Citation

Wong, Zi Jian and Goh, Vik Tor and Yap, Timothy Tzen Vun and Ng, Hu (2020) Vehicle Classification using Convolutional Neural Network for Electronic Toll Collection. In: Computational Science and Technology. Lecture Notes in Electrical Engineering (Computational Science and Technology), 603 . Springer Verlag, pp. 169-177. ISBN 9789811500572

Text 10.1007@978-981-15-0058-9.pdf - Published Version Restricted to Repository staff only Download (46MB)

Abstract

Electronic Toll Collection (ETC) is an automated toll collection system that is fast, efficient, and convenient. Transponder-based ETC’s such as Malaysia’s SmartTag is the most common and reliable. Transponders send identification information wirelessly and the toll fee is charged accordingly. However, it is susceptible to fraudulent transactions where transponders for more expensive vehicle classes such as trucks are swapped with vehicles from cheaper classes like taxis. As such, the toll operator must be able to independently classify the vehicle class instead of relying on information sent from potentially misused transponders. In this paper, we implement an automated video-based vehicle detection and classification system that can be used in conjunction with transponder-based ETCs. It uses the Convolutional Neural Network (CNN) to classify three vehicle classes, namely cars, trucks, and buses. The system is implemented using TensorFlow and is able to obtain high validation accuracy of 93.8% and low validation losses of 0.236. The proposed vehicle classification system can reduce the need for human operators, thus minimising cost and increasing efficiency.

Item Type:	Book Section
Uncontrolled Keywords:	Neural networks (Computer science), Vehicle classification, Computer vision, Machine learning, Tensorflow
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Divisions:	Faculty of Computing and Informatics (FCI) Faculty of Engineering (FOE)
Depositing User:	Ms Suzilawati Abu Samah
Date Deposited:	16 Dec 2020 12:08
Last Modified:	12 Apr 2023 07:45
URII:	http://shdl.mmu.edu.my/id/eprint/7952

Downloads

Edit (login required)