Synthetic data augmentation and deep learning for real-time weed detection in agricultural fields

HIGHLIGHTS

• What: The overall framework consists of four stages: CycleGAN training and use for producing the synthetic clean images which improves the dataset; Crop and weeds localization using YOLOv8 detection; further classification of the localized regions using VGG16; and_(4) Grad-CAM to explain which aspects of the input the model focused on while performing the classification, thereby assisting detection and classification. The aim of the research is to create a machine_learning system for accurate and real-time weed identification within agricultural fields. The project aims to use CycleGAN for creating synthetic data to overcome the challenges in . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.