Image Segmentation and Classification of E-waste for Training Robots for Waste Segregation

TL;DR

This paper develops a machine learning approach using YOLOv11 and Mask-RCNN models to classify electronic waste, enabling robots to perform automated waste segregation with high accuracy.

Contribution

It introduces a custom dataset of electronic waste images and demonstrates real-time object detection and classification for robotic waste segregation.

Findings

YOLOv11 achieved 70 mAP in real-time

Mask-RCNN achieved 41 mAP

Models can be integrated with robots for waste segregation

Abstract

Industry partners provided a problem statement that involves classifying electronic waste using machine learning models that will be used by pick-and-place robots for waste segregation. This was achieved by taking common electronic waste items, such as a mouse and charger, unsoldering them, and taking pictures to create a custom dataset. Then state-of-the art YOLOv11 model was trained and run to achieve 70 mAP in real-time. Mask-RCNN model was also trained and achieved 41 mAP. The model can be integrated with pick-and-place robots to perform segregation of e-waste.