EVELOPMENT SMART TRAFFIC LIGHT CONTROL SYSTEM (STLCS) USING THE YOLO OBJECT DETECTION MODEL: AN IMPERATIVE FOR COMPUTER LOGIC EDUCATION

The rapid growth of urban areas, combined with rising population density, has intensified roadway bottlenecks in many cities worldwide.This situation results in prolonged journey times, greater energy demand from vehicles, and heightened ecological impact.To address these concerns, innovative and adaptive transport regulation frameworks are essential.This study introduces a Smart Traffic Light Control System (STLCS), powered by the YOLO object detection framework, aimed at advancing conventional traffic control by integrating real-time vehicle recognition with dynamic light-phase adjustment.Unlike fixed-time traffic signals, the STLCS utilizes YOLOv8n (Ultralytics), a lightweight deep learning model, to provide efficient and accurate detection of vehicles.The hardware setup includes ESP32-CAM modules for video capture, multi-sensor inputs to identify vehicles, pedestrians, and priority-response events across varied conditions, an NVIDIA Jetson Nano for inference, and an Arduino UNO microcontroller to enable responsive traffic signal control.On the software side, the framework is built on Python, employing OpenCV, PyAV, and MoviePy for preprocessing, PyTorch for model deployment, and SUMO for simulating vehicle movement dynamics and emergency-response scenarios.A distinctive aspect of this system is its adaptive priority scheduling mechanism, which dynamically modifies signal cycles according to traffic density, prioritizes first-responder units, and enables eco-friendly green-wave coordination.This strategy not only improves roadway circulation but also reduces energy demand and minimizes atmospheric pollution.Experimental testing confirms that the STLCS consistently identifies vehicles and reacts to roadway fluctuations within seconds.Evaluation across multiple lanes demonstrates measurable gains in congestion relief, transport efficiency, and overall system reliability.By combining lightweight detection algorithms, affordable hardware, and validation through simulation-driven trials, this work introduces a practical, scalable, and emergency-aware STLCS.The proposed framework represents a meaningful contribution to smart city development, offering a flexible and cost-effective solution to contemporary urban mobility control challenges.