WasteNet

The world’s largest dataset for waste.

About WasteNet

Our pioneering research has been developed in partnership with academics at leading universities to create WasteNet: the world’s largest dataset for waste.

It boasts over 3 million training images created by deep learning and computer vision, refined by weight and brand-level detection.

Waste Image Datasets

Using Recycleye Vision, our computer vision experts have analysed over 3 million images of waste items in MRFs (and counting!).

Collated by our expert team of machine learning engineers and academic research partners, these databases are at the heart of our image detection capabilities.

Waste taxonomy

The Recycleye waste taxonomy offers a global standard for waste classification, providing you with a common, clear language for market participants.

Research papers

View Papers

Single Shot 2D Image to 3D Model

This research consists of 2 papers offering differing reconstruction approaches to obtain high accuracy inferences of 3D structures with textures from 2D single shot images….

View Papers

Deep Learning: Unsupervised Domain Adaptation

The goal of this WasteNet series is to engineer a Deep Learning model that will focus on UDA for the instance segmentation task. As such, there are only two other approaches that are addressing this. …

View Papers

An Application of Machine Learning for Brand-Level Waste Management

Computer vision for brand-level logo detection of waste in real-time was tested. The brand recognition of waste items can be used to increase the granularity of the waste characterisation, simultaneously providing information to improve mass measurements. …

View Papers

Recycleye Bin: A Human-in-the-Loop Approach to Computer Vision Waste Disposal

Studies have shown that the rate of recycling amongst individuals can be increased by correcting mistakes. …

View Papers

Instance Segmentation of Novel Objects in a Conveyer Setting

The advancements in deep learning have enabled rapid growth of computer vision capabilities. However, in order to achieve successful results, it requires a heavy reliance on the availability of large labelled datasets….

View Papers

A Generative Adversarial Network (GAN) to Generate Transparent Objects

The research conducted uses a technique which creates synthetic data using a general adversarial network to generate transparent objects….

View Papers

Synthetic Generation of Augmented 3D Data for Waste Classification

Machine learning techniques have demonstrated super-human abilities that are necessary towards improving the recycling infrastructure. …

Waste Industry

View

Modelling of a modern MRF

Paloma’s paper has a dual focus on two of the challenges faced by MRFs today: The challenges associated with efficiency, waste composition variation and waste sampling methods….

View

Decentralised and Digitised Mini Material Recovery Facilities

This research explores the disruption of centralised waste facilities to accommodate a decentralised model, known as the mini-MRF, that is capable of extracting more value out of waste streams….

View

Regulated Bans in Waste Management

Amandine looks at how we can form healthier consumer habits and increased recycling rates by enforcing regulations around complex materials….