Abstract
This project presents a real-time garbage classification system using a YOLO (You Only Look Once) deep learning model deployed with Python and OpenCV. The system utilizes a webcam to capture live video frames and processes each frame using a pre-trained YOLO model in TensorFlow Lite format to detect and classify different types of waste materials. The model is trained on 42 distinct categories of garbage, including plastics, metals, paper, textiles, electronics, and more. Once an object is detected, it is highlighted with bounding boxes and labeled with its class name and detection confidence, providing an intuitive and visual representation for users. The application aims to support automated waste segregation systems and promote better recycling practices by accurately identifying waste types in real time. The system architecture is lightweight and responsive, employing threading to ensure smooth video feed and inference handling simultaneously.
Reviews
There are no reviews yet.