Position Estimation of Mobile Robots Using Omni-Directional Cameras

Public Deposited
Resource Type
  • In this work, a design of a perception approach for indoor service mobile robots is considered. Unlike outdoor environments, in which Global Positioning System (GPS) can be utilized, indoor environments usually include small workspaces with complex details. Thus, a significantly higher localization precision is required. Readily available sensing techniques that meet those requirements utilize sensors such as transceivers and vision systems. These perception approaches depend on the workspace type. In the proposed approach, a stereo vision system has been used. Such an approach captures the environment features to produce a 2D/3D map. However, due to the mobility of indoor robots, the problem of losing environment features arises, e.g., they might encounter scenes with non-detectable features. In order to solve the difficulty of obtaining a highly precise map in a highly compact environment, a stereo panoramic vision perception model was developed to integrate the data from two omni-directional vision sensors.

Thesis Degree Level
Thesis Degree Name
Thesis Degree Discipline
Rights Notes
  • Copyright © 2015 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.
Date Created
  • 2015


In Collection: