Real-Time Model-Based SLAM Using Line Segments
Existing monocular vision-based SLAM systems favour interest point features as landmarks, but these are easily occluded and can only be reliably matched over a narrow range of viewpoints. Line segments offer an interesting alternative, as line matching is more stable with respect to viewpoint change...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 363 |
|---|---|
| container_issue | |
| container_start_page | 354 |
| container_title | |
| container_volume | |
| creator | Gee, Andrew P. Mayol-Cuevas, Walterio |
| description | Existing monocular vision-based SLAM systems favour interest point features as landmarks, but these are easily occluded and can only be reliably matched over a narrow range of viewpoints. Line segments offer an interesting alternative, as line matching is more stable with respect to viewpoint changes and lines are robust to partial occlusion. In this paper we present a model-based SLAM system that uses 3D line segments as landmarks. Unscented Kalman filters are used to initialise new line segments and generate a 3D wireframe model of the scene that can be tracked with a robust model-based tracking algorithm. Uncertainties in the camera position are fed into the initialisation of new model edges. Results show the system operating in real-time with resilience to partial occlusion. The maps of line segments generated during the SLAM process are physically meaningful and their structure is measured against the true 3D structure of the scene. |
| doi_str_mv | 10.1007/11919629_37 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>pascalfrancis_sprin</sourceid><recordid>TN_cdi_springer_books_10_1007_11919629_37</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>20046609</sourcerecordid><originalsourceid>FETCH-LOGICAL-p219t-ddf9348dab4da9934c2108a801d15624c3776026656bf659fa602c5ec8369f8f3</originalsourceid><addsrcrecordid>eNpNkEtPwzAQhM1LopSe-AO5cODgsutnfCwVLykVEm3PlhPbUSBNo7gX_j1BRYK9zI6-0Uo7hNwgzBFA3yMaNIoZy_UJueJSgMgV0_KUTFAhUs6FOfsDSp-TCXBg1GjBL8kspQ8YRxiUEiZk_h5cSzfNLmSrvQ8tfXAp-GxdLFbZNjVdnRVNF7J1qHehO6RrchFdm8LsV6dk-_S4Wb7Q4u35dbkoaM_QHKj30XCRe1cK78y4VgwhdzmgR6mYqLjWCphSUpVRSRPd6CoZqpwrE_PIp-T2eLd3qXJtHFxXNcn2Q7Nzw5dl4wNKgRlzd8dcGlFXh8GW-_1nsgj2py37ry3-DcVqU-I</addsrcrecordid><sourcetype>Index Database</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Real-Time Model-Based SLAM Using Line Segments</title><source>Springer Books</source><creator>Gee, Andrew P. ; Mayol-Cuevas, Walterio</creator><contributor>Zara, Jiri ; Remagnino, Paolo ; Bebis, George ; Koracin, Darko ; Boyle, Richard ; Theisel, Holger ; Nefian, Ara ; Meenakshisundaram, Gopi ; Malzbender, Tom ; Parvin, Bahram ; Pascucci, Valerio ; Molineros, Jose</contributor><creatorcontrib>Gee, Andrew P. ; Mayol-Cuevas, Walterio ; Zara, Jiri ; Remagnino, Paolo ; Bebis, George ; Koracin, Darko ; Boyle, Richard ; Theisel, Holger ; Nefian, Ara ; Meenakshisundaram, Gopi ; Malzbender, Tom ; Parvin, Bahram ; Pascucci, Valerio ; Molineros, Jose</creatorcontrib><description>Existing monocular vision-based SLAM systems favour interest point features as landmarks, but these are easily occluded and can only be reliably matched over a narrow range of viewpoints. Line segments offer an interesting alternative, as line matching is more stable with respect to viewpoint changes and lines are robust to partial occlusion. In this paper we present a model-based SLAM system that uses 3D line segments as landmarks. Unscented Kalman filters are used to initialise new line segments and generate a 3D wireframe model of the scene that can be tracked with a robust model-based tracking algorithm. Uncertainties in the camera position are fed into the initialisation of new model edges. Results show the system operating in real-time with resilience to partial occlusion. The maps of line segments generated during the SLAM process are physically meaningful and their structure is measured against the true 3D structure of the scene.</description><identifier>ISSN: 0302-9743</identifier><identifier>ISBN: 3540486267</identifier><identifier>ISBN: 9783540486268</identifier><identifier>ISBN: 3540486287</identifier><identifier>EISSN: 1611-3349</identifier><identifier>EISBN: 3540486275</identifier><identifier>EISBN: 9783540486275</identifier><identifier>DOI: 10.1007/11919629_37</identifier><language>eng</language><publisher>Berlin, Heidelberg: Springer Berlin Heidelberg</publisher><subject>Applied sciences ; Artificial intelligence ; Computer science; control theory; systems ; Edge Feature ; Exact sciences and technology ; Line Segment ; Model Edge ; Partial Occlusion ; Pattern recognition. Digital image processing. Computational geometry ; Unscented Kalman Filter</subject><ispartof>Advances in Visual Computing, 2006, p.354-363</ispartof><rights>Springer-Verlag Berlin Heidelberg 2006</rights><rights>2008 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/11919629_37$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/11919629_37$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>309,310,779,780,784,793,4050,4051,25140,27925,38255,41442,42511</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=20046609$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><contributor>Zara, Jiri</contributor><contributor>Remagnino, Paolo</contributor><contributor>Bebis, George</contributor><contributor>Koracin, Darko</contributor><contributor>Boyle, Richard</contributor><contributor>Theisel, Holger</contributor><contributor>Nefian, Ara</contributor><contributor>Meenakshisundaram, Gopi</contributor><contributor>Malzbender, Tom</contributor><contributor>Parvin, Bahram</contributor><contributor>Pascucci, Valerio</contributor><contributor>Molineros, Jose</contributor><creatorcontrib>Gee, Andrew P.</creatorcontrib><creatorcontrib>Mayol-Cuevas, Walterio</creatorcontrib><title>Real-Time Model-Based SLAM Using Line Segments</title><title>Advances in Visual Computing</title><description>Existing monocular vision-based SLAM systems favour interest point features as landmarks, but these are easily occluded and can only be reliably matched over a narrow range of viewpoints. Line segments offer an interesting alternative, as line matching is more stable with respect to viewpoint changes and lines are robust to partial occlusion. In this paper we present a model-based SLAM system that uses 3D line segments as landmarks. Unscented Kalman filters are used to initialise new line segments and generate a 3D wireframe model of the scene that can be tracked with a robust model-based tracking algorithm. Uncertainties in the camera position are fed into the initialisation of new model edges. Results show the system operating in real-time with resilience to partial occlusion. The maps of line segments generated during the SLAM process are physically meaningful and their structure is measured against the true 3D structure of the scene.</description><subject>Applied sciences</subject><subject>Artificial intelligence</subject><subject>Computer science; control theory; systems</subject><subject>Edge Feature</subject><subject>Exact sciences and technology</subject><subject>Line Segment</subject><subject>Model Edge</subject><subject>Partial Occlusion</subject><subject>Pattern recognition. Digital image processing. Computational geometry</subject><subject>Unscented Kalman Filter</subject><issn>0302-9743</issn><issn>1611-3349</issn><isbn>3540486267</isbn><isbn>9783540486268</isbn><isbn>3540486287</isbn><isbn>3540486275</isbn><isbn>9783540486275</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2006</creationdate><recordtype>conference_proceeding</recordtype><recordid>eNpNkEtPwzAQhM1LopSe-AO5cODgsutnfCwVLykVEm3PlhPbUSBNo7gX_j1BRYK9zI6-0Uo7hNwgzBFA3yMaNIoZy_UJueJSgMgV0_KUTFAhUs6FOfsDSp-TCXBg1GjBL8kspQ8YRxiUEiZk_h5cSzfNLmSrvQ8tfXAp-GxdLFbZNjVdnRVNF7J1qHehO6RrchFdm8LsV6dk-_S4Wb7Q4u35dbkoaM_QHKj30XCRe1cK78y4VgwhdzmgR6mYqLjWCphSUpVRSRPd6CoZqpwrE_PIp-T2eLd3qXJtHFxXNcn2Q7Nzw5dl4wNKgRlzd8dcGlFXh8GW-_1nsgj2py37ry3-DcVqU-I</recordid><startdate>2006</startdate><enddate>2006</enddate><creator>Gee, Andrew P.</creator><creator>Mayol-Cuevas, Walterio</creator><general>Springer Berlin Heidelberg</general><general>Springer</general><scope>IQODW</scope></search><sort><creationdate>2006</creationdate><title>Real-Time Model-Based SLAM Using Line Segments</title><author>Gee, Andrew P. ; Mayol-Cuevas, Walterio</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-p219t-ddf9348dab4da9934c2108a801d15624c3776026656bf659fa602c5ec8369f8f3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2006</creationdate><topic>Applied sciences</topic><topic>Artificial intelligence</topic><topic>Computer science; control theory; systems</topic><topic>Edge Feature</topic><topic>Exact sciences and technology</topic><topic>Line Segment</topic><topic>Model Edge</topic><topic>Partial Occlusion</topic><topic>Pattern recognition. Digital image processing. Computational geometry</topic><topic>Unscented Kalman Filter</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Gee, Andrew P.</creatorcontrib><creatorcontrib>Mayol-Cuevas, Walterio</creatorcontrib><collection>Pascal-Francis</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Gee, Andrew P.</au><au>Mayol-Cuevas, Walterio</au><au>Zara, Jiri</au><au>Remagnino, Paolo</au><au>Bebis, George</au><au>Koracin, Darko</au><au>Boyle, Richard</au><au>Theisel, Holger</au><au>Nefian, Ara</au><au>Meenakshisundaram, Gopi</au><au>Malzbender, Tom</au><au>Parvin, Bahram</au><au>Pascucci, Valerio</au><au>Molineros, Jose</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Real-Time Model-Based SLAM Using Line Segments</atitle><btitle>Advances in Visual Computing</btitle><date>2006</date><risdate>2006</risdate><spage>354</spage><epage>363</epage><pages>354-363</pages><issn>0302-9743</issn><eissn>1611-3349</eissn><isbn>3540486267</isbn><isbn>9783540486268</isbn><isbn>3540486287</isbn><eisbn>3540486275</eisbn><eisbn>9783540486275</eisbn><abstract>Existing monocular vision-based SLAM systems favour interest point features as landmarks, but these are easily occluded and can only be reliably matched over a narrow range of viewpoints. Line segments offer an interesting alternative, as line matching is more stable with respect to viewpoint changes and lines are robust to partial occlusion. In this paper we present a model-based SLAM system that uses 3D line segments as landmarks. Unscented Kalman filters are used to initialise new line segments and generate a 3D wireframe model of the scene that can be tracked with a robust model-based tracking algorithm. Uncertainties in the camera position are fed into the initialisation of new model edges. Results show the system operating in real-time with resilience to partial occlusion. The maps of line segments generated during the SLAM process are physically meaningful and their structure is measured against the true 3D structure of the scene.</abstract><cop>Berlin, Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><doi>10.1007/11919629_37</doi><tpages>10</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0302-9743 |
| ispartof | Advances in Visual Computing, 2006, p.354-363 |
| issn | 0302-9743 1611-3349 |
| language | eng |
| recordid | cdi_springer_books_10_1007_11919629_37 |
| source | Springer Books |
| subjects | Applied sciences Artificial intelligence Computer science control theory systems Edge Feature Exact sciences and technology Line Segment Model Edge Partial Occlusion Pattern recognition. Digital image processing. Computational geometry Unscented Kalman Filter |
| title | Real-Time Model-Based SLAM Using Line Segments |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-29T12%3A21%3A21IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-pascalfrancis_sprin&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Real-Time%20Model-Based%20SLAM%20Using%20Line%20Segments&rft.btitle=Advances%20in%20Visual%20Computing&rft.au=Gee,%20Andrew%20P.&rft.date=2006&rft.spage=354&rft.epage=363&rft.pages=354-363&rft.issn=0302-9743&rft.eissn=1611-3349&rft.isbn=3540486267&rft.isbn_list=9783540486268&rft.isbn_list=3540486287&rft_id=info:doi/10.1007/11919629_37&rft_dat=%3Cpascalfrancis_sprin%3E20046609%3C/pascalfrancis_sprin%3E%3Curl%3E%3C/url%3E&rft.eisbn=3540486275&rft.eisbn_list=9783540486275&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |