.

[16]  L. Tweeten.  Dodging a Malthusian bullet in the 21st Century , 1998 .

[17]  John R. Jensen,et al.  Introductory Digital Image Processing: A Remote Sensing Perspective , 1986 .

[18]  Differentiation of turfgrass and common weed species using hyperspectral radiometry , 2006, Weed Science.

[19]  John R. Jensen,et al.  Opening the black box of neural networks for remote sensing image classification , 2004 .

[20]  David A. Mortensen,et al.  Economic Importance of Managing Spatially Heterogeneous Weed Populations , 1998, Weed Technology.

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

[22]  T. F. Burks,et al.  Evaluation of Neural-network Classifiers for Weed Species Discrimination , 2005 .

[23]  S. O. Prasher,et al.  Application of artificial neural networks in image recognition and classification of crop and weeds , 2000 .

[24]  Hiroshi Okamoto,et al.  Plant classification for weed detection using hyperspectral imaging with wavelet analysis , 2007 .

[25]  Lei Tian,et al.  COLOR IMAGE SEGMENTATION WITHGENETIC ALGORITHM FOR IN-FIELD WEED SENSING , 2000 .

[26]  P. Atkinson,et al.  Introduction Neural networks in remote sensing , 1997 .

[27]  Scott D. Noble,et al.  Site-specific weed management: sensing requirements— what do we need to see? , 2005, Weed Science.

[28]  Moon S. Kim,et al.  Estimating Corn Leaf Chlorophyll Concentration from Leaf and Canopy Reflectance , 2000 .

[29]  Scott A. Shearer,et al.  BACKPROPAGATION NEURAL NETWORK DESIGN AND EVALUATION FOR CLASSIFYING WEED SPECIES USING COLOR IMAGE TEXTURE , 2000 .

[30]  P. C. Robert,et al.  Managing Spatially Variable Weed Populations , 1995 .

[31]  John F. Reid,et al.  DEVELOPMENT OF A PRECISION SPRAYER FOR SITE-SPECIFIC WEED MANAGEMENT , 1999 .

[32]  R. B. Brown,et al.  Prescription Maps for Spatially Variable Herbicide Application in No-till Corn , 1995 .

[33]  T. F. Burks,et al.  CLASSIFICATION OF WEED SPECIES USING COLOR TEXTURE FEATURES AND DISCRIMINANT ANALYSIS , 2000 .

[34]  Murray Smith,et al.  Neural Networks for Statistical Modeling , 1993 .

[35]  F. E. LaMastus,et al.  Using remote sensing to detect weed infestations in Glycine max , 2000, Weed Science.

[36]  F. Larney,et al.  Fertilizer, manure and compost effects on weed growth and competition with winter wheat in western Canada , 2005 .

[37]  L. R. Oliver,et al.  Assessing the Reflective Characteristics of Palmer Amaranth (Amaranthus Palmeri) and Pitted Morningglory (Ipomoea Lacunosa) Accessions , 2007, Weed Science.