Georeferenced Visual SLAM

dc.contributor.advisorMatiisen, Tambet, juhendaja
dc.contributor.advisorSepp, Edgar, juhendaja
dc.contributor.authorMägi, Erik
dc.contributor.otherTartu Ülikool. Loodus- ja täppisteaduste valdkondet
dc.contributor.otherTartu Ülikool. Arvutiteaduse instituutet
dc.date.accessioned2023-10-26T06:58:15Z
dc.date.available2023-10-26T06:58:15Z
dc.date.issued2023
dc.description.abstractThis thesis presents a complementary localization solution for taxis and ride-hailing operators in situations where GNSS is unavailable or unreliable. The proposed method leverages monocular visual SLAM techniques, specifically the ORB-SLAM 3 library, to create a map of the environment and localize within it. The system uses a car-mounted camera for image capture and an advanced GNSS receiver to record accurate ground truth. This data is then used as input for training a deep learning model to transform SLAM coordinates into georeferenced coordinates. The thesis explores different approaches to solving the coordinate transformation problem, including linear transformation, machine learning regression algorithms, and deep learning with neural networks. Results show that the deep learning based approach provides the best localization accuracy, surpassing that of modern smartphone GNSS. The study contributes a practical solution for real-time localization for ride-hailing operators when GNSS is compromised, with the potential for future implementation using smartphone cameras.et
dc.identifier.urihttps://hdl.handle.net/10062/93756
dc.language.isoenget
dc.publisherTartu Ülikoolet
dc.rightsopenAccesset
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.subjectVisual SLAMet
dc.subjectORB-SLAM 3et
dc.subjectgeoreferencinget
dc.subjectneural networkset
dc.subject.othermagistritöödet
dc.subject.otherinformaatikaet
dc.subject.otherinfotehnoloogiaet
dc.subject.otherinformaticset
dc.subject.otherinfotechnologyet
dc.titleGeoreferenced Visual SLAMet
dc.typeThesiset

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Magi_MSc_computer_science_2023.pdf
Size:
27.3 MB
Format:
Adobe Portable Document Format
Description:

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: