Issuu

International Research Journal of Engineering and Technology (IRJET)

e-ISSN: 2395-0056

Volume: 12 Issue: 04 | Apr 2025

p-ISSN: 2395-0072

www.irjet.net

Smart Traffic Management System with Real-Time Monitoring Maaz khan1, Jyoti Maurya2, Pushpa Kumavat3, Dr. Nita Patil4 1,2,,3-

Student, Department of Computer Engineering, K. C. College of Engineering, Thane, India

Professor, Department of Computer Engineering, K. C. College of Engineering, Thane, India

---------------------------------------------------------------------***---------------------------------------------------------------------

Abstract - This study presents a smart traffic management system that utilizes computer vision and artificial intelligence to address urban traffic congestion. The proposed system integrates the You Only Look Once (YOLO) object detection algorithm to detect and track vehicles in real-time using live camera feeds from traffic intersections. By analyzing traffic density, vehicle count, and movement patterns, the system dynamically adjusts traffic signals to optimize flow, reduce delays, and minimize fuel consumption and emissions. An intelligent algorithm determines the optimal signal timing based on real-time traffic conditions, ensuring adaptive and efficient traffic control. The system's scalability and compatibility allow seamless integration into various urban infrastructures while requiring lower implementation and maintenance costs than conventional traffic management systems. To evaluate its effectiveness, experiments were conducted using real-world traffic data, demonstrating high accuracy in vehicle detection, reliable traffic density calculations, and significant congestion reduction. The results indicate that this approach enhances traffic efficiency, reduces environmental impact, and improves commuter experiences. By leveraging advanced AI- driven techniques, the proposed system provides a cost- effective and adaptable solution for modernizing urban traffic management and paving the way for smart, sustainable cities.

Key Words: Smart traffic management, YOLO, AI, congestion optimization, real-time monitoring, webcam, computer vision, roboflow, IoT, 74HC595.

INTRODUCTION

dynamically. At the core of the system lies YOLOv8, a state-of- the-art object detection model capable of analyzing real-time traffic data from cameras and sensors. The system’s features include dynamic signal control based on traffic density and comprehensive data logging for future analysis. It offers significant advantages over conventional systems by adapting to real-time traffic conditions, enabling more efficient and sustainable traffic management practices. With its cost-effective implementation and scalability, the system is well-suited for deployment across various urban environments, ranging from small towns to large metropolitan areas. By addressing inefficiencies in traditional traffic systems, this project aims to enhance urban mobility, improve road safety, and reduce environmental impact.

2. LITERATURE SURVEY To determine the viability of our proposal and explore various execution methods, we reviewed numerous research articles. These studies provided valuable insights, helping us define our project’s vision and scheme of action. Implementing an intelligent traffic management system requires expertise in multiple domains, including Python, image processing, computer vision, and machine learning. Many blogs explain the workings of YOLO and its application in real-time traffic systems. Several studies have explored automated vehicle detection and traffic signal control, demonstrating the advantages of deep learning-based approaches in optimizing urban mobility.

Urbanization has led to exponential growth in vehicular traffic, exacerbating congestion and increasing the risk of road accidents. Traditional traffic management systems, reliant on static signal timing, fail to address the dynamic and unpredictable nature of traffic flows. The inefficiencies inherent in these systems contribute to prolonged wait times, increased fuel consumption, and higher greenhouse gas emissions, intensifying urban mobility challenges.

Recent research has focused on adaptive traffic signal systems that dynamically adjust signal timings based on real-time vehicle density.One such study presents a machine learning model that leverages YOLO for vehicle detection, allowing for efficient traffic regulation and improved congestion management [1].Another study introduces an approach that integrates deep learning with real-time image processing to optimize urban intersections, showcasing significant improvements in vehicle throughput and reduced delays [2].

The Smart Traffic Management System with Real-Time Monitoring seeks to address these challenges by leveraging advanced technologies. It integrates artificial intelligence (AI), machine learning, and computer vision to optimize traffic flow

Various traffic monitoring systems have also been developed using computer vision and deep learning models. Researchers have demonstrated how integrating YOLO with OpenCV enhances vehicle classification and counting, providing precise

ISO 9001:2008 Certified Journal

Impact Factor value: 8.315

Page 1406