No Cover Image

Journal article 524 views 198 downloads

Active stereo platform: online epipolar geometry update

Abdulla Mohamed, Phil Culverhouse, Angelo Cangelosi, Chenguang Yang

EURASIP Journal on Image and Video Processing, Volume: 2018, Issue: 1

Swansea University Author: Chenguang Yang

Abstract

This paper presents a novel method to update a variable epipolar geometry platform directly from the motor encoder based on mapping the motor encoder angle to the image space angle, avoiding the use of feature detection algorithms. First, an offline calibration is performed to establish a relationsh...

Full description

Published in: EURASIP Journal on Image and Video Processing
ISSN: 1687-5281
Published: 2018
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa43358
first_indexed 2018-08-14T12:57:50Z
last_indexed 2018-10-09T15:13:58Z
id cronfa43358
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2018-10-09T11:32:01.3683425</datestamp><bib-version>v2</bib-version><id>43358</id><entry>2018-08-14</entry><title>Active stereo platform: online epipolar geometry update</title><swanseaauthors><author><sid>d2a5024448bfac00a9b3890a8404380b</sid><ORCID/><firstname>Chenguang</firstname><surname>Yang</surname><name>Chenguang Yang</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2018-08-14</date><abstract>This paper presents a novel method to update a variable epipolar geometry platform directly from the motor encoder based on mapping the motor encoder angle to the image space angle, avoiding the use of feature detection algorithms. First, an offline calibration is performed to establish a relationship between the image space and the hardware space. Second, a transformation matrix is generated using the results from this mapping. The transformation matrix uses the updated epipolar geometry of the platform to rectify the images for further processing. The system has an overall error in the projection of &#xB1;&#x2009;5 pixels, which drops to &#xB1;&#x2009;1.24 pixels when the verge angle increases beyond 10&#xB0;. The platform used in this project has 3&#xB0; of freedom to control the verge angle and the size of the baseline.</abstract><type>Journal Article</type><journal>EURASIP Journal on Image and Video Processing</journal><volume>2018</volume><journalNumber>1</journalNumber><publisher/><issnElectronic>1687-5281</issnElectronic><keywords>Active stereo vision, Epipolar geometry, Calibration, Binocular vision, Real-time update</keywords><publishedDay>31</publishedDay><publishedMonth>12</publishedMonth><publishedYear>2018</publishedYear><publishedDate>2018-12-31</publishedDate><doi>10.1186/s13640-018-0292-8</doi><url/><notes/><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><apcterm/><lastEdited>2018-10-09T11:32:01.3683425</lastEdited><Created>2018-08-14T12:24:33.7633609</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Engineering and Applied Sciences - Uncategorised</level></path><authors><author><firstname>Abdulla</firstname><surname>Mohamed</surname><order>1</order></author><author><firstname>Phil</firstname><surname>Culverhouse</surname><order>2</order></author><author><firstname>Angelo</firstname><surname>Cangelosi</surname><order>3</order></author><author><firstname>Chenguang</firstname><surname>Yang</surname><orcid/><order>4</order></author></authors><documents><document><filename>0043358-14082018122709.pdf</filename><originalFilename>mohamed2018(2).pdf</originalFilename><uploaded>2018-08-14T12:27:09.4700000</uploaded><type>Output</type><contentLength>2421794</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><embargoDate>2018-08-14T00:00:00.0000000</embargoDate><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling 2018-10-09T11:32:01.3683425 v2 43358 2018-08-14 Active stereo platform: online epipolar geometry update d2a5024448bfac00a9b3890a8404380b Chenguang Yang Chenguang Yang true false 2018-08-14 This paper presents a novel method to update a variable epipolar geometry platform directly from the motor encoder based on mapping the motor encoder angle to the image space angle, avoiding the use of feature detection algorithms. First, an offline calibration is performed to establish a relationship between the image space and the hardware space. Second, a transformation matrix is generated using the results from this mapping. The transformation matrix uses the updated epipolar geometry of the platform to rectify the images for further processing. The system has an overall error in the projection of ± 5 pixels, which drops to ± 1.24 pixels when the verge angle increases beyond 10°. The platform used in this project has 3° of freedom to control the verge angle and the size of the baseline. Journal Article EURASIP Journal on Image and Video Processing 2018 1 1687-5281 Active stereo vision, Epipolar geometry, Calibration, Binocular vision, Real-time update 31 12 2018 2018-12-31 10.1186/s13640-018-0292-8 COLLEGE NANME COLLEGE CODE Swansea University 2018-10-09T11:32:01.3683425 2018-08-14T12:24:33.7633609 Faculty of Science and Engineering School of Engineering and Applied Sciences - Uncategorised Abdulla Mohamed 1 Phil Culverhouse 2 Angelo Cangelosi 3 Chenguang Yang 4 0043358-14082018122709.pdf mohamed2018(2).pdf 2018-08-14T12:27:09.4700000 Output 2421794 application/pdf Version of Record true 2018-08-14T00:00:00.0000000 true eng
title Active stereo platform: online epipolar geometry update
spellingShingle Active stereo platform: online epipolar geometry update
Chenguang Yang
title_short Active stereo platform: online epipolar geometry update
title_full Active stereo platform: online epipolar geometry update
title_fullStr Active stereo platform: online epipolar geometry update
title_full_unstemmed Active stereo platform: online epipolar geometry update
title_sort Active stereo platform: online epipolar geometry update
author_id_str_mv d2a5024448bfac00a9b3890a8404380b
author_id_fullname_str_mv d2a5024448bfac00a9b3890a8404380b_***_Chenguang Yang
author Chenguang Yang
author2 Abdulla Mohamed
Phil Culverhouse
Angelo Cangelosi
Chenguang Yang
format Journal article
container_title EURASIP Journal on Image and Video Processing
container_volume 2018
container_issue 1
publishDate 2018
institution Swansea University
issn 1687-5281
doi_str_mv 10.1186/s13640-018-0292-8
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Engineering and Applied Sciences - Uncategorised{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Engineering and Applied Sciences - Uncategorised
document_store_str 1
active_str 0
description This paper presents a novel method to update a variable epipolar geometry platform directly from the motor encoder based on mapping the motor encoder angle to the image space angle, avoiding the use of feature detection algorithms. First, an offline calibration is performed to establish a relationship between the image space and the hardware space. Second, a transformation matrix is generated using the results from this mapping. The transformation matrix uses the updated epipolar geometry of the platform to rectify the images for further processing. The system has an overall error in the projection of ± 5 pixels, which drops to ± 1.24 pixels when the verge angle increases beyond 10°. The platform used in this project has 3° of freedom to control the verge angle and the size of the baseline.
published_date 2018-12-31T04:25:50Z
_version_ 1858704088059871232
score 11.453587