Login | Register

Deep Neural Network Architectures and Learning Methodologies for Classification and Application in 3D Reconstruction

Title:

Deep Neural Network Architectures and Learning Methodologies for Classification and Application in 3D Reconstruction

Forbes, Timothy (2018) Deep Neural Network Architectures and Learning Methodologies for Classification and Application in 3D Reconstruction. Masters thesis, Concordia University.

[img]
Preview
Text (application/pdf)
Forbes_MCompSc_S2019.pdf - Accepted Version
Available under License Spectrum Terms of Access.
17MB

Abstract

In this work we explore two different scenarios of 3D reconstruction. The first, urban scenes, is approached using a deep learning network trained to identify structurally important classes within aerial imagery of cities. The network was trained using data taken from ISPRS benchmark dataset of the city of Vaihingen. Using the segmented maps generated by the network we can proceed to more accurately reconstruct the scenes by a process of clustering and then class specific model generation. The second scenario is that of underwater scenes. We use two separate networks to first identify caustics and then remove them from a scene. Data was generated synthetically as real world datasets for this subject are extremely hard to produce. Using the generated caustic free image we can then reconstruct the scene with more precision and accuracy through a process of structure from motion. We investigate different deep learning architectures and parameters for both scenarios. Our results are evaluated to be efficient and effective by comparing them with online benchmarks and alternative reconstruction attempts. We conclude by discussing the limitations of problem specific datasets and our potential research into the generation of datasets through the use of Generative-Adverserial-Networks.

Divisions:Concordia University > Gina Cody School of Engineering and Computer Science
Item Type:Thesis (Masters)
Authors:Forbes, Timothy
Institution:Concordia University
Degree Name:M. Comp. Sc.
Program:Computer Science
Date:December 2018
Thesis Supervisor(s):Mudur, Sudhir and Poullis, Charalambos
ID Code:985222
Deposited By: TIMOTHY FORBES
Deposited On:06 Feb 2020 03:13
Last Modified:06 Feb 2020 03:13
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.

Repository Staff Only: item control page

Downloads per month over past year

Research related to the current document (at the CORE website)
- Research related to the current document (at the CORE website)
Back to top Back to top