Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Integrated Network Toxicology and Metabolomics Reveal the Reproductive Toxicity Mechanisms of Alkaloid-Enriched Fractions in Tripterygium Glycosides Tablets.

Toxins·2026
Same author

Transformative biomechanics and mechanobiology breakthroughs shaping the future of health and medicine.

Innovation (Cambridge (Mass.))·2026
Same author

Mechanical and biological properties of dual-topology fusion orthotropic bone scaffold.

Biomaterials advances·2026
Same author

Intelligent Attention-Driven Deep Learning for Hip Disease Diagnosis: Fusing Multimodal Imaging and Clinical Text for Enhanced Precision and Early Detection.

Medicina (Kaunas, Lithuania)·2026
Same author

An automated vertebral heart scale measurement tool based on deep learning: Facilitating screening for prevention of canine cardiomegaly.

Preventive veterinary medicine·2026
Same author

DGS-YOLO: A Detection Network for Rapid Pig Face Recognition.

Animals : an open access journal from MDPI·2026

Related Experiment Video

Updated: Aug 12, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

600

DenseNet weed recognition model combining local variance preprocessing and attention mechanism.

Ye Mu1,2,3,4, Ruiwen Ni1,2,3,4, Lili Fu1,2,3,4

  • 1College of Information Technology, Jilin Agricultural University, Changchun, China.

Frontiers in Plant Science
|January 30, 2023
PubMed
Summary

This study introduces a novel method for accurately identifying weed species in complex crop fields. The developed model achieves 97.98% accuracy, significantly improving weed detection for intelligent weeding robots.

Keywords:
DenseNetattention mechanismimage preprocessinglocal varianceweed recognition

More Related Videos

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

469
Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

1.5K

Related Experiment Videos

Last Updated: Aug 12, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

600
Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

469
Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

1.5K

Area of Science:

  • Agricultural Science
  • Computer Vision
  • Machine Learning

Background:

  • Accurate weed identification in dense crop fields is challenging due to complex environments.
  • Existing methods struggle with distinguishing numerous, densely distributed weed species.

Purpose of the Study:

  • To develop an effective and accurate method for identifying weed species in complex agricultural settings.
  • To enhance the performance of weed detection models for intelligent weeding systems.

Main Methods:

  • Utilized local variance pre-processing for background segmentation and data enhancement.
  • Integrated Efficient Channel Attention (ECA) mechanism into an optimized DenseNet network to improve feature discrimination.
  • Trained the model using processed images to strengthen weed features and suppress background noise.

Main Results:

  • Achieved a high accuracy rate of 97.98% in weed species identification.
  • Demonstrated superior performance compared to established models like DenseNet, VGGNet, and ResNet.
  • The proposed method effectively removes complex backgrounds and prevents model overfitting.

Conclusions:

  • The developed model and method are highly suitable for accurate crop and weed species identification in complex environments.
  • This research provides a strong technical foundation for the advancement of intelligent weeding robots.
  • The approach significantly improves the accuracy and efficiency of automated weed management systems.