Unsupervised learning of compact 3D models based on the detection of recurrent structures
In this paper we describe a novel algorithm for constructing a compact representation of 3D laser range data. Our approach extracts an alphabet of local scans from the scene. The words of this alphabet are used to replace recurrent local 3D structures, which leads to a substantial compression of the...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 2142 |
|---|---|
| container_issue | |
| container_start_page | 2137 |
| container_title | |
| container_volume | |
| creator | Ruhnke, M Steder, B Grisetti, G Burgard, W |
| description | In this paper we describe a novel algorithm for constructing a compact representation of 3D laser range data. Our approach extracts an alphabet of local scans from the scene. The words of this alphabet are used to replace recurrent local 3D structures, which leads to a substantial compression of the entire point cloud. We optimize our model in terms of complexity and accuracy by minimizing the Bayesian information criterion (BIC). Experimental evaluations on large real-world data show that our method allows robots to accurately reconstruct environments with as few as 70 words. |
| doi_str_mv | 10.1109/IROS.2010.5649730 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_5649730</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5649730</ieee_id><sourcerecordid>5649730</sourcerecordid><originalsourceid>FETCH-LOGICAL-i218t-7c00d378545a3d05c1142e6f76e21591c23fcd18021b8306b039943d2be1b053</originalsourceid><addsrcrecordid>eNpVkNtKAzEYhOMJLLUPIN7kBbb-OSeXUk-FQkHrhVdlN_lXV9rdJckKvr0rFsGrYZiPYRhCLhnMGQN3vXxaP885jFZp6YyAIzJzxjLJpdTaaHlMJpwpUYDV-uRfJuH0L1P2nMxS-gAYq4yzTk_I60ubhh7jZ5Mw0B2WsW3aN9rV1Hf7vvSZilu67wLuEq3KH6ZraX5HGjCjz83oRjaiH2LENtOU4-DzEDFdkLO63CWcHXRKNvd3m8VjsVo_LBc3q6LhzObCeIAgjFVSlSKA8mycjro2GsfZjnkuah-YBc4qK0BXIJyTIvAKWQVKTMnVb22DiNs-Nvsyfm0PP4lv2DpW8Q</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Unsupervised learning of compact 3D models based on the detection of recurrent structures</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Ruhnke, M ; Steder, B ; Grisetti, G ; Burgard, W</creator><creatorcontrib>Ruhnke, M ; Steder, B ; Grisetti, G ; Burgard, W</creatorcontrib><description>In this paper we describe a novel algorithm for constructing a compact representation of 3D laser range data. Our approach extracts an alphabet of local scans from the scene. The words of this alphabet are used to replace recurrent local 3D structures, which leads to a substantial compression of the entire point cloud. We optimize our model in terms of complexity and accuracy by minimizing the Bayesian information criterion (BIC). Experimental evaluations on large real-world data show that our method allows robots to accurately reconstruct environments with as few as 70 words.</description><identifier>ISSN: 2153-0858</identifier><identifier>ISBN: 9781424466740</identifier><identifier>ISBN: 1424466741</identifier><identifier>EISSN: 2153-0866</identifier><identifier>EISBN: 9781424466764</identifier><identifier>EISBN: 1424466768</identifier><identifier>EISBN: 142446675X</identifier><identifier>EISBN: 9781424466757</identifier><identifier>DOI: 10.1109/IROS.2010.5649730</identifier><language>eng</language><publisher>IEEE</publisher><subject>Accuracy ; Clouds ; Complexity theory ; Data models ; Feature extraction ; Solid modeling ; Three dimensional displays</subject><ispartof>2010 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2010, p.2137-2142</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/5649730$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2056,27923,54918</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5649730$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Ruhnke, M</creatorcontrib><creatorcontrib>Steder, B</creatorcontrib><creatorcontrib>Grisetti, G</creatorcontrib><creatorcontrib>Burgard, W</creatorcontrib><title>Unsupervised learning of compact 3D models based on the detection of recurrent structures</title><title>2010 IEEE/RSJ International Conference on Intelligent Robots and Systems</title><addtitle>IROS</addtitle><description>In this paper we describe a novel algorithm for constructing a compact representation of 3D laser range data. Our approach extracts an alphabet of local scans from the scene. The words of this alphabet are used to replace recurrent local 3D structures, which leads to a substantial compression of the entire point cloud. We optimize our model in terms of complexity and accuracy by minimizing the Bayesian information criterion (BIC). Experimental evaluations on large real-world data show that our method allows robots to accurately reconstruct environments with as few as 70 words.</description><subject>Accuracy</subject><subject>Clouds</subject><subject>Complexity theory</subject><subject>Data models</subject><subject>Feature extraction</subject><subject>Solid modeling</subject><subject>Three dimensional displays</subject><issn>2153-0858</issn><issn>2153-0866</issn><isbn>9781424466740</isbn><isbn>1424466741</isbn><isbn>9781424466764</isbn><isbn>1424466768</isbn><isbn>142446675X</isbn><isbn>9781424466757</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2010</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNpVkNtKAzEYhOMJLLUPIN7kBbb-OSeXUk-FQkHrhVdlN_lXV9rdJckKvr0rFsGrYZiPYRhCLhnMGQN3vXxaP885jFZp6YyAIzJzxjLJpdTaaHlMJpwpUYDV-uRfJuH0L1P2nMxS-gAYq4yzTk_I60ubhh7jZ5Mw0B2WsW3aN9rV1Hf7vvSZilu67wLuEq3KH6ZraX5HGjCjz83oRjaiH2LENtOU4-DzEDFdkLO63CWcHXRKNvd3m8VjsVo_LBc3q6LhzObCeIAgjFVSlSKA8mycjro2GsfZjnkuah-YBc4qK0BXIJyTIvAKWQVKTMnVb22DiNs-Nvsyfm0PP4lv2DpW8Q</recordid><startdate>20100101</startdate><enddate>20100101</enddate><creator>Ruhnke, M</creator><creator>Steder, B</creator><creator>Grisetti, G</creator><creator>Burgard, W</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>20100101</creationdate><title>Unsupervised learning of compact 3D models based on the detection of recurrent structures</title><author>Ruhnke, M ; Steder, B ; Grisetti, G ; Burgard, W</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i218t-7c00d378545a3d05c1142e6f76e21591c23fcd18021b8306b039943d2be1b053</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2010</creationdate><topic>Accuracy</topic><topic>Clouds</topic><topic>Complexity theory</topic><topic>Data models</topic><topic>Feature extraction</topic><topic>Solid modeling</topic><topic>Three dimensional displays</topic><toplevel>online_resources</toplevel><creatorcontrib>Ruhnke, M</creatorcontrib><creatorcontrib>Steder, B</creatorcontrib><creatorcontrib>Grisetti, G</creatorcontrib><creatorcontrib>Burgard, W</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Ruhnke, M</au><au>Steder, B</au><au>Grisetti, G</au><au>Burgard, W</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Unsupervised learning of compact 3D models based on the detection of recurrent structures</atitle><btitle>2010 IEEE/RSJ International Conference on Intelligent Robots and Systems</btitle><stitle>IROS</stitle><date>2010-01-01</date><risdate>2010</risdate><spage>2137</spage><epage>2142</epage><pages>2137-2142</pages><issn>2153-0858</issn><eissn>2153-0866</eissn><isbn>9781424466740</isbn><isbn>1424466741</isbn><eisbn>9781424466764</eisbn><eisbn>1424466768</eisbn><eisbn>142446675X</eisbn><eisbn>9781424466757</eisbn><abstract>In this paper we describe a novel algorithm for constructing a compact representation of 3D laser range data. Our approach extracts an alphabet of local scans from the scene. The words of this alphabet are used to replace recurrent local 3D structures, which leads to a substantial compression of the entire point cloud. We optimize our model in terms of complexity and accuracy by minimizing the Bayesian information criterion (BIC). Experimental evaluations on large real-world data show that our method allows robots to accurately reconstruct environments with as few as 70 words.</abstract><pub>IEEE</pub><doi>10.1109/IROS.2010.5649730</doi><tpages>6</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 2153-0858 |
| ispartof | 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2010, p.2137-2142 |
| issn | 2153-0858 2153-0866 |
| language | eng |
| recordid | cdi_ieee_primary_5649730 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Accuracy Clouds Complexity theory Data models Feature extraction Solid modeling Three dimensional displays |
| title | Unsupervised learning of compact 3D models based on the detection of recurrent structures |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T04%3A17%3A22IST&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=Unsupervised%20learning%20of%20compact%203D%20models%20based%20on%20the%20detection%20of%20recurrent%20structures&rft.btitle=2010%20IEEE/RSJ%20International%20Conference%20on%20Intelligent%20Robots%20and%20Systems&rft.au=Ruhnke,%20M&rft.date=2010-01-01&rft.spage=2137&rft.epage=2142&rft.pages=2137-2142&rft.issn=2153-0858&rft.eissn=2153-0866&rft.isbn=9781424466740&rft.isbn_list=1424466741&rft_id=info:doi/10.1109/IROS.2010.5649730&rft_dat=%3Cieee_6IE%3E5649730%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781424466764&rft.eisbn_list=1424466768&rft.eisbn_list=142446675X&rft.eisbn_list=9781424466757&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=5649730&rfr_iscdi=true |