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 Experiment Videos

PortiK: A computer vision based solution for real-time automatic solid waste characterization - Application to an

Remi Cuingnet1, Yannik Ladegaillerie1, Jérôme Jossent1

  • 1Veolia Scientific & Technical Expertise Department, Maisons-Laffitte, France.

Waste Management (New York, N.Y.)
|July 23, 2022
PubMed
Summary

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

Generalization abilities of foundation models in waste classification.

Waste management (New York, N.Y.)·2025
Same author

Adipose Tissue Properties in Tumor-Bearing Breasts.

Frontiers in oncology·2020
Same author

TPF induction chemotherapy increases PD-L1 expression in tumour cells and immune cells in head and neck squamous cell carcinoma.

ESMO open·2018
Same author

IL-1β induces thymic stromal lymphopoietin and an atopic dermatitis-like phenotype in reconstructed healthy human epidermis.

The Journal of pathology·2017
Same author

Better understanding of water quality evolution in water distribution networks using data clustering.

Water research·2015
Same author

Multi-organ localization with cascaded global-to-local regression and shape prior.

Medical image analysis·2015

PortiK, an automated waste analysis solution, uses image analysis for real-time monitoring in material recovery facilities. This system accurately estimates the purity of recyclable streams, improving waste sorting efficiency.

Area of Science:

  • Waste Management
  • Computer Vision
  • Artificial Intelligence

Background:

  • Effective waste sorting is crucial for sustainable development but remains a significant challenge.
  • Material Recovery Facilities (MRFs) process municipal solid waste into valuable commodities.

Purpose of the Study:

  • To introduce PortiK, an automated system for real-time, non-intrusive waste analysis.
  • To improve operational efficiency and optimize processes in MRFs through accurate waste stream composition measurement.

Main Methods:

  • Development of an end-to-end solution integrating hardware specifications, data collection, and deep learning analysis.
  • Utilizing image analysis and object recognition for continuous waste stream monitoring.
  • Validation in an operational MRF environment, focusing on an aluminum can stream.
Keywords:
Computer visionDeep neural networkDeep-learningMRFMaterial recovery facilitiesSolid waste characterization

Related Experiment Videos

Main Results:

  • PortiK achieved 91.2% precision and 90.3% recall for aluminum can detection, with <1% underestimation.
  • Contaminant detection showed 80.2% precision and 78.4% recall, with 2.2% underestimation.
  • Purity estimation error reduced to ±7% within 5 minutes and ±5% within 8 hours.

Conclusions:

  • The PortiK system demonstrates feasibility and relevance for online quality control in MRFs.
  • Automated waste analysis significantly enhances the accuracy and efficiency of sorting recyclable materials.
  • The technology offers a pathway to optimize recycling processes and contribute to sustainable waste management.