Performance of YOLOv5 Object Detection for Waste Type Classification: A Case Study on Domestic Inorganic Waste

DOI

10.2991/978-94-6463-768-7_11How to use a DOI?

Keywords

YOLO; plastic waste classification; deep learning; convolutional neural networks; waste management; sustainable environment

Abstract

To address the issue of environmental pollution caused by domestic inorganic waste, a technology capable of efficiently classifying waste types with high accuracy is needed. This study aims to explore the use of YOLO (You Only Look Once), an algorithm based on deep learning using convolutional neural networks (CNN), for classifying types of domestic inorganic waste. YOLO has the ability to detect objects in real-time with high accuracy. In this research, the YOLO model was trained using a dataset of images containing various types of waste such as PET bottles, plastic bags, plastic packaging, glass bottles, cans, and different kinds of paper waste. The dataset consists of 1869 images of domestic inorganic waste, including household waste in controlled environments. The system is divided into several parts. The first part involves building a smart trash system using a Jetson Nano board for inference, connected to a camera and a stepper motor rail slider. The second part focuses on the model for classifying types of domestic waste using the YOLOv5 model. Experimental results show that YOLOv5 is capable of classifying waste types with an accuracy of up to 98% for mAP@0.5, 97.3% for precision, 96.5% for recall, and a detection speed of 29 fps on the Jetson board. This study demonstrates the effectiveness of YOLOv5 and provides a strong foundation for the development of smart and efficient domestic inorganic waste management systems.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Erwin Ardias Saputa
AU  - Martdiansyah Martdiansyah
AU  - Muhammad Aristo Indrajaya
AU  - Muhammad Dwiki Bayu Aristo
AU  - Andi Iin Nindy Karlinda Kadir
AU  - Alricha
PY  - 2025
DA  - 2025/07/07
TI  - Performance of YOLOv5 Object Detection for Waste Type Classification: A Case Study on Domestic Inorganic Waste
BT  - Proceedings of the 3rd International Conference on Science in Engineering and Technology (ICOSIET 2024)
PB  - Atlantis Press
SP  - 88
EP  - 102
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-768-7_11
DO  - 10.2991/978-94-6463-768-7_11
ID  - Saputa2025
ER  -