This project combines YOLOv8 and cloud computing for detecting and classifying road damage, including alligator cracking, edge cracking, longitudinal cracking, patching, potholes, rutting, and transverse cracking. The system utilizes a dataset from Roboflow to train the YOLOv8 model, ensuring high accuracy and speed in identifying and classifying various types of road damage. YOLOv8’s efficiency allows for rapid detection, making it ideal for applications in road maintenance. The cloud infrastructure is used to store and process the data securely. User details, including passwords, usernames, and emails, as well as image paths, are encrypted to maintain privacy and security. By utilizing cloud technologies, the project offers scalable and accessible data storage, enabling easy retrieval and processing from any location. This solution aims to provide transportation and municipal authorities with an effective tool for monitoring of road conditions, enabling timely repairs and improving overall road safety.

Keywords: YOLOv8, cloud computing, road damage detection, pothole classification, real-time monitoring, encrypted data storage, image path encryption, road condition analysis, machine learning.