NORMA eResearch @NCI Library

A Deep Learning Approach to Vehicle Make and Model Recognition with Specification Matching

Tanga, Samuel Biwei (2021) A Deep Learning Approach to Vehicle Make and Model Recognition with Specification Matching. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (1MB) | Preview


Vehicle Make and Model Recognition (VMMR) has risen to become a highly significant research area within the automobile sector in recent years. Specifically, it is beneficial in traffic analysis, vehicle analysis, and detection of crimes associated with vehicles, among other applications. A VMMR system with great accuracy and the ability to create dynamic real-time results helps save resources. For this recognition and classification task, a system that is sufficiently capable to handle the ambiguity and multiplicity that occurs between various makes and models needs to be implemented. This project aims to develop a vehicle model recognition system that can appropriately recognise and perform classification of vehicles into appropriate make and model classes they belong to with an attempt to match the accurately recognized vehicles with their standardized specifications. The author proposes three different models in order to address this challenge and develop a system that is more adaptive and responsive than previously proposed methods. The system is developed with these models (MobileNet-v2, ResNet50, VGG16) by training them with the train sets and evaluating the models by their accuracy and computational time. ResNet-50 outperforms the other models considering the accuracy and minimal trade-off with computational time. The ResNet-50 model is then incorporated into a GUI application which can be used for real life applications, this to displays the importance of the system to the automobile industry and intelligent transport systems.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
T Technology > TL Motor vehicles. Aeronautics. Astronautics
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 13 Mar 2023 16:31
Last Modified: 13 Mar 2023 16:31

Actions (login required)

View Item View Item