The accelerated advancement of urban infrastructure has underscored the significance of smart city technologies, especially within traffic management, wherein vehicle detection and classification assume a crucial role. This manuscript presents a vehicle identification framework specifically designed for the roadways of Bangladesh, employing the YOLOv8n model to optimize traffic flow, alleviate congestion, and augment road safety. The system utilizes a custom dataset from real-time traffic footage in Bangladesh, classifying vehicles into eight categories. As part of this study, we evaluated our model utilizing Bangladeshi real-time traffic video data. The study showcases the model's capability to navigate intricate urban settings, although accuracy enhancement is necessary, especially in congested traffic. The findings underscore the model's potential for improving traffic surveillance and supporting smart city developments.
Vehicle Classification and Detection Using YOLOv8: A Study on Highway Traffic Analysis
07.12.2024
792303 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Traffic Sign Detection Using YOLOv8
IEEE | 2024
|Analysis of Traffic Management System using YOLOv8
IEEE | 2023
|