Graph Laplacian Regularization for Robust Optical Flow Estimation
This paper proposes graph Laplacian regularization for robust estimation of optical flow. First, we analyze the spectral properties of dense graph Laplacians and show that dense graphs achieve a better trade-off between preserving flow discontinuities and filtering noise, compared with the usual Lap...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on image processing 2020-01, Vol.29, p.3970-3983 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 3983 |
|---|---|
| container_issue | |
| container_start_page | 3970 |
| container_title | IEEE transactions on image processing |
| container_volume | 29 |
| creator | Young, Sean I. Naman, Aous T. Taubman, David |
| description | This paper proposes graph Laplacian regularization for robust estimation of optical flow. First, we analyze the spectral properties of dense graph Laplacians and show that dense graphs achieve a better trade-off between preserving flow discontinuities and filtering noise, compared with the usual Laplacian. Using this analysis, we then propose a robust optical flow estimation method based on Gaussian graph Laplacians. We revisit the framework of iteratively reweighted least-squares from the perspective of graph edge reweighting, and employ the Welsch loss function to preserve flow discontinuities and handle occlusions. Our experiments using the Middlebury and MPI-Sintel optical flow datasets demonstrate the robustness and the efficiency of our proposed approach. |
| doi_str_mv | 10.1109/TIP.2019.2945653 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_pubmed_primary_31613756</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8864090</ieee_id><sourcerecordid>2352191226</sourcerecordid><originalsourceid>FETCH-LOGICAL-c347t-e50633fc55ab8627732c0ad388b1efa798924c04fd12bdc223aa8daa5308d39d3</originalsourceid><addsrcrecordid>eNpdkE1Lw0AQhhdRtFbvgiABL15SZ_Yr2WMpfhQKFdFz2Gw2mpJ2426C6K93tdWDpxmY5x1mHkLOECaIoK6f5g8TCqgmVHEhBdsjI1QcUwBO92MPIksz5OqIHIewAkAuUB6SI4YSWSbkiEzvvO5ek4XuWm0avUke7cvQat986r5xm6R2Pnl05RD6ZNn1jdFtctu69-Qm9M36BzkhB7Vugz3d1TF5vr15mt2ni-XdfDZdpIbxrE-tAMlYbYTQZS5pljFqQFcsz0u0tc5Urig3wOsKaVkZSpnWeaW1YJBXTFVsTK62ezvv3gYb-mLdBGPbVm-sG0JBGUiKjHKM6OU_dOUGv4nXRUpQVEipjBRsKeNdCN7WRefjT_6jQCi-9RZRb_Gtt9jpjZGL3eKhXNvqL_DrMwLnW6Cx1v6N81xyUMC-AMtsfLM</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2352191226</pqid></control><display><type>article</type><title>Graph Laplacian Regularization for Robust Optical Flow Estimation</title><source>IEEE Xplore Digital Library</source><creator>Young, Sean I. ; Naman, Aous T. ; Taubman, David</creator><creatorcontrib>Young, Sean I. ; Naman, Aous T. ; Taubman, David</creatorcontrib><description>This paper proposes graph Laplacian regularization for robust estimation of optical flow. First, we analyze the spectral properties of dense graph Laplacians and show that dense graphs achieve a better trade-off between preserving flow discontinuities and filtering noise, compared with the usual Laplacian. Using this analysis, we then propose a robust optical flow estimation method based on Gaussian graph Laplacians. We revisit the framework of iteratively reweighted least-squares from the perspective of graph edge reweighting, and employ the Welsch loss function to preserve flow discontinuities and handle occlusions. Our experiments using the Middlebury and MPI-Sintel optical flow datasets demonstrate the robustness and the efficiency of our proposed approach.</description><identifier>ISSN: 1057-7149</identifier><identifier>EISSN: 1941-0042</identifier><identifier>DOI: 10.1109/TIP.2019.2945653</identifier><identifier>PMID: 31613756</identifier><identifier>CODEN: IIPRE4</identifier><language>eng</language><publisher>United States: IEEE</publisher><subject>Computer terminals ; Eigenvalues and eigenfunctions ; Estimation ; Inverse problems ; Kernel ; Laplace equations ; Optical flow ; Optical flow (image analysis) ; Optical imaging ; Optical properties ; Optimization ; Pedestrians ; Regularization ; robust estimation ; Robustness</subject><ispartof>IEEE transactions on image processing, 2020-01, Vol.29, p.3970-3983</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c347t-e50633fc55ab8627732c0ad388b1efa798924c04fd12bdc223aa8daa5308d39d3</citedby><cites>FETCH-LOGICAL-c347t-e50633fc55ab8627732c0ad388b1efa798924c04fd12bdc223aa8daa5308d39d3</cites><orcidid>0000-0002-4304-1959 ; 0000-0002-8458-6402 ; 0000-0002-5774-7143</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8864090$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27923,27924,54757</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/8864090$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/31613756$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Young, Sean I.</creatorcontrib><creatorcontrib>Naman, Aous T.</creatorcontrib><creatorcontrib>Taubman, David</creatorcontrib><title>Graph Laplacian Regularization for Robust Optical Flow Estimation</title><title>IEEE transactions on image processing</title><addtitle>TIP</addtitle><addtitle>IEEE Trans Image Process</addtitle><description>This paper proposes graph Laplacian regularization for robust estimation of optical flow. First, we analyze the spectral properties of dense graph Laplacians and show that dense graphs achieve a better trade-off between preserving flow discontinuities and filtering noise, compared with the usual Laplacian. Using this analysis, we then propose a robust optical flow estimation method based on Gaussian graph Laplacians. We revisit the framework of iteratively reweighted least-squares from the perspective of graph edge reweighting, and employ the Welsch loss function to preserve flow discontinuities and handle occlusions. Our experiments using the Middlebury and MPI-Sintel optical flow datasets demonstrate the robustness and the efficiency of our proposed approach.</description><subject>Computer terminals</subject><subject>Eigenvalues and eigenfunctions</subject><subject>Estimation</subject><subject>Inverse problems</subject><subject>Kernel</subject><subject>Laplace equations</subject><subject>Optical flow</subject><subject>Optical flow (image analysis)</subject><subject>Optical imaging</subject><subject>Optical properties</subject><subject>Optimization</subject><subject>Pedestrians</subject><subject>Regularization</subject><subject>robust estimation</subject><subject>Robustness</subject><issn>1057-7149</issn><issn>1941-0042</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpdkE1Lw0AQhhdRtFbvgiABL15SZ_Yr2WMpfhQKFdFz2Gw2mpJ2426C6K93tdWDpxmY5x1mHkLOECaIoK6f5g8TCqgmVHEhBdsjI1QcUwBO92MPIksz5OqIHIewAkAuUB6SI4YSWSbkiEzvvO5ek4XuWm0avUke7cvQat986r5xm6R2Pnl05RD6ZNn1jdFtctu69-Qm9M36BzkhB7Vugz3d1TF5vr15mt2ni-XdfDZdpIbxrE-tAMlYbYTQZS5pljFqQFcsz0u0tc5Urig3wOsKaVkZSpnWeaW1YJBXTFVsTK62ezvv3gYb-mLdBGPbVm-sG0JBGUiKjHKM6OU_dOUGv4nXRUpQVEipjBRsKeNdCN7WRefjT_6jQCi-9RZRb_Gtt9jpjZGL3eKhXNvqL_DrMwLnW6Cx1v6N81xyUMC-AMtsfLM</recordid><startdate>20200101</startdate><enddate>20200101</enddate><creator>Young, Sean I.</creator><creator>Naman, Aous T.</creator><creator>Taubman, David</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-4304-1959</orcidid><orcidid>https://orcid.org/0000-0002-8458-6402</orcidid><orcidid>https://orcid.org/0000-0002-5774-7143</orcidid></search><sort><creationdate>20200101</creationdate><title>Graph Laplacian Regularization for Robust Optical Flow Estimation</title><author>Young, Sean I. ; Naman, Aous T. ; Taubman, David</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c347t-e50633fc55ab8627732c0ad388b1efa798924c04fd12bdc223aa8daa5308d39d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer terminals</topic><topic>Eigenvalues and eigenfunctions</topic><topic>Estimation</topic><topic>Inverse problems</topic><topic>Kernel</topic><topic>Laplace equations</topic><topic>Optical flow</topic><topic>Optical flow (image analysis)</topic><topic>Optical imaging</topic><topic>Optical properties</topic><topic>Optimization</topic><topic>Pedestrians</topic><topic>Regularization</topic><topic>robust estimation</topic><topic>Robustness</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Young, Sean I.</creatorcontrib><creatorcontrib>Naman, Aous T.</creatorcontrib><creatorcontrib>Taubman, David</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Xplore Digital Library</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>MEDLINE - Academic</collection><jtitle>IEEE transactions on image processing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Young, Sean I.</au><au>Naman, Aous T.</au><au>Taubman, David</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Graph Laplacian Regularization for Robust Optical Flow Estimation</atitle><jtitle>IEEE transactions on image processing</jtitle><stitle>TIP</stitle><addtitle>IEEE Trans Image Process</addtitle><date>2020-01-01</date><risdate>2020</risdate><volume>29</volume><spage>3970</spage><epage>3983</epage><pages>3970-3983</pages><issn>1057-7149</issn><eissn>1941-0042</eissn><coden>IIPRE4</coden><abstract>This paper proposes graph Laplacian regularization for robust estimation of optical flow. First, we analyze the spectral properties of dense graph Laplacians and show that dense graphs achieve a better trade-off between preserving flow discontinuities and filtering noise, compared with the usual Laplacian. Using this analysis, we then propose a robust optical flow estimation method based on Gaussian graph Laplacians. We revisit the framework of iteratively reweighted least-squares from the perspective of graph edge reweighting, and employ the Welsch loss function to preserve flow discontinuities and handle occlusions. Our experiments using the Middlebury and MPI-Sintel optical flow datasets demonstrate the robustness and the efficiency of our proposed approach.</abstract><cop>United States</cop><pub>IEEE</pub><pmid>31613756</pmid><doi>10.1109/TIP.2019.2945653</doi><tpages>14</tpages><orcidid>https://orcid.org/0000-0002-4304-1959</orcidid><orcidid>https://orcid.org/0000-0002-8458-6402</orcidid><orcidid>https://orcid.org/0000-0002-5774-7143</orcidid></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1057-7149 |
| ispartof | IEEE transactions on image processing, 2020-01, Vol.29, p.3970-3983 |
| issn | 1057-7149 1941-0042 |
| language | eng |
| recordid | cdi_pubmed_primary_31613756 |
| source | IEEE Xplore Digital Library |
| subjects | Computer terminals Eigenvalues and eigenfunctions Estimation Inverse problems Kernel Laplace equations Optical flow Optical flow (image analysis) Optical imaging Optical properties Optimization Pedestrians Regularization robust estimation Robustness |
| title | Graph Laplacian Regularization for Robust Optical Flow Estimation |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-10T15%3A19%3A44IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Graph%20Laplacian%20Regularization%20for%20Robust%20Optical%20Flow%20Estimation&rft.jtitle=IEEE%20transactions%20on%20image%20processing&rft.au=Young,%20Sean%20I.&rft.date=2020-01-01&rft.volume=29&rft.spage=3970&rft.epage=3983&rft.pages=3970-3983&rft.issn=1057-7149&rft.eissn=1941-0042&rft.coden=IIPRE4&rft_id=info:doi/10.1109/TIP.2019.2945653&rft_dat=%3Cproquest_RIE%3E2352191226%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2352191226&rft_id=info:pmid/31613756&rft_ieee_id=8864090&rfr_iscdi=true |