Abstract: Urban traffic management remains an important concern as high-density traffic causes congestion, delays, and emergency- related challenges. This paper involves an automated LED notification system that uses computer vision and deep learning for vehicle detection and classification, with a focus on alerting and prioritizing emergency vehicles like ambulances in high- traffic density areas. Continuous transmission of traffic data from the webcam is processed with the YOLO model, which is chosen for its speed and accuracy in dynamic environments such as roads and streets, enabling quality detection and counts in various lanes. The system classifies vehicles in real time and distinguishes emergency vehicles such as ambulances from general traffic, thus enabling automated LED alerts to notify other vehicles to make way for emergency vehicles. Embedded Deep Reinforcement Learning is the core of this programming system; it connects variable lanes to dynamic timing of lights via intelligent lane allocation, aiming to reduce congestion and maximize response time for emergency vehicles. The DRL agent is self-trained using historical records and real-time feedback to improve traffic flow and prioritization for ambulances, with advances in LED notifications and traffic light synchronization using computer vision. Managing congestion is aided by providing real-time information, such as lane counts, average speed, and traffic flow, which can be useful to operators. Once any lane is recognized as having an ambulance, it is immediately tagged as a "high priority" lane, triggering the LED notification system to alert other vehicles and coordinate traffic signals for immediate clearance. Through these measures, the system improves traffic efficiency and emergency response in high-density areas.
Keywords: IoT, Radio Frequency, Microcontrollers, Arduino UNO, Transmitters, Receivers
Copyright Form