Content area
With rapid urbanization and increasing vehicle ownership, traditional traffic management systems that rely on fixed schedules and basic sensors are no longer sufficient to handle growing congestion. These outdated systems often result in longer travel times, frequent bottlenecks, and delayed emergency responses. To address these issues, AI-driven solutions powered by deep learning (DL) provide an intelligent alternative by dynamically adjusting traffic signals based on real-time conditions. This project presents an AI- powered traffic monitoring and management system that utilizes YOLO for real-time vehicle detection and accident monitoring, deployed through a lightweight and interactive Streamlit interface. The system analyzes live traffic feeds, counts vehicles, detects accidents, and adjusts signal timings to improve flow and reduce delays. In emergencies, it identifies active ambulances or fire trucks and prioritizes their movement, while triggering automatic alerts through APIs like Twilio for rapid response. A web- based Streamlit dashboard enables centralized monitoring and visualization for traffic authorities, while the mobile application delivers live traffic updates and safety alerts to the public. By integrating deep learning with intuitive user interfaces, the system enhances urban traffic efficiency, boosts public safety, and lays the groundwork for smarter city infrastructure.