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

Search research articles

Related Experiment Video

Updated: Sep 26, 2025

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

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

Published on: February 9, 2024

Tea Chrysanthemum Detection by Leveraging Generative Adversarial Networks and Edge Computing.

Chao Qi¹, Junfeng Gao², Kunjie Chen¹

¹College of Engineering, Nanjing Agricultural University, Nanjing, China.

Frontiers in Plant Science

|April 25, 2022

Summary

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

Evolution of pre- and post-operative balance characteristics in patients undergoing anterior cruciate ligament reconstruction: implications for rehabilitation.

Frontiers in bioengineering and biotechnology·2026

Same author

The Pick fold in tau filaments from human MAPT mutants.

Acta neuropathologica·2026

Same author

Carbon-to-nitrogen stoichiometry shapes divergent intracellular and extracellular antibiotic resistance gene fates through a dissolved organic matter-extracellular polymeric substance-mobile genetic element cascade in cyanobacteria-bacteria co-cultures.

Water research·2026

Same author

Zinc-Doped Calcium Phosphate Nanoagonists Amplifies cGAS-STING Signaling for Boosting Pyroptosis-Induced Cancer Immunotherapy.

Journal of functional biomaterials·2026

Same author

A proposed method for locating the tibial attachment for medial patellotibial ligament reconstruction: A cadaveric anatomical and imaging study.

Journal of experimental orthopaedics·2026

Same author

Dynamic tensile mechanical properties and energy dissipation characteristics of sandstone with varying degrees of initial damage.

Scientific reports·2026

Generating high-resolution datasets for tea chrysanthemum detection is challenging. A novel tea chrysanthemum-generative adversarial network (TC-GAN) was developed, achieving 90.09% average precision for selective harvesting robots.

Area of Science:

Agricultural Engineering
Computer Vision
Deep Learning

Background:

High-resolution datasets are essential for deep learning-based tea chrysanthemum detection.
Developing selective harvesting robots requires accurate object detection in complex environments.
Generating high-resolution datasets for tea chrysanthemums in unstructured settings presents a significant challenge.

Purpose of the Study:

To propose a novel generative adversarial network (GAN) for generating high-resolution tea chrysanthemum datasets.
To address the challenge of creating detailed image data for agricultural robotics.
To improve the performance of object detection models for selective harvesting.

Main Methods:

Designed a novel tea chrysanthemum-generative adversarial network (TC-GAN).

Keywords:

NVIDIA Jetson TX2 deep learning edge computing generative adversarial network tea chrysanthemum

More Related Videos

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

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

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Sep 26, 2025

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

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

Published on: February 9, 2024

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

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

Published on: December 15, 2023

Implemented a non-linear mapping network for feature untangling.

Utilized a customized regularization method for fine-grained image detail control.

Employed a gradient diversion design with multi-scale feature extraction for training optimization.

Main Results:

The TC-GAN achieved an optimal average precision (AP) of 90.09% using generated 512x512 images.
The generated dataset significantly improved the performance of the TC-YOLO object detection model.
The detection model achieved a 0.1s inference time when deployed on an NVIDIA Jetson TX2 platform.

Conclusions:

The proposed TC-GAN effectively generates high-resolution tea chrysanthemum datasets.
This approach enhances the accuracy of object detection for selective harvesting robots.
The developed system shows potential for real-world deployment in agricultural automation.