| Issue |
EPJ Web Conf.
Volume 357, 2026
International Conference on Advanced Materials and Characterization (ICAMC 2025)
|
|
|---|---|---|
| Article Number | 01006 | |
| Number of page(s) | 10 | |
| Section | Energy & Engineering Materials | |
| DOI | https://doi.org/10.1051/epjconf/202635701006 | |
| Published online | 10 March 2026 | |
https://doi.org/10.1051/epjconf/202635701006
A SSD MobileNetV2-Based Waste Management System for Campuses Using TensorFlow
Department of Electrical and Electronic Engineering, Student, Government engineering college, Thrissur 680009, Kerala, India
* Corresponding author: This email address is being protected from spambots. You need JavaScript enabled to view it.
Published online: 10 March 2026
Abstract
Waste management is a challenge for modern cities, as it impacts environmental sustainability and the quality of life perceived by citizens. A key element for the success of waste segregation initiatives is achieving excellent cooperation from citizens; however, in today's busy lifestyles, this is not aways feasible. With the development of the Internet of Things (IoT) and Artificial Intelligence (AI), existing waste management systems can be replaced with iot based system to perform real-time monitoring and efficient waste management. The ‘Intelligent waste management system’ is an idea of an image-based automatic classification of waste materials in a localized area, such as a campus. The detection of objects, such as paper, plastic, and pens, and their classification were performed using a pretrained object detection model, thereby simplifying waste segregation. Sensors are embedded in each waste compartment to monitor the fill level, allowing bins to be replaced as needed. In this way, the traditional waste management system can be improved, bringing society closer to a greener and healthier future.
Key words: Waste classification / Object detection / CNN / TensorFlow / Internet of Thing
© The Authors, published by EDP Sciences, 2026
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.

