Deep Learning Based Vehicle Classification
Date of Award
4-12-2023
Publication Type
Thesis
Degree Name
M.Sc.
Department
Computer Science
Keywords
Deep learning, Vehicle classification, Intelligent transportation systems, Residual network
Supervisor
I.Ahmad
Supervisor
D. Wu
Rights
info:eu-repo/semantics/openAccess
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Abstract
Vehicle classification is an essential part of intelligent transportation systems(ITS). This work proposes a model based on transfer learning, combining data augmentation for the recognition and classification of local vehicle classes in Canada. It takes inspiration from contemporary deep learning (DL) achievements image classification. This makes use of the Dataset named Stanford AI of Vehicles, which has 16185 photos. The images in this section are divided into 196 types of various vehicles. To increase performance further, additional classification blocks are added to the residual network (ResNet-50)-based model which is being used. In this case, vehicle type details are automatically extracted and classified. A number of measures like accuracy, precision, recall, etc. were used during the analysis to evaluate the results. The proposed model exhibited increasing accuracy despite the vehicles’ different physical characteristics. In comparison to the current baseline method and the two pre-trained DL systems, AlexNet and VGG-16, our suggested method outperforms them all. The suggested ResNet-50 pre-trained model achieved an accuracy of 90.07% in the classification of native vehicle types, according to outcome comparisons. We have also compared this by running VGG-16 where we are getting an accuracy of 82.5%. Along with this Vehicle classification, we have implemented number plate detection and smart vehicle counter systems which all together makes our transport system better than ever before.
Recommended Citation
Muhib, Ragheb Barkat, "Deep Learning Based Vehicle Classification" (2023). Electronic Theses and Dissertations. 9036.
https://scholar.uwindsor.ca/etd/9036