DESIGN AND IMPLEMENTATION OF YOLO-LITTER PATROL

ABSTRACT The increasing prevalence of littering from vehicles is a significant environmental concern that contributes to pollution. This project, “YOLO-Litter Patrol”, aims to address this issue by developing a real-time object detection system that identifies instances of littering from vehicles. The system leverages the state-of-the-art You Only Look Once (YOLO) algorithm for object detection. YOLO, with its ability to perform object detection in real-time, is particularly suited for this application. The project involves collecting a dataset of images or videos of cars throwing things from the window, training the YOLO model on this dataset, and testing the model’s performance on new, unseen data. The goal of the project is to create a tool that can be used to monitor roads and highways for littering behavior, providing data that can be used to inform policy and enforcement measures. By identifying and addressing this environmentally harmful behavior, the project contributes efforts to reduce pollution and promote sustainable practices.