Deep Neural Network Aiding Visual Odometry for Land Vehicles Navigation

Simple item page
dc.contributor.advisorEl-Sheimy, Naser M.
dc.contributor.authorSalib, Abanob M. A.
dc.contributor.committeememberEl-Sheimy, Naser M
dc.contributor.committeememberNoureldin, Aboelmagd MA
dc.contributor.committeememberKattan, Lina
dc.dateFall Convocation
dc.date.accessioned2023-02-11T00:32:11Z
dc.date.embargolift2023-02-22
dc.date.issued2020-12-09
dc.description.abstractSelf-driving cars consider vision sensor (monocular/stereo camera) as the primary sensor for driving vehicles and providing rich visual information which can be utilized for obstacle avoidance and scene understanding. This thesis introduces an improved visual odometry algorithm for vehicle navigation by including deep neural network such as YOLOv3 through masking the moving objects within each frame, and excluding these objects in order to aid the RANSAC (RANdom SAmple Consensus) to raise the inliers ratio. Pedestrians and moving vehicles can add outliers and reduce RANSAC performance. In some cases, the RANSAC algorithm can fail, such as when any dataset has a significant number of contaminated points or is non-realistic, such as within the dynamic environment. By integrating a machine learning module, RANSAC was able to rely more on static features than on dynamic features, resulting in lower RANSAC computing cost. Different datasets were used to check the proposed algorithm’s efficiency. The results are promising because they reflect a rise in the elapsed time reduction for primary matching and RANSAC and incrementation in inliers proportion. Through implementing the suggested approach, the final navigation solution for two different datasets presents a significant improvement over the typical visual odometry technique.
dc.identifier.citationSalib, A. M. A. (2020). Deep Neural Network Aiding Visual Odometry for Land Vehicles Navigation (Master's thesis, University of Calgary, Calgary, Canada). Retrieved from https://prism.ucalgary.ca.
dc.identifier.urihttp://hdl.handle.net/1880/115856
dc.identifier.urihttps://dx.doi.org/10.11575/PRISM/40750
dc.language.isoenen
dc.language.isoEnglish
dc.publisher.facultyGraduate Studiesen
dc.publisher.facultySchulich School of Engineering
dc.publisher.institutionUniversity of Calgaryen
dc.rightsUniversity of Calgary graduate students retain copyright ownership and moral rights for their thesis. You may use this material in any way that is permitted by the Copyright Act or through licensing that has been assigned to the document. For uses that are not allowable under copyright legislation or licensing, you are required to seek permission.en
dc.subjectDeep Neural Networks
dc.subjectFeature Matching
dc.subjectRANSAC
dc.subjectComputer Vision
dc.subjectMonocular Camera
dc.subjectArtificial Intelligence
dc.subjectEnhance Final Navigation Solution
dc.subjectTrajectory
dc.subjectInertial
dc.subjectIMU
dc.subjectCamera Calibration
dc.subjectYOLOv3
dc.subjectCNNs
dc.subjectANNs
dc.subjectsensor fusion
dc.subjectLand Vehicles
dc.subject.classificationArtificial Intelligence
dc.subject.classificationComputer Science
dc.titleDeep Neural Network Aiding Visual Odometry for Land Vehicles Navigation
dc.typemaster thesis
thesis.degree.disciplineEngineering – Geomatics
thesis.degree.grantorUniversity of Calgaryen
thesis.degree.grantorUniversity of Calgary
thesis.degree.nameMaster of Science (MSc)
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
ucalgary_2020_salib_abanob.pdf
Size:
6.34 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.6 KB
Format:
Plain Text
Description:
Download
Collections
Open Theses and Dissertations