Real-time Recyclable Waste Detection Using YOLOv8 for Reverse Vending Machines

Abstract

Increasing challenges in waste management necessitate optimizing the efficiency of recycling systems. Reverse Vending Machines (RVMs) offer a promising solution by incentivizing recycling through user rewards. However, inaccurate waste detection methods hinder the effectiveness of RVMs. This study explores the potential of the YOLOv8 deep learning algorithm to enhance real-time waste classification accuracy in RVMs. We propose a YOLOv8-based framework for real-time detection of seven key recyclable materials. The model is trained on a combined dataset comprising the public TrashNet dataset and a study-specific dataset tailored to materials and variations encountered in RVMs. Performance evaluation metrics include F1-score, precision, recall, and PR curves.Results demonstrate the superior performance of the YOLOv8-based approach compared to other popular deep learning algorithms, including YOLOv5, YOLOv7, and YOLOv9. The YOLOv8 model achieves an accuracy rate of over 97%, significantly outperforming other algorithms. This improvement translates into enhanced recycling efficiency and reduced misclassification errors in RVMs. This research contributes to the development of more sustainable waste management systems by improving the efficiency and accuracy of RVMs. The YOLOv8-based framework presents a promising solution for real-time waste detection in RVMs, paving the way for more effective recycling practices and reduced environmental impact.