Vehicle Class Prediction at Toll Gate Using Deep Learning

Abstract

In the era of digitalization and automation, efficiency in the traffic management system at toll gates is very important. One of the efforts to improve this efficiency is to develop an automatic vehicle class detection system using deep learning technology, especially Convolutional Neural Network (CNN). This research aims to design and implement a CNN model that can identify and classify the types of vehicles passing through toll gates. The model development process includes collecting and annotating vehicle image data, data pre-processing, and CNN model training and testing. The evaluation results show that the developed model can achieve an accuracy of about 96% in detecting vehicle classes, so it can be integrated with the toll gate system to increase the speed and accuracy in the vehicle classification process. Thus, this solution is expected to reduce the waiting time of toll users and improve operational efficiency.