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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Laboratory evaluation of commercially available and naturally occurring predatory mites against Thrips parvispinus (Thysanoptera: Thripidae).

Experimental & applied acarology·2026
Same author

Towards a non-Fourier event-based opto-electronic convolution accelerator.

Optics express·2026
Same author

2D-to-3D Image Reconstruction in Agriculture: A Review of Methods, Challenges, and AI-Driven Opportunities.

Sensors (Basel, Switzerland)·2026
Same author

AI-Driven Firmness Prediction of Kiwifruit Using Image-Based Vibration Response Analysis.

Sensors (Basel, Switzerland)·2025
Same author

A Novel Hybrid Technique for Detecting and Classifying Hyperspectral Images of Tomato Fungal Diseases Based on Deep Feature Extraction and Manhattan Distance.

Sensors (Basel, Switzerland)·2025
Same author

Estimation of Strawberry Canopy Volume in Unmanned Aerial Vehicle RGB Imagery Using an Object Detection-Based Convolutional Neural Network.

Sensors (Basel, Switzerland)·2024

Related Experiment Video

Updated: Mar 29, 2026

Analysis of Multidimensional Microscopy Data Using Cell-ACDC
06:17

Analysis of Multidimensional Microscopy Data Using Cell-ACDC

Published on: November 7, 2025

711

RD-GuideNet: A Depth-Guided Framework for Robust Detection, Segmentation, and Temporal Tracking of White Button

Namrata Dutt1, Daeun Choi1, Yiannis Ampatzidis2

  • 1Department of Agricultural and Biological Engineering, Gulf Coast Research and Education Center, Institute of Food and Agricultural Sciences, University of Florida, Wimauma, FL 33598, USA.

Sensors (Basel, Switzerland)
|March 28, 2026
PubMed
Summary

A new computer vision system, RD-GuideNet, improves automated mushroom harvesting by accurately detecting and tracking white button mushrooms using RGB and depth images. This technology addresses labor shortages in mushroom farming.

Keywords:
3D shape analysisRGB-Dautomated harvestingdepth fusiondepth-guided computer visioninstance segmentationprecision agriculturetemporal tracking

More Related Videos

Automatic Identification of Dendritic Branches and their Orientation
06:08

Automatic Identification of Dendritic Branches and their Orientation

Published on: September 17, 2021

2.4K
Acquiring Fluorescence Time-lapse Movies of Budding Yeast and Analyzing Single-cell Dynamics using GRAFTS
17:01

Acquiring Fluorescence Time-lapse Movies of Budding Yeast and Analyzing Single-cell Dynamics using GRAFTS

Published on: July 18, 2013

13.4K

Related Experiment Videos

Last Updated: Mar 29, 2026

Analysis of Multidimensional Microscopy Data Using Cell-ACDC
06:17

Analysis of Multidimensional Microscopy Data Using Cell-ACDC

Published on: November 7, 2025

711
Automatic Identification of Dendritic Branches and their Orientation
06:08

Automatic Identification of Dendritic Branches and their Orientation

Published on: September 17, 2021

2.4K
Acquiring Fluorescence Time-lapse Movies of Budding Yeast and Analyzing Single-cell Dynamics using GRAFTS
17:01

Acquiring Fluorescence Time-lapse Movies of Budding Yeast and Analyzing Single-cell Dynamics using GRAFTS

Published on: July 18, 2013

13.4K

Area of Science:

  • Agricultural Engineering
  • Computer Vision
  • Robotics

Background:

  • Mushroom farms face significant labor shortages, particularly for harvesting white button mushrooms (Agaricus bisporus), which requires skilled manual labor.
  • Timely harvesting is crucial for mushroom quality and yield, making automation a key area for research.

Purpose of the Study:

  • To develop a depth-guided computer vision framework for automated mushroom detection, segmentation, and tracking.
  • To create a novel image-processing algorithm (RD-GuideNet) integrating RGB and depth data for enhanced mushroom perception.
  • To evaluate RD-GuideNet's performance against state-of-the-art models (YOLOv8, YOLOv11) for segmentation and tracking accuracy.

Main Methods:

  • Development of RD-GuideNet, a novel algorithm combining RGB and depth image processing.
  • Implementation of a custom depth-guided tracking algorithm for maintaining mushroom identity across video frames.
  • Comparative analysis of RD-GuideNet against YOLOv8 and YOLOv11 using F1-scores for segmentation and tracking consistency metrics.

Main Results:

  • RD-GuideNet achieved a superior F1-score of 0.93 for mushroom segmentation, surpassing YOLOv8 (0.88) and YOLOv11 (0.86).
  • The system produced sharper, more accurate mushroom cap boundaries compared to existing models.
  • Tracking consistency reached 92.7%, demonstrating robust performance in dense mushroom beds, though slightly lower than YOLOv8/YOLOv11.

Conclusions:

  • Depth-based geometric reasoning and deep learning offer complementary strengths for precise perception in agricultural automation.
  • RD-GuideNet provides a strong foundation for developing selective and timely robotic harvesting systems for mushrooms.
  • Future research will explore hybrid frameworks combining deep learning and geometric approaches for further improvements in detection reliability and shape fidelity.