Detection of broadleaf weeds growing in turfgrass with convolutional neural networks.

Journal: Pest management science
Published Date:

Abstract

BACKGROUND: Weed infestations reduce turfgrass aesthetics and uniformity. Postemergence (POST) herbicides are applied uniformly on turfgrass, hence areas without weeds are also sprayed. Deep learning, particularly the architecture of convolutional neural network (CNN), is a state-of-art approach to recognition of images and objects. In this paper, we report deep learning CNN (DL-CNN) models that are remarkably accurate at detection of broadleaf weeds in turfgrasses.

Authors

  • Jialin Yu
    Department of Mathematics and Numerical Simulation and High-Performance Computing Laboratory, School of Sciences, Nanchang University, Nanchang 330031, China.
  • Shaun M Sharpe
    Gulf Coast Research and Education Center, University of Florida, Wimauma, FL, USA.
  • Arnold W Schumann
    Citrus Research and Education Center, University of Florida, Lake Alfred, FL, USA.
  • Nathan S Boyd
    Gulf Coast Research and Education Center, University of Florida, Wimauma, FL, USA.