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.

You might also read

Related Articles

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

Sort by

Same author

Exploiting 2D Neural Network Frameworks for 3D Segmentation Through Depth Map Analytics of Harvested Wild Blueberries (<i>Vaccinium angustifolium</i> Ait.).

Journal of imaging·2024

See all related articles

Search research articles

Related Experiment Video

Updated: Jan 9, 2026

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

Published on: August 23, 2017

Enhanced Image Annotation in Wild Blueberry (Vaccinium angustifolium Ait.) Fields Using Sequential Zero-Shot

Connor C Mullins^1,2, Travis J Esau^1,2, Riley Johnstone^1,2

¹Department of Engineering, Faculty of Agriculture, Dalhousie University, Truro, NS B2N 5E3, Canada.

Sensors (Basel, Switzerland)

|December 11, 2025

Summary

This study introduces an automated pipeline for annotating agricultural images, significantly improving precision agriculture. The system efficiently detects ripe berries, buds, grass, and diseases, aiding data-driven crop management.

Keywords:

Grounding DINO SAM2 YOLO-world deep learning grounded SAM

More Related Videos

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Related Experiment Videos

Last Updated: Jan 9, 2026

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

Published on: August 23, 2017

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Area of Science:

Agricultural Science
Computer Vision
Machine Learning

Background:

Manual image annotation is a bottleneck for data-driven precision agriculture.
Automated annotation is crucial for tasks like ripeness detection, disease identification, and growth monitoring.
Current methods are labor-intensive and impractical for large-scale farming.

Purpose of the Study:

To evaluate an automated annotation pipeline integrating zero-shot detection models (Grounding DINO, YOLO-World) with Segment Anything Model version 2 (SAM2).
To assess the pipeline's effectiveness in detecting and segmenting key agricultural elements in wild blueberry systems.
To compare the performance and processing times of different model configurations.

Main Methods:

Integration of Grounding DINO and YOLO-World with SAM2 for image annotation.
Testing on detecting ripe wild blueberries, buds, hair fescue, and red leaf disease.
Evaluation of mean Intersection over Union (mIoU) for accuracy and processing times for efficiency.

Main Results:

Grounding DINO outperformed YOLO-World across tested categories.
Specific model pairings (Swin-T/Swin-B with SAM2-Large/Small) achieved high mIoU scores for different targets.
Faster processing times were observed with smaller SAM2 versions (Tiny, Small, Base), though SAM2-Large offered higher accuracy.

Conclusions:

The developed pipeline offers a scalable solution for rapid and accurate agricultural image annotation.
Optimized model selection balances accuracy and processing speed for practical applications.
Future work should explore broader applications across diverse cropping systems and crops.