Adaptive Traffic Signal Control System Based on Ultrasonic Sensors using Kalman Filter

Urban traffic congestion is increasing daily as a result of traditional traffic signal systems’ incapacity to handle increasingly intricate traffic patterns. A more advanced approach is suggested in this work: an adaptive traffic signal control system that uses a Kalman Filter (KF) and ultrasonic sensors to predict traffic density in real time for four-lane crossings. The core of the system is an Arduino Mega microcontroller, which interprets data from ultrasonic sensors positioned at intersections along with LEDs connected in parallel to the microcontroller. The KF provides a clear image of the number of cars, basically traffic density in each lane segment, and predicts the optimum density of traffic by removing noise from the sensor data. The results of the simulation demonstrate that this four-lane adaptive traffic control system prioritizes the lane with the highest traffic density or congestion and dynamically modifies the green light duration in each lane based on the traffic density in that lane. Ensuring that all signal changes are in sync with required yellow phases to improve safety, the design integrates parallel switching across all lanes. Simulations confirm correct congestion prioritization and dynamic phase adjustment. Future work will extend from independent intersection control to AI-enhanced, network-wide traffic analysis while preserving the core KF-filtering framework; leverage V2I-enabled machine learning for improved density estimation and signal timing; integrate priority signaling for emergency vehicles via RFID/GPS; deploy energy-efficient solar-powered LEDs with adaptive dimming; and develop advanced adaptive control that responds to pedestrians, weather conditions, and temporal traffic patterns.