This project utilizes the collected images to develop AI-powered computer vision models capable of detecting and tracking the location and extent of cracks over time. Once trained, these AI models can be applied to similar monitoring tasks with minimal technical expertise, which increases their accessibility and impact. Advanced techniques such as Digital Image Correlation will also be explored to accurately monitor deformations caused by shrinkage and thermal expansion. These visual measurements are critical, as they offer a non-contact and non-destructive means of estimating the mechanical performance of the pavement materials under evaluation. This methodology can be extended to long-term automated structural health monitoring of pavements, walls, and other flat civil infrastructure components. By relying on standard cameras and scalable computer vision algorithms, the system offers a cost-effective, low-barrier solution for continuous surface defect detection throughout the service life of materials such as concrete.