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

Sparse-MoE-SAM: A Lightweight Framework Integrating MoE and SAM with a Sparse Attention Mechanism for Plant Disease Segmentation in Resource-Constrained Environments.

Plants (Basel, Switzerland)·2025
Same author

Decoding of polar-coded OFDM systems over multipath fading channels with interleaving and channel state information.

Scientific reports·2024
Same author

CTDUNet: A Multimodal CNN-Transformer Dual U-Shaped Network with Coordinate Space Attention for <i>Camellia oleifera</i> Pests and Diseases Segmentation in Complex Environments.

Plants (Basel, Switzerland)·2024
Same author

Empagliflozin rescues diabetic myocardial microvascular injury via AMPK-mediated inhibition of mitochondrial fission.

Redox biology·2018
Same author

Preparation of Starch-Hard Carbon Spherules from Ginkgo Seeds and Their Phenol-Adsorption Characteristics.

Molecules (Basel, Switzerland)·2018
Same author

ATM Signaling Pathway Is Implicated in the SMYD3-mediated Proliferation and Migration of Gastric Cancer Cells.

Journal of gastric cancer·2018

Related Experiment Video

Updated: Apr 15, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.7K

TB-DLossNet: Fine-Grained Segmentation of Tea Leaf Diseases Based on Semantic-Visual Fusion.

Shuqi Zheng1, Hao Zhou1, Ziyang Shi1

  • 1School of Electronic Information and Physics, Central South University of Forestry and Technology, Changsha 410004, China.

Plants (Basel, Switzerland)
|April 14, 2026
PubMed
Summary

A new AI model, TB-DLossNet, accurately segments plant diseases in Camellia oleifera crops. This advanced image analysis improves precision agriculture by precisely identifying lesions, even small ones, for better disease management.

Keywords:
Camellia oleiferaVMambadeep learningmultimodal integrationpest and disease segmentation

More Related Videos

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

3.4K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.7K

Related Experiment Videos

Last Updated: Apr 15, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.7K
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

3.4K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.7K

Area of Science:

  • Agricultural Science
  • Computer Vision
  • Plant Pathology

Background:

  • Camellia oleifera is a vital oil crop threatened by diseases, necessitating precise disease detection for effective management.
  • Current pixel-level lesion segmentation methods face challenges with semantic ambiguity, blurred boundaries, and detecting micro-lesions in complex field conditions.

Purpose of the Study:

  • To develop an advanced segmentation framework, TB-DLossNet, for accurate pixel-level disease lesion identification in Camellia oleifera.
  • To address limitations in existing methods, including semantic ambiguity, boundary issues, and the detection of small pathological features.

Main Methods:

  • Proposed TB-DLossNet, a novel semantic-visual multi-modal fusion framework utilizing VMamba as the visual backbone.
  • Integrated BERT-encoded text for cross-modal semantic guidance, a boundary enhancement branch, and multi-scale deep supervision.
  • Introduced a dynamic weight loss function conditioned on lesion area to improve sensitivity to minute pathological features.

Main Results:

  • TB-DLossNet achieved a Mean Intersection over Union (mIoU) of 87.02%, surpassing state-of-the-art methods.
  • Demonstrated superior performance in reducing false-negative rates and enhancing boundary precision in complex field scenarios.
  • Validated robustness and transferability through generalization tests on an apple disease dataset.

Conclusions:

  • TB-DLossNet offers a robust solution for precise plant disease segmentation in challenging agricultural environments.
  • The semantic-visual fusion approach effectively resolves ambiguities and improves lesion boundary detection.
  • The framework shows significant potential for advancing precision plant protection strategies in agriculture.