Live tracking and mapping from both general and rotation-only camera motion

We present an approach to real-time tracking and mapping that supports any type of camera motion in 3D environments, that is, general (parallax-inducing) as well as rotation-only (degenerate) motions. Our approach effectively generalizes both a panorama mapping and tracking system and a keyframe-bas...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gauglitz, S., Sweeney, C., Ventura, J., Turk, M., Hollerer, T.
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 22
container_issue
container_start_page 13
container_title
container_volume
creator Gauglitz, S.
Sweeney, C.
Ventura, J.
Turk, M.
Hollerer, T.
description We present an approach to real-time tracking and mapping that supports any type of camera motion in 3D environments, that is, general (parallax-inducing) as well as rotation-only (degenerate) motions. Our approach effectively generalizes both a panorama mapping and tracking system and a keyframe-based Simultaneous Localization and Mapping (SLAM) system, behaving like one or the other depending on the camera movement. It seamlessly switches between the two and is thus able to track and map through arbitrary sequences of general and rotation-only camera movements. Key elements of our approach are to design each system component such that it is compatible with both panoramic data and Structure-from-Motion data, and the use of the `Geometric Robust Information Criterion' to decide whether the transformation between a given pair of frames can best be modeled with an essential matrix E, or with a homography H. Further key features are that no separate initialization step is needed, that the reconstruction is unbiased, and that the system continues to collect and map data after tracking failure, thus creating separate tracks which are later merged if they overlap. The latter is in contrast to most existing tracking and mapping systems, which suspend tracking and mapping, thus discarding valuable data, while trying to relocalize the camera with respect to the initial map. We tested our system on a variety of video sequences, successfully tracking through different camera motions and fully automatically building panoramas as well as 3D structures.
doi_str_mv 10.1109/ISMAR.2012.6402532
format Conference Proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6402532</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6402532</ieee_id><sourcerecordid>6402532</sourcerecordid><originalsourceid>FETCH-LOGICAL-i285t-dbef3238fb5a68b9195542a5a751615ba8a1009e9fc11acd78232b69ba497ce23</originalsourceid><addsrcrecordid>eNpVkMtOwzAURI0QEqjkB2DjH0jw9Sv2sqp4VAQh8VhX14lTDEkcORFS_54WumE1M2ekWQwhV8AKAGZv1q9Py5eCM-CFlowrwU9IZksDUpdCag3s9F9m4pxk0_TJGAO2B0ZekMcqfHs6J6y_wrClODS0x3E8-DbFnro4f9CtH3zC7rdNccY5xCGPQ7ejNfb7hvbxgC7JWYvd5LOjLsj73e3b6iGvnu_Xq2WVB27UnDfOt4IL0zqF2jgLVinJUWGpQINyaBAYs962NQDWTWm44E5bh9KWtediQa7_doP3fjOm0GPabY4XiB-ak09N</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Live tracking and mapping from both general and rotation-only camera motion</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Gauglitz, S. ; Sweeney, C. ; Ventura, J. ; Turk, M. ; Hollerer, T.</creator><creatorcontrib>Gauglitz, S. ; Sweeney, C. ; Ventura, J. ; Turk, M. ; Hollerer, T.</creatorcontrib><description>We present an approach to real-time tracking and mapping that supports any type of camera motion in 3D environments, that is, general (parallax-inducing) as well as rotation-only (degenerate) motions. Our approach effectively generalizes both a panorama mapping and tracking system and a keyframe-based Simultaneous Localization and Mapping (SLAM) system, behaving like one or the other depending on the camera movement. It seamlessly switches between the two and is thus able to track and map through arbitrary sequences of general and rotation-only camera movements. Key elements of our approach are to design each system component such that it is compatible with both panoramic data and Structure-from-Motion data, and the use of the `Geometric Robust Information Criterion' to decide whether the transformation between a given pair of frames can best be modeled with an essential matrix E, or with a homography H. Further key features are that no separate initialization step is needed, that the reconstruction is unbiased, and that the system continues to collect and map data after tracking failure, thus creating separate tracks which are later merged if they overlap. The latter is in contrast to most existing tracking and mapping systems, which suspend tracking and mapping, thus discarding valuable data, while trying to relocalize the camera with respect to the initial map. We tested our system on a variety of video sequences, successfully tracking through different camera motions and fully automatically building panoramas as well as 3D structures.</description><identifier>ISBN: 9781467346603</identifier><identifier>ISBN: 1467346608</identifier><identifier>EISBN: 9781467346610</identifier><identifier>EISBN: 9781467346627</identifier><identifier>EISBN: 1467346616</identifier><identifier>EISBN: 1467346624</identifier><identifier>DOI: 10.1109/ISMAR.2012.6402532</identifier><language>eng</language><publisher>IEEE</publisher><subject>Cameras ; Data models ; Merging ; Real-time systems ; Robustness ; Simultaneous localization and mapping ; Tracking</subject><ispartof>2012 IEEE International Symposium on Mixed and Augmented Reality (ISMAR), 2012, p.13-22</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6402532$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6402532$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Gauglitz, S.</creatorcontrib><creatorcontrib>Sweeney, C.</creatorcontrib><creatorcontrib>Ventura, J.</creatorcontrib><creatorcontrib>Turk, M.</creatorcontrib><creatorcontrib>Hollerer, T.</creatorcontrib><title>Live tracking and mapping from both general and rotation-only camera motion</title><title>2012 IEEE International Symposium on Mixed and Augmented Reality (ISMAR)</title><addtitle>ISMAR</addtitle><description>We present an approach to real-time tracking and mapping that supports any type of camera motion in 3D environments, that is, general (parallax-inducing) as well as rotation-only (degenerate) motions. Our approach effectively generalizes both a panorama mapping and tracking system and a keyframe-based Simultaneous Localization and Mapping (SLAM) system, behaving like one or the other depending on the camera movement. It seamlessly switches between the two and is thus able to track and map through arbitrary sequences of general and rotation-only camera movements. Key elements of our approach are to design each system component such that it is compatible with both panoramic data and Structure-from-Motion data, and the use of the `Geometric Robust Information Criterion' to decide whether the transformation between a given pair of frames can best be modeled with an essential matrix E, or with a homography H. Further key features are that no separate initialization step is needed, that the reconstruction is unbiased, and that the system continues to collect and map data after tracking failure, thus creating separate tracks which are later merged if they overlap. The latter is in contrast to most existing tracking and mapping systems, which suspend tracking and mapping, thus discarding valuable data, while trying to relocalize the camera with respect to the initial map. We tested our system on a variety of video sequences, successfully tracking through different camera motions and fully automatically building panoramas as well as 3D structures.</description><subject>Cameras</subject><subject>Data models</subject><subject>Merging</subject><subject>Real-time systems</subject><subject>Robustness</subject><subject>Simultaneous localization and mapping</subject><subject>Tracking</subject><isbn>9781467346603</isbn><isbn>1467346608</isbn><isbn>9781467346610</isbn><isbn>9781467346627</isbn><isbn>1467346616</isbn><isbn>1467346624</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2012</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNpVkMtOwzAURI0QEqjkB2DjH0jw9Sv2sqp4VAQh8VhX14lTDEkcORFS_54WumE1M2ekWQwhV8AKAGZv1q9Py5eCM-CFlowrwU9IZksDUpdCag3s9F9m4pxk0_TJGAO2B0ZekMcqfHs6J6y_wrClODS0x3E8-DbFnro4f9CtH3zC7rdNccY5xCGPQ7ejNfb7hvbxgC7JWYvd5LOjLsj73e3b6iGvnu_Xq2WVB27UnDfOt4IL0zqF2jgLVinJUWGpQINyaBAYs962NQDWTWm44E5bh9KWtediQa7_doP3fjOm0GPabY4XiB-ak09N</recordid><startdate>201211</startdate><enddate>201211</enddate><creator>Gauglitz, S.</creator><creator>Sweeney, C.</creator><creator>Ventura, J.</creator><creator>Turk, M.</creator><creator>Hollerer, T.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201211</creationdate><title>Live tracking and mapping from both general and rotation-only camera motion</title><author>Gauglitz, S. ; Sweeney, C. ; Ventura, J. ; Turk, M. ; Hollerer, T.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i285t-dbef3238fb5a68b9195542a5a751615ba8a1009e9fc11acd78232b69ba497ce23</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2012</creationdate><topic>Cameras</topic><topic>Data models</topic><topic>Merging</topic><topic>Real-time systems</topic><topic>Robustness</topic><topic>Simultaneous localization and mapping</topic><topic>Tracking</topic><toplevel>online_resources</toplevel><creatorcontrib>Gauglitz, S.</creatorcontrib><creatorcontrib>Sweeney, C.</creatorcontrib><creatorcontrib>Ventura, J.</creatorcontrib><creatorcontrib>Turk, M.</creatorcontrib><creatorcontrib>Hollerer, T.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Gauglitz, S.</au><au>Sweeney, C.</au><au>Ventura, J.</au><au>Turk, M.</au><au>Hollerer, T.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Live tracking and mapping from both general and rotation-only camera motion</atitle><btitle>2012 IEEE International Symposium on Mixed and Augmented Reality (ISMAR)</btitle><stitle>ISMAR</stitle><date>2012-11</date><risdate>2012</risdate><spage>13</spage><epage>22</epage><pages>13-22</pages><isbn>9781467346603</isbn><isbn>1467346608</isbn><eisbn>9781467346610</eisbn><eisbn>9781467346627</eisbn><eisbn>1467346616</eisbn><eisbn>1467346624</eisbn><abstract>We present an approach to real-time tracking and mapping that supports any type of camera motion in 3D environments, that is, general (parallax-inducing) as well as rotation-only (degenerate) motions. Our approach effectively generalizes both a panorama mapping and tracking system and a keyframe-based Simultaneous Localization and Mapping (SLAM) system, behaving like one or the other depending on the camera movement. It seamlessly switches between the two and is thus able to track and map through arbitrary sequences of general and rotation-only camera movements. Key elements of our approach are to design each system component such that it is compatible with both panoramic data and Structure-from-Motion data, and the use of the `Geometric Robust Information Criterion' to decide whether the transformation between a given pair of frames can best be modeled with an essential matrix E, or with a homography H. Further key features are that no separate initialization step is needed, that the reconstruction is unbiased, and that the system continues to collect and map data after tracking failure, thus creating separate tracks which are later merged if they overlap. The latter is in contrast to most existing tracking and mapping systems, which suspend tracking and mapping, thus discarding valuable data, while trying to relocalize the camera with respect to the initial map. We tested our system on a variety of video sequences, successfully tracking through different camera motions and fully automatically building panoramas as well as 3D structures.</abstract><pub>IEEE</pub><doi>10.1109/ISMAR.2012.6402532</doi><tpages>10</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier ISBN: 9781467346603
ispartof 2012 IEEE International Symposium on Mixed and Augmented Reality (ISMAR), 2012, p.13-22
issn
language eng
recordid cdi_ieee_primary_6402532
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Cameras
Data models
Merging
Real-time systems
Robustness
Simultaneous localization and mapping
Tracking
title Live tracking and mapping from both general and rotation-only camera motion
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T20%3A46%3A47IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Live%20tracking%20and%20mapping%20from%20both%20general%20and%20rotation-only%20camera%20motion&rft.btitle=2012%20IEEE%20International%20Symposium%20on%20Mixed%20and%20Augmented%20Reality%20(ISMAR)&rft.au=Gauglitz,%20S.&rft.date=2012-11&rft.spage=13&rft.epage=22&rft.pages=13-22&rft.isbn=9781467346603&rft.isbn_list=1467346608&rft_id=info:doi/10.1109/ISMAR.2012.6402532&rft_dat=%3Cieee_6IE%3E6402532%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781467346610&rft.eisbn_list=9781467346627&rft.eisbn_list=1467346616&rft.eisbn_list=1467346624&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6402532&rfr_iscdi=true