Type
Text
Type
Thesis
Date
2007-12-01
Keywords
3D Visual Simultaneous Localization and Mapping | SLAM | Urban Search and Rescue Environments | USAR | landmarks | Scale Invariant Feature Transform | SIFT
Language
en_US
Source
This work is sponsored by the Stony Brook University Graduate School in compliance with the requirements for completion of degree.
Identifier
http://hdl.handle.net/11401/70834
Publisher
The Graduate School, Stony Brook University: Stony Brook, NY.
Format
application/pdf
Abstract
In this thesis, a unique landmark identification and matching method is proposed for identifying and matching distinguishable landmarks for 3D Visual Simultaneous Localization and Mapping (SLAM) in unknown cluttered Urban Search and Rescue (USAR) environments. The novelty of the method is the utilization of both 3D (i.e., depth images) and 2D images. By utilizing a Scale Invariant Feature Transform (SIFT) -based approach and incorporating 3D depth imagery, more reliable and robust recognition and iv matching of landmarks from multiple images for 3D mapping of the environment is achieved. Landmarks are determined effectively within the images utilizing a combination of SIFT keypoints, depth segmentation, edge detection and morphological techniques and a convex hull algorithm. These landmarks are matched through out the scene and used by the proposed Visual SLAM methodology for 6 degrees-of-freedom robot localization and for creation of a 3D virtualized map of USAR environments with respect to a world frame. Experiments presented herein utilizing the proposed methodology verify: (i) its ability to identify clusters of SIFT keypoints in both 3D and 2D images for representation of potential landmarks in the scene, and (ii) the use of the identified landmarks in constructing a 3D map of unknown cluttered USAR environments. Furthermore, conclusions on the proposed methodology, highlighting the contributions and future work are presented.
Recommended Citation
Zhang, Zhe, "Robot-Assisted 3D Mapping of Unknown Cluttered Environments" (2007). Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions). 52.
https://commons.library.stonybrook.edu/stony-brook-theses-and-dissertations-collection/52