Vehicle type validation for highway entrances using convolutional neural networks

Abstract

Vehicle type validation for Highway entrances using convolutional neural networks is an approach taken to automate the highway toll systems of Sri Lanka. Available automated highway toll systems in the world use sensor-based validation systems to validate the vehicles that are entering the highways. Mainteneance cost of these systems is high. A vision-based validation system has not been implemented, as yet. This paper introduces a vision-based method to validate vehicles for highway systems which can reduce the cost while increasing the efficiency and safety. A Convolutional Neural Network (CNN) model was developed to achieve this objective. The CNN model employed here uses a binary classification to categorize vehicles as allowed vehicles and non-allowed vehicles for entering the highway. The model developed here showed 86.69% accuracy. The model was manually tested for different vehicle types using a GUI based application and all the test images were successfully classified into their classes.