Return to search

Using Deep Learning Semantic Segmentation to Estimate Visual Odometry

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. / Includes bibliography. / Thesis (M.S.)--Florida Atlantic University, 2018. / FAU Electronic Theses and Dissertations Collection

Identiferoai:union.ndltd.org:fau.edu/oai:fau.digital.flvc.org:fau_40781
ContributorsBlankenship, Jason R. (author), Su, Hongbo (Thesis advisor), Florida Atlantic University (Degree grantor), College of Engineering and Computer Science, Department of Civil, Environmental and Geomatics Engineering
PublisherFlorida Atlantic University
Source SetsFlorida Atlantic University
LanguageEnglish
Detected LanguageEnglish
TypeElectronic Thesis or Dissertation, Text
Format57 p., application/pdf
RightsCopyright © 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/

Page generated in 0.0018 seconds