Traffic monitoring systems are a crucial aspect of Intelligent Transportation Systems (ITS). This study utilizes a state-of-the-art deep learning algorithm, YOLOv8, with OpenCV, to address the challenges of vehicle counting and classification. The specific research area chosen was a highway in Malaysia, which had not been previously investigated in algorithm-based vehicle detection systems. The implementation of this model on the highway is essential for enhancing road safety and preventing accidents. Our findings reveal that the model achieved a remarkable 96% accuracy in detecting vehicles and 94.08% accuracy in classifying them. As a result, it is recommended to implement this model on the highway to improve traffic management and increase overall safety.
Vehicle Class Detection and Counting on a Malaysian Road Using YOLOv8 and OpenCV
26.08.2024
618326 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Vehicle Detection and Counting in Traffic Video Based on OpenCV
Trans Tech Publications | 2013
|Road Edge Detection Using OpenCV for an Autonomous Road-Marking Robot Design
Springer Verlag | 2025
|Reckoning and Speed Revealing of Automobile Using OpenCV and YOLOv8 by Real-Time Visual Image
Springer Verlag | 2024
|Coal logistics park traffic flow statistical system and method based on YOLOv8 and OpenCV
Europäisches Patentamt | 2025
|