Note
Includes bibliography.
Member of
Contributors
Publisher
Florida Atlantic University
Date Issued
2018
EDTF Date Created
2018
Description
In this research, image segmentation and visual odometry estimations in real time
are addressed, and two main contributions were made to this field. First, a new image
segmentation and classification algorithm named DilatedU-NET is introduced. This deep
learning based algorithm is able to process seven frames per-second and achieves over
84% accuracy using the Cityscapes dataset. Secondly, a new method to estimate visual
odometry is introduced. Using the KITTI benchmark dataset as a baseline, the visual
odometry error was more significant than could be accurately measured. However, the
robust framerate speed made up for this, able to process 15 frames per second.
are addressed, and two main contributions were made to this field. First, a new image
segmentation and classification algorithm named DilatedU-NET is introduced. This deep
learning based algorithm is able to process seven frames per-second and achieves over
84% accuracy using the Cityscapes dataset. Secondly, a new method to estimate visual
odometry is introduced. Using the KITTI benchmark dataset as a baseline, the visual
odometry error was more significant than could be accurately measured. However, the
robust framerate speed made up for this, able to process 15 frames per second.
Language
Type
Form
Extent
57 p.
Subject (Topical)
Identifier
FA00005990
Additional Information
Includes bibliography.
Thesis (M.S.)--Florida Atlantic University, 2018.
FAU Electronic Theses and Dissertations Collection
Date Backup
2018
Date Created Backup
2018
Date Text
2018
Date Created (EDTF)
2018
Date Issued (EDTF)
2018
Extension
FAU
IID
FA00005990
Organizations
Attributed name: Florida Atlantic University
Attributed name: College of Engineering and Computer Science
Attributed name: Department of Civil, Environmental and Geomatics Engineering
Person Preferred Name
Blankenship, Jason R.
author
Graduate College
Physical Description
application/pdf
57 p.
Title Plain
Using Deep Learning Semantic Segmentation to Estimate Visual Odometry
Use and Reproduction
Copyright © is held by the author, with permission granted to Florida Atlantic University to digitize, archive and distribute this item for non-profit research and educational purposes. Any reuse of this item in excess of fair use or other copyright exemptions requires permission of the copyright holder.
http://rightsstatements.org/vocab/InC/1.0/
Origin Information
2018
2018
Florida Atlantic University
Boca Raton, Fla.
Physical Location
Florida Atlantic University Libraries
Place
Boca Raton, Fla.
Sub Location
Digital Library
Title
Using Deep Learning Semantic Segmentation to Estimate Visual Odometry
Other Title Info
Using Deep Learning Semantic Segmentation to Estimate Visual Odometry