Convolutional neural network based on the fusion of image classification and segmentation module for weed detection in alfalfa.

Journal: Pest management science
PMID:

Abstract

BACKGROUND: Accurate and reliable weed detection in real time is essential for realizing autonomous precision herbicide application. The objective of this research was to propose a novel neural network architecture to improve the detection accuracy for broadleaf weeds growing in alfalfa.

Authors

  • Jie Yang
    Key Laboratory of Development and Maternal and Child Diseases of Sichuan Province, Department of Pediatrics, Sichuan University, Chengdu, China.
  • Yong Chen
    Department of Urology, Chongqing University Fuling Hospital, Chongqing, China.
  • Jialin Yu
    Department of Mathematics and Numerical Simulation and High-Performance Computing Laboratory, School of Sciences, Nanchang University, Nanchang 330031, China.