POTHOLE & CRACK DETECTION SYSTEM USING ML & COMPUTER VISION

Abstract: This project aims to develop an automated system that can detect potholes and cracks on roads using image processing and machine learning techniques. Roads are an important part of daily transportation, but damages like potholes and cracks can cause accidents and affect vehicle movement. Traditionally, road inspection is done manually, which takes a lot of time and effort. To solve this problem, this project presents a system that can automatically detect potholes and cracks using machine learning and computer vision.

The system uses images of roads as input and processes them using deep learning techniques such as Convolutional Neural Networks (CNN) and object detection models like YOLO. The model is trained on a dataset of road images containing different types of damages. Once trained, it can identify and highlight potholes and cracks in both images and real time video.

The proposed system helps in faster and more accurate detection compared to manual methods. It can be Useful for road maintenance authorities to monitor road condition and take timely action. In the future, this system can be improved by adding GPS tracking and mobile based application for real time reporting.

Keywords: Potholes, Cracks, Road Damage, Machine Learning, Computer Vision, Image Processing, Road Safety.