Homing in scale space
Thesis (M.Sc.)--Memorial University of Newfoundland, 2009. Computer Science Includes bibliographical references (leaves 77-81) Local visual homing is the process of determining the direction of movement required to return an agent to a goal location by comparing the current image with an image taken...
Main Author: | |
---|---|
Other Authors: | |
Format: | Thesis |
Language: | English |
Published: |
2009
|
Subjects: | |
Online Access: | http://collections.mun.ca/cdm/ref/collection/theses4/id/48069 |
id |
ftmemorialunivdc:oai:collections.mun.ca:theses4/48069 |
---|---|
record_format |
openpolar |
spelling |
ftmemorialunivdc:oai:collections.mun.ca:theses4/48069 2023-05-15T17:23:33+02:00 Homing in scale space Churchill, David, 1983- Memorial University of Newfoundland. Dept. of Computer Science 2009 xii, 81 leaves : ill. (chiefly col.) Image/jpeg; Application/pdf http://collections.mun.ca/cdm/ref/collection/theses4/id/48069 Eng eng Electronic Theses and Dissertations (9.21 MB) -- http://collections.mun.ca/PDFs/theses/Churchill_David.pdf a3242429 http://collections.mun.ca/cdm/ref/collection/theses4/id/48069 The author retains copyright ownership and moral rights in this thesis. Neither the thesis nor substantial extracts from it may be printed or otherwise reproduced without the author's permission. Paper copy kept in the Centre for Newfoundland Studies, Memorial University Libraries Image processing Image registration Robots--Motion Text Electronic thesis or dissertation 2009 ftmemorialunivdc 2015-08-06T19:21:57Z Thesis (M.Sc.)--Memorial University of Newfoundland, 2009. Computer Science Includes bibliographical references (leaves 77-81) Local visual homing is the process of determining the direction of movement required to return an agent to a goal location by comparing the current image with an image taken at the goal, known as the snapshot image. One way of accomplishing visual homing is by computing the correspondences between features and then analyzing the resulting flow field to determine the correct direction of motion. Typically, some strong assumptions need to be posited in order to compute the home direction from the flow field. For example, it is difficult to locally distinguish translation from rotation, so many authors assume rotation to be computable by other means (e.g. magnetic compass). We present a novel approach to visual homing using scale change information from the Scale Invariant Feature Transform (SIFT) which we use to compute landmark correspondences. The method we describe is able to determine the direction of the goal in the robot's frame of reference, irrespective of the relative 3D orientation with the goal. Thesis Newfoundland studies University of Newfoundland Memorial University of Newfoundland: Digital Archives Initiative (DAI) |
institution |
Open Polar |
collection |
Memorial University of Newfoundland: Digital Archives Initiative (DAI) |
op_collection_id |
ftmemorialunivdc |
language |
English |
topic |
Image processing Image registration Robots--Motion |
spellingShingle |
Image processing Image registration Robots--Motion Churchill, David, 1983- Homing in scale space |
topic_facet |
Image processing Image registration Robots--Motion |
description |
Thesis (M.Sc.)--Memorial University of Newfoundland, 2009. Computer Science Includes bibliographical references (leaves 77-81) Local visual homing is the process of determining the direction of movement required to return an agent to a goal location by comparing the current image with an image taken at the goal, known as the snapshot image. One way of accomplishing visual homing is by computing the correspondences between features and then analyzing the resulting flow field to determine the correct direction of motion. Typically, some strong assumptions need to be posited in order to compute the home direction from the flow field. For example, it is difficult to locally distinguish translation from rotation, so many authors assume rotation to be computable by other means (e.g. magnetic compass). We present a novel approach to visual homing using scale change information from the Scale Invariant Feature Transform (SIFT) which we use to compute landmark correspondences. The method we describe is able to determine the direction of the goal in the robot's frame of reference, irrespective of the relative 3D orientation with the goal. |
author2 |
Memorial University of Newfoundland. Dept. of Computer Science |
format |
Thesis |
author |
Churchill, David, 1983- |
author_facet |
Churchill, David, 1983- |
author_sort |
Churchill, David, 1983- |
title |
Homing in scale space |
title_short |
Homing in scale space |
title_full |
Homing in scale space |
title_fullStr |
Homing in scale space |
title_full_unstemmed |
Homing in scale space |
title_sort |
homing in scale space |
publishDate |
2009 |
url |
http://collections.mun.ca/cdm/ref/collection/theses4/id/48069 |
genre |
Newfoundland studies University of Newfoundland |
genre_facet |
Newfoundland studies University of Newfoundland |
op_source |
Paper copy kept in the Centre for Newfoundland Studies, Memorial University Libraries |
op_relation |
Electronic Theses and Dissertations (9.21 MB) -- http://collections.mun.ca/PDFs/theses/Churchill_David.pdf a3242429 http://collections.mun.ca/cdm/ref/collection/theses4/id/48069 |
op_rights |
The author retains copyright ownership and moral rights in this thesis. Neither the thesis nor substantial extracts from it may be printed or otherwise reproduced without the author's permission. |
_version_ |
1766113241703907328 |