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 Experiment Videos

An end-to-end detection and classification model for tea leaf grading in complex orchard environments.

Wencheng Hong1,2, Tao Wang1, Weiwei Zu1

  • 1School of Information Engineering, Huzhou University, Huzhou, China.

Frontiers in Plant Science
|June 22, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Light Acquisition02:16

Light Acquisition

In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.

You might also read

Related Articles

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

Sort by
Same author

The ocular surface consequences of lacrimal gland loss are life-stage dependent.

The ocular surface·2026
Same author

A chromosomal-level genome assembly of Batocera lineolata Chevrolat, 1852 (Coleoptera: Cerambycidae).

Scientific data·2026
Same author

The contribution rate of stem-leaf and root of alfalfa (<i>Medicago sativa L.</i>) with diverse spatial distribution patterns to sediment and runoff reduction on the Loess Plateau.

Frontiers in plant science·2026
Same author

Adaptive Cavity-Enabled Crystalline Chirality in Nanocarbon Cages.

Angewandte Chemie (International ed. in English)·2026
Same author

Effective refractive error coverage and vision impairment among schoolchildren in Xinjiang, China.

The British journal of ophthalmology·2026
Same author

Design of Unattended Rain and Snow Protection Device for Total Station Based on D-S Evidence Fusion.

Sensors (Basel, Switzerland)·2026

This study introduces Tea-DETR, a robust model for automatic tea grading in complex field conditions. It achieves high accuracy with fewer parameters, improving real-time detection for tea quality assessment.

Area of Science:

  • Computer Vision
  • Agricultural Technology
  • Machine Learning

Background:

  • Existing automatic tea-grade determination models struggle with feature robustness and background interference in open-field settings.
  • There's a need for lightweight yet accurate models for real-time tea quality assessment.

Purpose of the Study:

  • To develop an improved detection model, Tea-DETR, for automatic tea-grade determination in complex open-air tea gardens.
  • To enhance feature representation and attention allocation for better accuracy and efficiency.

Main Methods:

  • Proposed Tea-DETR based on the RT-DETR detection paradigm, featuring backbone optimization and feature interaction enhancement.
  • Developed a lightweight backbone module to improve long-range dependency modeling and background interference suppression.
Keywords:
RT-DETRfeature enhancementlightweight networkobject detectionopen-field tea gardentea grade determination

Related Experiment Videos

  • Implemented an efficient attention-enhancement mechanism for adaptive focus on critical target regions.

    • Main Results:

    • Tea-DETR achieved 92.2% accuracy and 82.0% mAP@0.5 with 14.65M parameters, a 26.8% reduction from the baseline.
    • Demonstrated improved convergence stability and enhanced ability to distinguish subtle semantic differences among tea grades.
    • Effectively alleviated ambiguous discrimination under complex backgrounds.

    Conclusions:

    • The proposed method enhances fine-grained feature capture for small tea-leaf targets in open-field environments.
    • Tea-DETR provides a robust solution for real-time, non-destructive automatic tea-grade determination.
    • Maintains real-time inference efficiency for practical field applications.