Skip to Main Content
 

Global Search Box

 
 
 

ETD Abstract Container

Abstract Header

Weighted Plane Features for Simultaneous Localization and Mapping

Leyder, Nicholas
http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1637319722546457

Abstract Details

2021, Master of Science (MS), Ohio University, Computer Science (Engineering and Technology).
This thesis presents the utilization of weighted plane features for SLAM to increase the overall accuracy of SLAM systems. Planes are created from depth images and matched according to their normal and best fitting points allowing them to have invariance to rotational and scale changes. The planes created are weighted by their area in the current frame during pose optimization. A modified version of ORB-SLAM2 was then used to evaluate the new plane feature on a popular dataset and was shown to have increased accuracy when compared to other state-of-the-art SLAM systems.
David Chelberg (Advisor)
63 p.
Computer Science
Computer Vision; SLAM

Recommended Citations

Citations

  • Leyder, N. (2021). Weighted Plane Features for Simultaneous Localization and Mapping [Master's thesis, Ohio University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1637319722546457

    APA Style (7th edition)

  • Leyder, Nicholas. Weighted Plane Features for Simultaneous Localization and Mapping. 2021. Ohio University, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1637319722546457.

    MLA Style (8th edition)

  • Leyder, Nicholas. "Weighted Plane Features for Simultaneous Localization and Mapping." Master's thesis, Ohio University, 2021. http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1637319722546457

    Chicago Manual of Style (17th edition)

ohiou1637319722546457
102
© 2021, all rights reserved.
This open access ETD is published by Ohio University and OhioLINK.