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

Light Acquisition

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.

Plant Breeding and Biotechnology

Plant Breeding and Biotechnology

Crop cultivation has a long history in human civilization, with records showing the cultivation of cereal plants beginning at around 8000 BC. This early plant breeding was developed primarily to provide a steady supply of food.

Transformers in Distribution System

Transformers in Distribution System

Transformers in distribution systems can be broadly categorized into distribution substation transformers and other distribution transformers. They are crucial for stepping down high transmission voltages to levels suitable for distribution and end-user applications.
Distribution substation transformers come in various ratings and typically use mineral oil for insulation and cooling. To prevent moisture and air from entering the oil, some transformers use an inert gas like nitrogen to fill the...

Transgenic Plants

Transgenic Plants

Recombinant DNA technology called transgenesis is often used to add a foreign gene or remove a detrimental gene from an organism. Such genetically modified organisms are called transgenic organisms.
The first-ever transgenic plant was a tobacco plant developed in 1983 that showed resistance against the tobacco mosaic virus. Since then, many transgenic plants have been developed and commercialized for improving the agricultural, ornamental, and horticultural value of a crop plant. Transgenic...

You might also read

Related Articles

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

Sort by

Same author

Deep Learning Model for Predicting Lung Adenocarcinoma Recurrence from Whole Slide Images.

Cancers·2024

Same author

Transforming Poultry Farming: A Pyramid Vision Transformer Approach for Accurate Chicken Counting in Smart Farm Environments.

Sensors (Basel, Switzerland)·2024

Same author

A Review on Recent Deep Learning-Based Semantic Segmentation for Urban Greenness Measurement.

Sensors (Basel, Switzerland)·2024

Same author

Open set classification of sound event.

Scientific reports·2024

Same author

Detection of unknown strawberry diseases based on OpenMatch and two-head network for continual learning.

Frontiers in plant science·2022

Same author

Deep Metric Learning-Based Strawberry Disease Detection With Unknowns.

Frontiers in plant science·2022

Search research articles

Related Experiment Video

Updated: Aug 15, 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

Transformer-Based Weed Segmentation for Grass Management.

Kan Jiang¹, Usman Afzaal², Joonwhoan Lee¹

¹Artificial Intelligence Lab, Department of Computer Science and Engineering, Jeonbuk National University, Jeonju 54896, Republic of Korea.

Sensors (Basel, Switzerland)

|January 8, 2023

Summary

Deep learning models, specifically Transformer architectures like SegFormer, show promise for accurate weed detection and mapping in agriculture. This technology aids in automated weed control, improving crop yield and field aesthetics.

Keywords:

SegFormer Segmenter Swin Transformer Transformer semantic segmentation weed detection

More Related Videos

Protocols for Quantifying Transferable Pesticide Residues in Turfgrass Systems

Protocols for Quantifying Transferable Pesticide Residues in Turfgrass Systems

Published on: March 15, 2017

A PCR-based Genotyping Method to Distinguish Between Wild-type and Ornamental Varieties of Imperata cylindrica

A PCR-based Genotyping Method to Distinguish Between Wild-type and Ornamental Varieties of Imperata cylindrica

Published on: February 20, 2012

Related Experiment Videos

Last Updated: Aug 15, 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

Protocols for Quantifying Transferable Pesticide Residues in Turfgrass Systems

Protocols for Quantifying Transferable Pesticide Residues in Turfgrass Systems

Published on: March 15, 2017

A PCR-based Genotyping Method to Distinguish Between Wild-type and Ornamental Varieties of Imperata cylindrica

A PCR-based Genotyping Method to Distinguish Between Wild-type and Ornamental Varieties of Imperata cylindrica

Published on: February 20, 2012

Area of Science:

Agricultural Science
Computer Vision
Artificial Intelligence

Background:

Weed control is critical for crop cultivation and turf management, as weeds compete for resources, reduce yield, and contaminate food.
Effective weed detection and mapping are essential for efficient agricultural practices and maintaining field aesthetics.
Deep learning (DL) offers advanced solutions for object recognition and localization in images, with significant potential in agriculture.

Purpose of the Study:

To investigate the application of attention-based Transformer models for weed detection and localization.
To develop and evaluate deep learning-based semantic segmentation models for identifying 10 different weed classes.
To assess the performance of Swin Transformer, SegFormer, and Segmenter architectures on a custom weed dataset.

Main Methods:

A dataset of 1006 images across 10 weed classes was curated and augmented for training deep learning models.
Three Transformer architectures (Swin Transformer, SegFormer, Segmenter) were implemented for semantic segmentation tasks.
Model performance was evaluated using Mean Accuracy (mAcc) and Mean Intersection of Union (mIoU) metrics.

Main Results:

SegFormer achieved the highest performance with a Mean Accuracy (mAcc) of 75.18% and Mean Intersection of Union (mIoU) of 65.74%.
SegFormer demonstrated superior performance compared to Swin Transformer and Segmenter.
SegFormer was also the most computationally efficient model, with only 3.7 million parameters.

Conclusions:

Transformer models, particularly SegFormer, are effective for semantic segmentation of weeds, enabling precise localization.
The developed models have potential applications in automated weed control systems and robots.
This research contributes to advancing precision agriculture through AI-driven weed management solutions.