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

You might also read

Related Articles

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

Sort by

Same author

Epoxy Composites Reinforced with Sol-Gel Synthesized Alumina-Silica, Alumina, and Natural Silica Fillers: Comparative Mechanical Performance.

Gels (Basel, Switzerland)·2026

Same author

Editorial: Biomechanics of aging: advances in exercise and intervention strategies for older adult wellness.

Frontiers in public health·2026

Same author

A systematic review of machine learning approaches to bovine tuberculosis in cattle.

Research in veterinary science·2026

Same author

Biomineralization of Glucose Oxidase from <i>Aspergillus niger</i> in ZIF-zni for Enhanced Biocatalytic Performance.

Bioengineering (Basel, Switzerland)·2026

Same author

Inverse optimal control of muscle force sharing during pathological gait.

Journal of biomechanics·2026

Same author

The Impact of Energy and Protein Levels on Yellow Mealworm Growth and Chemical Composition.

Insects·2026

Same journal

A tri-axis optomechanical accelerometer with plasmonic MIM waveguide and structural direction-dependent optical signatures.

Scientific reports·2026

Same journal

Holographic leaky-wave antennas with independently controlled multiple counter-rotating vortex beams.

Scientific reports·2026

Same journal

Differential associations of longitudinal hearing and vision trajectories with dementia and mild cognitive impairment in older adults.

Scientific reports·2026

Same journal

Abdominal obesity and leisure-time sedentary behavior in relation to gastroesophageal reflux disease risk: a prospective cohort study from the UK Biobank.

Scientific reports·2026

Same journal

Effect of nitrogen-rich COF incorporation on the structure and separation performance of polyamide nanofiltration membranes.

Scientific reports·2026

Same journal

Withanolide A inhibits hIAPP aggregation: An In silico, biophysical, and drosophila-based In vivo validation.

Scientific reports·2026

See all related articles

Search research articles

Related Experiment Video

Updated: May 30, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Versatile waste sorting in small batch and flexible manufacturing industries using deep learning techniques.

Arso M Vukicevic^1,2, Milos Petrovic³, Nebojsa Jurisevic⁴

¹Faculty of Engineering, University of Kragujevac, Sestre Janjic 6, Kragujevac, Serbia. arso_kg@yahoo.com.

Scientific Reports

|January 30, 2025

Summary

This summary is machine-generated.

This study uses the Segment Anything Model (SAM) for automated waste sorting, enabling flexible workstations to adapt quickly to new waste types with high accuracy. This approach reduces costs and speeds up deployment in manufacturing.

Keywords:

Artificial Intelligence Deep Learning Manufacturing Recycling Waste Sorting

More Related Videos

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories

Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories

Published on: July 10, 2019

Related Experiment Videos

Last Updated: May 30, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories

Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories

Published on: July 10, 2019

Area of Science:

Robotics and Automation
Artificial Intelligence
Environmental Science

Background:

Modern manufacturing requires flexible automated systems for LEAN and small batch production.
Automated waste sorting needs to adapt to diverse and changing waste streams.

Purpose of the Study:

To evaluate the Segment Anything Model (SAM) family for robotic waste sorting.
To develop a versatile, two-step procedure for automated waste object separation and classification.

Main Methods:

Utilized SAM architectures (SAM, FastSAM, MobileSAMv2, EfficientSAM) for waste object extraction.
Employed classification architectures (MobileNetV2, VGG19, Dense-Net, Squeeze-Net, ResNet, Inception-v3) for sorting.
Developed a two-step pipeline simplifying adaptation to new waste types.

Main Results:

Achieved high accuracy (86-97%) in sorting diverse waste streams (floating, municipal, e-waste, smart bins).
Demonstrated robust performance using MobileNetV2 with SAM and FastSAM.
Validated the pipeline's effectiveness across multiple use cases.

Conclusions:

The SAM-based approach significantly reduces the need for custom algorithms, lowering costs and development time.
This method enhances robotic waste sorting efficiency, productivity, and accuracy.
The proposed procedure offers a scalable solution for adaptable waste management in manufacturing and recycling.