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

Aggregates Classification01:29

Aggregates Classification

956
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
956

You might also read

Related Articles

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

Sort by
Same author

Mechanisms of Ibuprofen Retention and Release in Dual-Responsive P(NIPAM-co-AAc) Nanogels: Coupling of Mesh Sieving and Affinity Switching.

Gels (Basel, Switzerland)·2026
Same author

Inspired by the Hydrophilic Nature of Squid Muscles: Constructing High-Performance Anti-fatigue Polymeric Hydrogel Artificial Muscles Using Energy Dissipation.

The journal of physical chemistry. B·2026
Same author

Encapsulation of Menthol in Bimodal Mesoporous Silica via Normal-Temperature and Alcohol-Thermal Loading Methods for Achieving Sustained Releasing Performances.

Nanomaterials (Basel, Switzerland)·2026
Same author

Editorial: Advances in intelligence or nanomedicine-based theranostics for cancers.

Frontiers in oncology·2026
Same author

Efficient Encapsulation and Sustained Release of Linalyl Acetate Using Fractal Bimodal Mesoporous Silica.

Nanomaterials (Basel, Switzerland)·2026
Same author

Reduced Metal-Codoped TiO<sub>2</sub>/LSX Zeolite Catalysis: A Sustainable Solution for Crystal Violet Dye Degradation.

ACS omega·2026

Related Experiment Video

Updated: Jan 11, 2026

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.6K

Robust referring image segmentation for construction and demolition waste recognition.

Jun He1, Tao Jiang1, Sunyan Hong1

  • 1School of Information Engineering, Kunming University, Kunming 650214, China; Yunnan Key Laboratory of Intelligent Logistics Equipment and Systems, Kunming 650214, China.

Waste Management (New York, N.Y.)
|November 18, 2025
PubMed
Summary

This study introduces RefSegformer-CDW, a robust system for automated Construction and Demolition Waste (CDW) sorting. It significantly improves accuracy by rejecting invalid commands, enhancing recycling efficiency.

Keywords:
Automated Waste SortingImage SegmentationLanguage-Vision FusionPrompt RobustnessWaste Management

More Related Videos

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

25.0K
Automated Analysis of C. elegans Fluorescence Images using SegElegans
06:27

Automated Analysis of C. elegans Fluorescence Images using SegElegans

Published on: October 10, 2025

550

Related Experiment Videos

Last Updated: Jan 11, 2026

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.6K
From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

25.0K
Automated Analysis of C. elegans Fluorescence Images using SegElegans
06:27

Automated Analysis of C. elegans Fluorescence Images using SegElegans

Published on: October 10, 2025

550

Area of Science:

  • Robotics and Automation
  • Computer Vision
  • Environmental Engineering

Background:

  • Automated sorting of Construction and Demolition Waste (CDW) is crucial for increasing recycling rates.
  • Current language-guided recognition systems (Referring Image Segmentation - RIS) lack robustness in dynamic industrial settings, leading to sorting errors.
  • Ambiguous operator instructions and misaligned visual cues hinder the practical deployment of intelligent CDW sorting.

Purpose of the Study:

  • To develop a robust recognition framework, RefSegformer-CDW, to enhance the reliability of automated CDW sorting.
  • To introduce a cross-modal verification mechanism for rejecting invalid commands and preventing sorting errors.
  • To create the Ref-CODD dataset, a benchmark for training and validating robust RIS systems with adversarial negative samples.

Main Methods:

  • Development of the RefSegformer-CDW architecture with an integrated cross-modal verification mechanism.
  • Creation of the Ref-CODD dataset, comprising real-world CDW imagery and adversarial negative samples simulating challenging scenarios.
  • Evaluation of the framework's performance using metrics such as mean Intersection over Union (mIoU) and overall Intersection over Union (oIoU).

Main Results:

  • RefSegformer-CDW achieved a mean Intersection over Union (mIoU) of 94.03% on the Ref-CODD dataset, outperforming state-of-the-art by 1.24%.
  • The framework demonstrated high stability under varying illumination, with only a 2.38 percentage point drop in mIoU between dark and normal lighting.
  • Robust performance was observed across diverse waste types, with an average oIoU of 93.90% on ten different CDW categories.

Conclusions:

  • RefSegformer-CDW offers a significant advancement in robust automated sorting for Construction and Demolition Waste.
  • The integrated cross-modal verification effectively prevents sorting errors caused by ambiguous or invalid operator commands.
  • The Ref-CODD dataset provides a valuable resource for future research in developing reliable language-guided segmentation systems for industrial waste management.