Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Effects of aluminate flocculant on turion germination and seedling growth of Potamogeton crispus.

Aquatic toxicology (Amsterdam, Netherlands)·2017

Same author

Folate-conjugated amphiphilic block copolymer micelle for targeted and redox-responsive delivery of doxorubicin.

Journal of biomaterials science. Polymer edition·2017

Same author

Survival of the fittest: Cancer challenges T cell metabolism.

Cancer letters·2017

Same author

EEG-based emotion estimation using adaptive tracking of discriminative frequency components.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2017

Same author

Two new stilbenoids from aerial parts of Flickingeria fimbriata.

Journal of Asian natural products research·2017

Same author

Enhancing performance of P300-Speller under mental workload by incorporating dual-task data during classifier training.

Computer methods and programs in biomedicine·2017

Same journal

Machine-learning-assisted comparative analysis of rice growth and yield formation in field and plant factory systems.

Frontiers in plant science·2026

Same journal

TomatoweedDet: a real-field multi-class weed detection dataset and YOLO benchmark for tomato production systems.

Frontiers in plant science·2026

Same journal

Genomic advances in orphan and underutilized Brassicaceae crops and their wild relatives.

Frontiers in plant science·2026

Same journal

Delayed sowing limits grain number per spike in wheat by restricting young spike differentiation through reduced photothermal resources.

Frontiers in plant science·2026

Same journal

Deterministic assembly and centralized networks define the <i>Pinus massoniana</i> rhizosphere mycobiota.

Frontiers in plant science·2026

Same journal

Cover cropping enhances fruit quality in protected citrus cultivation by modulating rhizosphere microbiome and iron availability.

Frontiers in plant science·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jun 15, 2025

Study on the Metabolism of Six Systemic Insecticides in a Newly Established Cell Suspension Culture Derived from Tea Camellia Sinensis L. Leaves

Study on the Metabolism of Six Systemic Insecticides in a Newly Established Cell Suspension Culture Derived from Tea Camellia Sinensis L. Leaves

Published on: June 15, 2019

TP-Transfiner: high-quality segmentation network for tea pest.

Ruizhao Wu¹, Feng He^1,2, Ziyang Rong^1,2

¹College of Informatics, Huazhong Agricultural University, Wuhan, China.

Frontiers in Plant Science

|August 28, 2024

Summary

This summary is machine-generated.

This study introduces TeaPest-Transfiner (TP-Transfiner), an advanced AI model for detecting and segmenting tea pests, improving accuracy in challenging dense and mimicry scenarios. The novel framework enhances feature extraction and achieves state-of-the-art performance, aiding efficient tea production quality control.

Keywords:

Mask Transfiner attention mechanism dense and mimicry scenarios instance segmentation tea pest

More Related Videos

Remote Sensing Evaluation of Two-spotted Spider Mite Damage on Greenhouse Cotton

Remote Sensing Evaluation of Two-spotted Spider Mite Damage on Greenhouse Cotton

Published on: April 28, 2017

Isolation and Selection of Entomopathogenic Fungi from Soil Samples and Evaluation of Fungal Virulence against Insect Pests

Isolation and Selection of Entomopathogenic Fungi from Soil Samples and Evaluation of Fungal Virulence against Insect Pests

Published on: September 28, 2021

Related Experiment Videos

Last Updated: Jun 15, 2025

Study on the Metabolism of Six Systemic Insecticides in a Newly Established Cell Suspension Culture Derived from Tea Camellia Sinensis L. Leaves

Study on the Metabolism of Six Systemic Insecticides in a Newly Established Cell Suspension Culture Derived from Tea Camellia Sinensis L. Leaves

Published on: June 15, 2019

Remote Sensing Evaluation of Two-spotted Spider Mite Damage on Greenhouse Cotton

Remote Sensing Evaluation of Two-spotted Spider Mite Damage on Greenhouse Cotton

Published on: April 28, 2017

Isolation and Selection of Entomopathogenic Fungi from Soil Samples and Evaluation of Fungal Virulence against Insect Pests

Isolation and Selection of Entomopathogenic Fungi from Soil Samples and Evaluation of Fungal Virulence against Insect Pests

Published on: September 28, 2021

Area of Science:

Agricultural Science
Computer Vision
Artificial Intelligence

Background:

Traditional Convolutional Neural Network (CNN) methods struggle with accurate and efficient tea pest detection, especially in dense or mimicry scenarios, due to insufficient feature extraction.
Prompt detection and control of tea pests are vital for maintaining the quality of tea production.

Purpose of the Study:

To develop an end-to-end framework, TeaPest-Transfiner (TP-Transfiner), for improved tea pest detection and segmentation, specifically addressing challenges in dense and mimicry environments.
To enhance feature extraction capabilities beyond traditional CNN modules for greater accuracy and efficiency in pest identification.

Main Methods:

Integration of a deformable attention block, combining deformable convolution and self-attention, to improve feature extraction.
Enhancement of the Feature Pyramid Network (FPN) architecture with a feature-aligned pyramid network (FaPN).
Utilization of focal loss for sample balancing during training and dataset-specific parameter adaptation, alongside the creation of the TeaPestDataset with 1,752 images of 29 tea pest species.

Main Results:

The TP-Transfiner model achieved state-of-the-art performance on the TeaPestDataset, with a detection precision (AP50) of 87.211% and segmentation performance of 87.381%.
Demonstrated a significant improvement in segmentation average precision (mAP) by 9.4% compared to Mask R-CNN.
Achieved a 30% reduction in model size compared to Mask R-CNN while maintaining fast inference speeds and a compact model, indicating practical applicability.

Conclusions:

The proposed TP-Transfiner framework effectively addresses the limitations of traditional methods in detecting and segmenting tea pests in complex scenarios.
The model's enhanced feature extraction, optimized architecture, and dataset-specific training contribute to its superior performance and practical potential for real-world tea garden pest control.