Visual simultaneous localization and mapping in a noisy static environment

Simple item page
dc.contributor.authorMakhubela, J. K.
dc.contributor.co-supervisorNkoana, Tshepiso
dc.contributor.supervisorZuva, Tranos, Prof.
dc.date.accessioned2021-08-20T04:51:41Z
dc.date.available2021-08-20T04:51:41Z
dc.date.issued2019-03
dc.descriptionM. Tech. (Department of Information and Communication Technology, Faculty of Applied and Computer Sciences), Vaal University of Technologyen_US
dc.description.abstractSimultaneous Localization and Mapping (SLAM) has seen tremendous interest amongst the research community in recent years due to its ability to make the robot truly independent in navigation. Visual Simultaneous Localization and Mapping (VSLAM) is when an autonomous mobile robot is embedded with a vision sensor such as monocular, stereo vision, omnidirectional or Red Green Blue Depth (RGBD) camera to localize and map an unknown environment. The purpose of this research is to address the problem of environmental noise, such as light intensity in a static environment, which has been an issue that makes a Visual Simultaneous Localization and Mapping (VSLAM) system to be ineffective. In this study, we have introduced a Light Filtering Algorithm into the Visual Simultaneous Localization and Mapping (VSLAM) method to reduce the amount of noise in order to improve the robustness of the system in a static environment, together with the Extended Kalman Filter (EKF) algorithm for localization and mapping and A* algorithm for navigation. Simulation is utilized to execute experimental performance. Experimental results show a 60% landmark or landfeature detection of the total landmark or landfeature within a simulation environment and a root mean square error (RMSE) of 0.13m, which is minimal when compared with other Simultaneous Localization and Mapping (SLAM) systems from literature. The inclusion of a Light Filtering Algorithm has enabled the Visual Simultaneous Localization and Mapping (VSLAM) system to navigate in an obscure environment.en_US
dc.identifier.urihttp://hdl.handle.net/10352/462
dc.language.isoenen_US
dc.publisherVaal University of Technologyen_US
dc.subjectSimultaneous Localization and Mapping (SLAM)en_US
dc.subjectVisual Simultaneous Localization and Mapping (VSLAM)en_US
dc.subjectEnvironmental noiseen_US
dc.subjectLight intensityen_US
dc.subjectStatic environmenten_US
dc.subjectExtended Kalman Filteren_US
dc.subject.lcshDissertations, Academic -- South Africaen_US
dc.subject.lcshAlgorithmen_US
dc.subject.lcshComputer Communication Networksen_US
dc.subject.lcshRoboticsen_US
dc.titleVisual simultaneous localization and mapping in a noisy static environmenten_US
dc.typeThesisen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
VSLAM thesis_V2(004) TC final check Sat 9 March.pdf
Size:
2.43 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.02 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Theses and Dissertations (Information Communication Technology)