Smart Waste Management System Using Deep Learning

Abstract: The rapid increase in waste generation across urban and rural areas demands intelligent, automated solutions for effective waste segregation. This paper presents an AI-Powered Smart Waste Sorting Bin that integrates deep learning, computer vision, and Internet of Things (IoT) technologies to automate the classification of waste into biodegradable and non-biodegradable categories. A camera mounted on a laptop captures images of waste items placed near the bin. An Infrared (IR) sensor connected to a Raspberry Pi Pico microcontroller detects the presence of waste and triggers the image acquisition process. The captured image is then analysed by a trained YOLOv8 (You Only Look Once, version 8) deep learning model, which classifies the waste based on visual features. The classification result is communicated via serial protocol to the Raspberry Pi Pico, which activates servo motors to route the waste into the appropriate bin compartment. A 16×2 LCD display provides real-time feedback to the user. Experimental results confirm that the system achieves reliable waste classification with minimal human intervention, offering a practical and cost-effective solution for smart city waste management.

Keywords: Deep Learning, YOLOv8, Waste Classification, IoT, Raspberry Pi Pico, Smart Waste Management, Computer Vision, Servo Motor