ML2 WCN UKM Computer Vision Project

UKM WCN

Updated 2 months ago

605

views

45

downloads
Classes (9)
Bottle Cap
Food Foam Container
Food Wrapper
Other Bottle
Plastic Bag
Plastic Clear Bottle
Plastic Cup
Plastic Food Container
Plastic Lid

Metrics

Try This Model
Drop an image or
Description

ML2: Machine Learning for Mitigating Litter

This project, designed by Mushfiqur Rahman Saad, a postgraduate student at Universiti Kebangsaan Malaysia and a researcher at the Wireless Research Lab, leverages machine learning to address the global plastic waste problem.

Using a citizen science approach, over 8,000 images were collected and used to train the first robust plastic waste detection model tailored to the unique environmental conditions of developing regions. The images feature diverse urban and natural landscapes, with plastic waste classes defined by their specific characteristics, such as "Clear Plastic Bottle."

As an entirely open-source initiative, ML2 is designed for replication and reuse, empowering communities and researchers to enhance plastic waste monitoring and auditing. By working together, this project aims to contribute meaningfully to solving the plastic waste crisis. If you'd like to know more about use cases, webapp examples feel free to reach out to me mushfiqur.my@gmail.com

Use This Trained Model

Try it in your browser, or deploy via our Hosted Inference API and other deployment methods.

Cite This Project

LICENSE
CC BY 4.0

If you use this dataset in a research paper, please cite it using the following BibTeX:

                        @misc{
                            ml2-wcn-ukm_dataset,
                            title = { ML2 WCN UKM Dataset },
                            type = { Open Source Dataset },
                            author = { UKM WCN },
                            howpublished = { \url{ https://universe.roboflow.com/ukm-wcn/ml2-wcn-ukm } },
                            url = { https://universe.roboflow.com/ukm-wcn/ml2-wcn-ukm },
                            journal = { Roboflow Universe },
                            publisher = { Roboflow },
                            year = { 2025 },
                            month = { jan },
                            note = { visited on 2025-03-28 },
                            }
                        
                    

Similar Projects

See More