Potholes pose significant financial and safety hazards to motorists worldwide, emphasizing the demand for innovative solutions for detection and repair. Conventional methods, reliant on manual inspection and patching, prove to be inefficient and unsustainable, prompting the need for automated detection systems. However, merely expediting the patching process does not address the underlying issues that cause the potholes in the first place. This paper introduces a pothole detection and mapping system over Google Street View, utilizing highly effective learning models and Google Map’s APIs. Our system extracts images along specified routes from the Google Street View API, processes them using a detection model, and plots the results on an interactive map. Additionally, it compiles these findings into a video that simulates a drive along the route. By leveraging deep learning techniques, we provide users with valuable insights into road conditions, facilitating proactive maintenance strategies. The evaluation demonstrates high classification accuracy and sensitivity in pothole detection. Additionally, the system’s capacity to analyze data over time enables municipalities to identify and pinpoint persistent pothole-prone areas, paving the way for targeted interventions to prevent future hazards. Future work includes expanding the dataset and developing a user-friendly interface to enhance the system’s capabilities and usability. Our system offers a promising solution for long-term pothole repair and maintenance, contributing to safer and more sustainable transportation infrastructure for communities around the world.