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

Exploring biodiversity patterns at the landscape scale by linking landscape energy and land use/land cover heterogeneity.

The Science of the total environment·2024
Same author

Author Correction: Towards the automatic detection of social biomarkers in autism spectrum disorder: introducing the simulated interaction task (SIT).

NPJ digital medicine·2022
Same author

Ag-YOLO: A Real-Time Low-Cost Detector for Precise Spraying With Case Study of Palms.

Frontiers in plant science·2022
Same author

Primarily tests of a optoelectronic in-canopy sensor for evaluation of vertical disease infection in cereals.

Pest management science·2021
Same author

Publisher Correction: Rapid and low-cost insect detection for analysing species trapped on yellow sticky traps.

Scientific reports·2021
Same author

Global data on earthworm abundance, biomass, diversity and corresponding environmental properties.

Scientific data·2021

Related Experiment Video

Updated: Nov 9, 2025

A Precise and Autonomous System for the Detection of Insect Emergence Patterns
06:22

A Precise and Autonomous System for the Detection of Insect Emergence Patterns

Published on: January 9, 2019

5.9K

Early Detection of Stripe Rust in Winter Wheat Using Deep Residual Neural Networks.

Michael Schirrmann1, Niels Landwehr2,3, Antje Giebel1

  • 1Department of Engineering for Crop Production, Leibniz Institute for Agricultural Engineering and Bioeconomy, Potsdam, Germany.

Frontiers in Plant Science
|April 16, 2021
PubMed
Summary
This summary is machine-generated.

This study developed a deep learning image classifier to detect stripe rust (Pst) in wheat. The system achieved 90% accuracy at the patch level and 77% at the image level, enabling early disease detection.

Keywords:
ResNetcamera sensordeep learningimage recognitionmonitoringsmart farmingwheat cropsyellow rust

More Related Videos

A Fast Silver Staining Protocol Enabling Simple and Efficient Detection of SSR Markers using a Non-denaturing Polyacrylamide Gel
10:27

A Fast Silver Staining Protocol Enabling Simple and Efficient Detection of SSR Markers using a Non-denaturing Polyacrylamide Gel

Published on: April 20, 2018

11.1K
Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images
11:49

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

9.6K

Related Experiment Videos

Last Updated: Nov 9, 2025

A Precise and Autonomous System for the Detection of Insect Emergence Patterns
06:22

A Precise and Autonomous System for the Detection of Insect Emergence Patterns

Published on: January 9, 2019

5.9K
A Fast Silver Staining Protocol Enabling Simple and Efficient Detection of SSR Markers using a Non-denaturing Polyacrylamide Gel
10:27

A Fast Silver Staining Protocol Enabling Simple and Efficient Detection of SSR Markers using a Non-denaturing Polyacrylamide Gel

Published on: April 20, 2018

11.1K
Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images
11:49

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

9.6K

Area of Science:

  • Agricultural Science
  • Plant Pathology
  • Computer Vision

Background:

  • Stripe rust (Pst) causes significant wheat yield losses, necessitating effective control strategies.
  • Fungicide application is crucial for managing Pst outbreaks, but precise timing is key to optimize efficacy and minimize environmental impact.
  • Advanced monitoring tools are needed for high-throughput field phenotyping and early detection of Pst.

Purpose of the Study:

  • To develop and evaluate a deep learning-based image classifier for detecting Pst symptoms in winter wheat canopies.
  • To assess the performance of a deep residual neural network (ResNet) for automated Pst identification.
  • To explore the potential of camera-based sensors for early Pst outbreak detection and disease monitoring.

Main Methods:

  • A large image dataset was created using a standard RGB camera mounted on a platform (2m height) over inoculated and Pst-free winter wheat plots.
  • An image classifier was trained using a deep residual neural network (ResNet) on 224 × 224 px image patches.
  • The classifier's performance was evaluated at both patch and image levels, including early disease stages with low Pst prevalence.

Main Results:

  • The image classifier achieved 90% accuracy at the patch level.
  • At the image level, the classifier reached a total accuracy of 77%.
  • Early detection accuracy was 57% at 0.5% disease spread and 76% at 2-4% disease spread, demonstrating effectiveness in initial outbreak phases.

Conclusions:

  • Deep learning image classification shows high potential for accurate and early detection of stripe rust in wheat.
  • The developed classifier can be optimized for implementation in embedded systems for drones or vehicles, enabling rapid Pst outbreak mapping.
  • This technology can significantly improve disease monitoring and fungicide application strategies in wheat production.