Thesis Details

Rozpoznání druhu vozidla v obraze

Bachelor's Thesis Student: Čabala Roman Academic Year: 2019/2020 Supervisor: Špaňhel Jakub, Ing.
Language
Slovak
Abstract

The goal of this bachelor thesis is to recognize the type of vehicle from the image using neural networks. Vehicles are divided into 6 types, namely a car, a small van, a van, a mini truck, a truck and a bus. The data set was picked from videos that record the trajectory of the vehicles. Subsequently, an image annotation tool was built. The following architectures were used for network training: VGG16, ResNet50, Xception, InceptionResNet-v2. The result of the work is a comparison of architectures. All architectures were trained and achieved a result above 90%.

Keywords

vehicle type classification, Python, Tensorflow, Keras, VGG16, ResNet50, Xception, InceptionResNet

Department
Degree Programme
Information Technology
Files
Status
defended, grade C
Date
9 July 2020
Reviewer
Committee
Herout Adam, prof. Ing., Ph.D. (DCGM FIT BUT), předseda
Bidlo Michal, doc. Ing., Ph.D. (DCSY FIT BUT), člen
Čadík Martin, doc. Ing., Ph.D. (DCGM FIT BUT), člen
Grégr Matěj, Ing., Ph.D. (DIFS FIT BUT), člen
Kočí Radek, Ing., Ph.D. (DITS FIT BUT), člen
Citation
ČABALA, Roman. Rozpoznání druhu vozidla v obraze. Brno, 2020. Bachelor's Thesis. Brno University of Technology, Faculty of Information Technology. 2020-07-09. Supervised by Špaňhel Jakub. Available from: https://www.fit.vut.cz/study/thesis/23009/
BibTeX
@bachelorsthesis{FITBT23009,
    author = "Roman \v{C}abala",
    type = "Bachelor's thesis",
    title = "Rozpozn\'{a}n\'{i} druhu vozidla v obraze",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2020,
    location = "Brno, CZ",
    language = "slovak",
    url = "https://www.fit.vut.cz/study/thesis/23009/"
}
Back to top