Abstract
dc:description.abstractIn this thesis, a framework based on open-source hardware is proposed and built to study the practicability of its use in indoor robotics research. Two Raspberry Pi camera modules are used as a range sensor for indoor robot triangulation in a static scene, which infers 3D information from 2D space using stereo vision. The local Block Matching method and Semi-Global matching method are implemented in dense disparity map estimations. 3D reconstructions are performed and binary 2D maps are generated. Previous work has paid attention to iterative methods to minimize the global energy function in solving matching problems. This thesis presents two vectorized methods that are suitable in stereo vision triangulation and acceptable for use in robotic applications. Results show that the depth estimation of both methods can be accurate to centimeters in between half a meter to four meters of range. Real-time implementation of these approaches has not been investigated.
Degree
thesis:*- Name thesis:degree_name
- Master of Applied Science (M.App.Sc.)
- Level thesis:degree_level
- Master's
- Discipline thesis:degree_discipline
- Engineering, Mechanical
- Grantor dc:publisher
- Carleton University
- Year dc:date.issued
- 2017
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Zhuang, Kun
Subjects
dc:subject × 3Rights
dc:rights- Statement dc:rights
-
- Copyright © 2017 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, research, scholarship, and teaching. Theses may only be shared by linking to Carleton University Institutional Repository and no part may be used without proper attribution to the author. No part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner.
- Language dc:language.iso
- en