Three-dimensional scene flow
Scene flow is the three-dimensional motion field of points in the world, just as optical flow is the two-dimensional motion field of points in an image. Any optical flow is simply the projection of the scene flow onto the image plane of a camera. We present a framework for the computation of dense,...
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 | 729 vol.2 |
|---|---|
| container_issue | |
| container_start_page | 722 |
| container_title | |
| container_volume | 2 |
| creator | Vedula, S. Baker, S. Rander, P. Collins, R. Kanade, T. |
| description | Scene flow is the three-dimensional motion field of points in the world, just as optical flow is the two-dimensional motion field of points in an image. Any optical flow is simply the projection of the scene flow onto the image plane of a camera. We present a framework for the computation of dense, non-rigid scene flow from optical flow. Our approach leads to straightforward linear algorithms and a classification of the task into three major scenarios: complete instantaneous knowledge of the scene structure; knowledge only of correspondence information; and no knowledge of the scene structure. We also show that multiple estimates of the normal flow cannot be used to estimate dense scene flow directly without some form of smoothing or regularization. |
| doi_str_mv | 10.1109/ICCV.1999.790293 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>pascalfrancis_6IE</sourceid><recordid>TN_cdi_pascalfrancis_primary_1536971</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>790293</ieee_id><sourcerecordid>1536971</sourcerecordid><originalsourceid>FETCH-LOGICAL-i116t-2b1d8d0c745000f6e737f55c2b04ed156d8d3c51de2d12a39d5798c195c699973</originalsourceid><addsrcrecordid>eNo9T01LAzEUDIig1L0X8dCD113zkn3JvqMsfhQKXmqvJU1eMLLdlo0g_nsDK85lDjPMhxBLkA2ApId13-8aIKLGklSkL0RFtpPWEEowrboSVc6fsqBFQCOvxd32Y2KuQzrymNNpdMMqex55FYfT9424jG7IXP3xQrw_P23713rz9rLuHzd1AjBftTpA6IL0tsWSHA1bbSOiVwfZcig9RdUeIbAKoJymgJY6D4TelK1WL8T9nHt22bshTm70Ke_PUzq66WcPqA1ZKLbb2ZaY-V-dn-pf0TVGdg</addsrcrecordid><sourcetype>Index Database</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Three-dimensional scene flow</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Vedula, S. ; Baker, S. ; Rander, P. ; Collins, R. ; Kanade, T.</creator><creatorcontrib>Vedula, S. ; Baker, S. ; Rander, P. ; Collins, R. ; Kanade, T.</creatorcontrib><description>Scene flow is the three-dimensional motion field of points in the world, just as optical flow is the two-dimensional motion field of points in an image. Any optical flow is simply the projection of the scene flow onto the image plane of a camera. We present a framework for the computation of dense, non-rigid scene flow from optical flow. Our approach leads to straightforward linear algorithms and a classification of the task into three major scenarios: complete instantaneous knowledge of the scene structure; knowledge only of correspondence information; and no knowledge of the scene structure. We also show that multiple estimates of the normal flow cannot be used to estimate dense scene flow directly without some form of smoothing or regularization.</description><identifier>ISBN: 9780769501642</identifier><identifier>ISBN: 0769501648</identifier><identifier>DOI: 10.1109/ICCV.1999.790293</identifier><language>eng</language><publisher>Los Alamitos CA: IEEE</publisher><subject>Applied sciences ; Artificial intelligence ; Cameras ; Computer science; control theory; systems ; Ear ; Exact sciences and technology ; Image motion analysis ; Layout ; Motion estimation ; Neutron spin echo ; Optical computing ; Pattern recognition. Digital image processing. Computational geometry ; Read only memory ; Robots ; Smoothing methods</subject><ispartof>Proceedings of the Seventh IEEE International Conference on Computer Vision, 1999, Vol.2, p.722-729 vol.2</ispartof><rights>2000 INIST-CNRS</rights><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/790293$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,4050,4051,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/790293$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=1536971$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><creatorcontrib>Vedula, S.</creatorcontrib><creatorcontrib>Baker, S.</creatorcontrib><creatorcontrib>Rander, P.</creatorcontrib><creatorcontrib>Collins, R.</creatorcontrib><creatorcontrib>Kanade, T.</creatorcontrib><title>Three-dimensional scene flow</title><title>Proceedings of the Seventh IEEE International Conference on Computer Vision</title><addtitle>ICCV</addtitle><description>Scene flow is the three-dimensional motion field of points in the world, just as optical flow is the two-dimensional motion field of points in an image. Any optical flow is simply the projection of the scene flow onto the image plane of a camera. We present a framework for the computation of dense, non-rigid scene flow from optical flow. Our approach leads to straightforward linear algorithms and a classification of the task into three major scenarios: complete instantaneous knowledge of the scene structure; knowledge only of correspondence information; and no knowledge of the scene structure. We also show that multiple estimates of the normal flow cannot be used to estimate dense scene flow directly without some form of smoothing or regularization.</description><subject>Applied sciences</subject><subject>Artificial intelligence</subject><subject>Cameras</subject><subject>Computer science; control theory; systems</subject><subject>Ear</subject><subject>Exact sciences and technology</subject><subject>Image motion analysis</subject><subject>Layout</subject><subject>Motion estimation</subject><subject>Neutron spin echo</subject><subject>Optical computing</subject><subject>Pattern recognition. Digital image processing. Computational geometry</subject><subject>Read only memory</subject><subject>Robots</subject><subject>Smoothing methods</subject><isbn>9780769501642</isbn><isbn>0769501648</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>1999</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNo9T01LAzEUDIig1L0X8dCD113zkn3JvqMsfhQKXmqvJU1eMLLdlo0g_nsDK85lDjPMhxBLkA2ApId13-8aIKLGklSkL0RFtpPWEEowrboSVc6fsqBFQCOvxd32Y2KuQzrymNNpdMMqex55FYfT9424jG7IXP3xQrw_P23713rz9rLuHzd1AjBftTpA6IL0tsWSHA1bbSOiVwfZcig9RdUeIbAKoJymgJY6D4TelK1WL8T9nHt22bshTm70Ke_PUzq66WcPqA1ZKLbb2ZaY-V-dn-pf0TVGdg</recordid><startdate>1999</startdate><enddate>1999</enddate><creator>Vedula, S.</creator><creator>Baker, S.</creator><creator>Rander, P.</creator><creator>Collins, R.</creator><creator>Kanade, T.</creator><general>IEEE</general><general>IEEE Computer Society</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope><scope>IQODW</scope></search><sort><creationdate>1999</creationdate><title>Three-dimensional scene flow</title><author>Vedula, S. ; Baker, S. ; Rander, P. ; Collins, R. ; Kanade, T.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i116t-2b1d8d0c745000f6e737f55c2b04ed156d8d3c51de2d12a39d5798c195c699973</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>1999</creationdate><topic>Applied sciences</topic><topic>Artificial intelligence</topic><topic>Cameras</topic><topic>Computer science; control theory; systems</topic><topic>Ear</topic><topic>Exact sciences and technology</topic><topic>Image motion analysis</topic><topic>Layout</topic><topic>Motion estimation</topic><topic>Neutron spin echo</topic><topic>Optical computing</topic><topic>Pattern recognition. Digital image processing. Computational geometry</topic><topic>Read only memory</topic><topic>Robots</topic><topic>Smoothing methods</topic><toplevel>online_resources</toplevel><creatorcontrib>Vedula, S.</creatorcontrib><creatorcontrib>Baker, S.</creatorcontrib><creatorcontrib>Rander, P.</creatorcontrib><creatorcontrib>Collins, R.</creatorcontrib><creatorcontrib>Kanade, T.</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><collection>Pascal-Francis</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Vedula, S.</au><au>Baker, S.</au><au>Rander, P.</au><au>Collins, R.</au><au>Kanade, T.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Three-dimensional scene flow</atitle><btitle>Proceedings of the Seventh IEEE International Conference on Computer Vision</btitle><stitle>ICCV</stitle><date>1999</date><risdate>1999</risdate><volume>2</volume><spage>722</spage><epage>729 vol.2</epage><pages>722-729 vol.2</pages><isbn>9780769501642</isbn><isbn>0769501648</isbn><abstract>Scene flow is the three-dimensional motion field of points in the world, just as optical flow is the two-dimensional motion field of points in an image. Any optical flow is simply the projection of the scene flow onto the image plane of a camera. We present a framework for the computation of dense, non-rigid scene flow from optical flow. Our approach leads to straightforward linear algorithms and a classification of the task into three major scenarios: complete instantaneous knowledge of the scene structure; knowledge only of correspondence information; and no knowledge of the scene structure. We also show that multiple estimates of the normal flow cannot be used to estimate dense scene flow directly without some form of smoothing or regularization.</abstract><cop>Los Alamitos CA</cop><pub>IEEE</pub><doi>10.1109/ICCV.1999.790293</doi><tpages>8</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISBN: 9780769501642 |
| ispartof | Proceedings of the Seventh IEEE International Conference on Computer Vision, 1999, Vol.2, p.722-729 vol.2 |
| issn | |
| language | eng |
| recordid | cdi_pascalfrancis_primary_1536971 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Applied sciences Artificial intelligence Cameras Computer science control theory systems Ear Exact sciences and technology Image motion analysis Layout Motion estimation Neutron spin echo Optical computing Pattern recognition. Digital image processing. Computational geometry Read only memory Robots Smoothing methods |
| title | Three-dimensional scene flow |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-28T19%3A00%3A45IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-pascalfrancis_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Three-dimensional%20scene%20flow&rft.btitle=Proceedings%20of%20the%20Seventh%20IEEE%20International%20Conference%20on%20Computer%20Vision&rft.au=Vedula,%20S.&rft.date=1999&rft.volume=2&rft.spage=722&rft.epage=729%20vol.2&rft.pages=722-729%20vol.2&rft.isbn=9780769501642&rft.isbn_list=0769501648&rft_id=info:doi/10.1109/ICCV.1999.790293&rft_dat=%3Cpascalfrancis_6IE%3E1536971%3C/pascalfrancis_6IE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=790293&rfr_iscdi=true |