Weeds detection by ground-level hyperspectral imaging Academic Article uri icon

abstract

  • Weed control of grass and broadleaf is commonly performed by applying selective herbicides homogeneously all over the field. Applying the herbicide only where needed has economical and environmental benefits. Combining remote sensing tools and techniques with precision agriculture concept has the potential to automatically locate and identify weeds. The objective of this work is to detect grasses and broadleaf weeds among cereal as well as broadleaf crops by spectroscopy. Leaf and canopy spectral relative reflectance values of three targets: crop (wheat and chickpea); grass weeds (GW); and broadleaf weeds (BLW) were obtained by field spectrometer. Leaf spectral classifications for botanical genera as well as category were almost perfect (99%). Canopy spectral classification for targets was accurate (95%) in homogeneous field of view (FOV). Within the critical period for weeds …

publication date

  • January 1, 2010