A Real-Time Traffic Monitoring System Based on YOLOv8 for Vehicle Detection and Classification

Urban traffic congestion presents significant challenges that require efficient and intelligent management solutions. Traditional traffic monitoring methods lack precision and adapt-ability, especially under varying conditions. Our project aims to develop a real-time traffic monitoring system using...

Full description

Saved in:
Bibliographic Details
Published inIEEE Green Energy and Systems Conference pp. 1 - 6
Main Authors Castillo, Jimwell, Rosculete, Robin, Babayans, Raymond Gharapeti, Merzoian, Anthony, Groves, Kaylee, Calva, Gisela, Dollente, Alma, Jia, Xudong, Li, Bingbing, Jiang, Xunfei
Format Conference Proceeding
LanguageEnglish
Published IEEE 04.11.2024
Subjects
Cameras
convolutional neural networks
Machine learning algorithms
Monitoring
Real-time systems
real-time traffic monitoring
Road safety
Smart systems
Testing
Traffic congestion
traffic management
User interfaces
Vehicle detection
Online AccessGet full text
ISSN2640-0138
DOI10.1109/GESS63533.2024.10784465

Cover

More Information
Summary:Urban traffic congestion presents significant challenges that require efficient and intelligent management solutions. Traditional traffic monitoring methods lack precision and adapt-ability, especially under varying conditions. Our project aims to develop a real-time traffic monitoring system using 2D camera technology and machine learning algorithms to address these gaps. The system includes a camera array for data collection, a data processing unit, and a user interface for real-time monitoring. Our solution employs YOLOv8 for accurate vehicle detection and classification and is demonstrated through rigorous testing. The system offers a robust framework for enhancing urban traffic management, reducing congestion, and improving road safety. Experimental results highlight the system's effectiveness in data aggregation, storage, and real-time processing.
ISSN:2640-0138
DOI:10.1109/GESS63533.2024.10784465