Direct Optical-Flow-Aware Computational Framework for 3D Reconstruction
In this paper, a direct computational method is presented which combines optical flow and structure from motion (SfM) by putting the SfM problem in the framework of optical flow estimation. In other word, the optical flow is reparametrized in term of the camera's motion and scene's depth,...
Saved in:
| Published in | IEEE access Vol. 7; pp. 169518 - 169527 |
|---|---|
| Main Authors | , |
| Format | Journal Article |
| Language | English |
| Published |
Piscataway
IEEE
2019
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | In this paper, a direct computational method is presented which combines optical flow and structure from motion (SfM) by putting the SfM problem in the framework of optical flow estimation. In other word, the optical flow is reparametrized in term of the camera's motion and scene's depth, resulting in a similar variation optimization as in optical flow estimation. Meanwhile, three techniques are proposed to improve the accuracy and robustness of the direct approach, including the fast guided interpolation (FGI), the left-right consistency constraint and the soft segment constraint. Experimental results on the Middlebury dataset and KITTI2012 dataset show that the proposed approach can achieve highly-accurate 3D reconstruction with the dense and smooth surface which results in a state-of-the-art performance in optical flow. |
|---|---|
| AbstractList | In this paper, a direct computational method is presented which combines optical flow and structure from motion (SfM) by putting the SfM problem in the framework of optical flow estimation. In other word, the optical flow is reparametrized in term of the camera's motion and scene's depth, resulting in a similar variation optimization as in optical flow estimation. Meanwhile, three techniques are proposed to improve the accuracy and robustness of the direct approach, including the fast guided interpolation (FGI), the left-right consistency constraint and the soft segment constraint. Experimental results on the Middlebury dataset and KITTI2012 dataset show that the proposed approach can achieve highly-accurate 3D reconstruction with the dense and smooth surface which results in a state-of-the-art performance in optical flow. |
| Author | Chen, Pei Hu, Huijuan |
| Author_xml | – sequence: 1 givenname: Huijuan orcidid: 0000-0001-8454-0335 surname: Hu fullname: Hu, Huijuan organization: School of Data Science and Computer, Sun Yat-sen University, Guangzhou, China – sequence: 2 givenname: Pei orcidid: 0000-0002-7594-3228 surname: Chen fullname: Chen, Pei email: chenpei@mail.sysu.edu.cn organization: Guangdong Key Laboratory of Information Security Technology, Sun Yat-sen University, Guangzhou, China |
| BookMark | eNpNUctqwzAQFCWFpmm-IBdDz04lWbKlY3AeDQQCTXsWsrwqTh3LlW1C_75OHUL3ssswM8swj2hUuQoQmhE8JwTLl0Warg6HOcVEzqnkTJLkDo0piWUY8Sge_bsf0LRpjrgf0UM8GaPNsvBg2mBft4XRZbgu3TlcnLWHIHWnumt1W7hKl8Ha6xOcnf8KrPNBtAzewLiqaX1nLowndG912cD0uifoY716T1_D3X6zTRe70DAs2jA2mjBLI4IJJFRYyYEzMMBYzmgiIMZCWgGCEcw45rmQsWA24yYjnOocRxO0HXxzp4-q9sVJ-x_ldKH-AOc_lfZ9lBJUAozmPIl0wijTtjcSVAuciyyXnNus93oevGrvvjtoWnV0ne_DNooyzmMqhYh7VjSwjHdN48HevhKsLgWooQB1KUBdC-hVs0FVAMBNISQWCcfRLzsTgX0 |
| CODEN | IAECCG |
| CitedBy_id | crossref_primary_10_1109_ACCESS_2020_3045764 |
| Cites_doi | 10.1007/s11263-011-0466-7 10.1109/CVPR.2017.731 10.1007/s11263-013-0644-x 10.1007/s11263-013-0639-7 10.1109/TRO.2015.2463671 10.1137/100799988 10.1016/B978-0-08-051581-6.50070-2 10.1007/s11263-006-6616-7 10.1007/3-540-47969-4_48 10.1109/CVPR.2015.7298649 10.1109/TPAMI.2009.161 10.1109/ICCV.2007.4408903 10.1007/3-540-45103-X_81 10.1109/TPAMI.2004.54 10.1007/s11263-016-0908-3 10.1007/BF00158167 10.1007/s11263-011-0422-6 10.1007/978-3-319-24947-6_2 10.1145/1360612.1360666 10.1109/34.865186 10.1109/TPAMI.2005.44 10.1109/34.1000236 10.1016/0004-3702(81)90024-2 10.1109/ICCV.2011.6126396 10.1109/CVPR.2012.6248074 10.1109/ICCV.2001.937668 10.1109/WACV.2018.00102 10.1017/S0263574705211621 10.1038/293133a0 10.1109/ICCV.2017.42 10.1109/CCV.1988.590045 10.1023/A:1007941100561 10.1109/TIP.2008.925381 10.1109/CVPR.2017.179 10.1109/CVPR.2016.445 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019 |
| DBID | 97E ESBDL RIA RIE AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D DOA |
| DOI | 10.1109/ACCESS.2019.2954917 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Xplore CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts METADEX Technology Research Database Materials Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Directory of Open Access Journals |
| DatabaseTitle | CrossRef Materials Research Database Engineered Materials Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace METADEX Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | Materials Research Database |
| Database_xml | – sequence: 1 dbid: DOA name: Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: RIE name: IEEE Xplore url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 2169-3536 |
| EndPage | 169527 |
| ExternalDocumentID | oai_doaj_org_article_7e42d573a7424af68482a80d8bd955fb 10_1109_ACCESS_2019_2954917 8908750 |
| Genre | orig-research |
| GroupedDBID | 0R~ 4.4 5VS 6IK 97E AAJGR ABVLG ACGFS ADBBV ALMA_UNASSIGNED_HOLDINGS BCNDV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD ESBDL GROUPED_DOAJ IFIPE IPLJI JAVBF KQ8 M43 M~E O9- OCL OK1 RIA RIE RIG RNS AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c408t-6ca14f23101e728f95e54ece44d4278e6089f8e84104505d89684fb5cb152ad03 |
| IEDL.DBID | RIE |
| ISSN | 2169-3536 |
| IngestDate | Tue Oct 22 15:15:58 EDT 2024 Thu Oct 10 20:33:58 EDT 2024 Fri Aug 23 03:24:14 EDT 2024 Wed Jun 26 19:28:14 EDT 2024 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c408t-6ca14f23101e728f95e54ece44d4278e6089f8e84104505d89684fb5cb152ad03 |
| ORCID | 0000-0001-8454-0335 0000-0002-7594-3228 |
| OpenAccessLink | https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/document/8908750 |
| PQID | 2455629886 |
| PQPubID | 4845423 |
| PageCount | 10 |
| ParticipantIDs | proquest_journals_2455629886 crossref_primary_10_1109_ACCESS_2019_2954917 doaj_primary_oai_doaj_org_article_7e42d573a7424af68482a80d8bd955fb ieee_primary_8908750 |
| PublicationCentury | 2000 |
| PublicationDate | 20190000 2019-00-00 20190101 2019-01-01 |
| PublicationDateYYYYMMDD | 2019-01-01 |
| PublicationDate_xml | – year: 2019 text: 20190000 |
| PublicationDecade | 2010 |
| PublicationPlace | Piscataway |
| PublicationPlace_xml | – name: Piscataway |
| PublicationTitle | IEEE access |
| PublicationTitleAbbrev | Access |
| PublicationYear | 2019 |
| Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| References | ref35 ref13 ref12 ref36 ref14 ref31 ref30 n (ref15) 2001; 29 chen (ref25) 2017 ref11 ref32 ref10 ref1 ref39 ref17 ref38 ref16 haralock (ref2) 1991 ref19 ref18 wei (ref33) 2004 ref24 ref23 ref26 yu (ref37) 2016 brox (ref4) 2004; 3024 ref20 ref42 ref41 ref22 ref21 ref43 ref28 tao (ref34) 2002 ref29 ref8 ref7 ref9 ref3 liu (ref27) 2009 ref6 ref5 ref40 |
| References_xml | – ident: ref21 doi: 10.1007/s11263-011-0466-7 – start-page: 532 year: 2002 ident: ref34 article-title: A global matching framework for stereo computation publication-title: Proc IEEE Int Conf Comput Vis contributor: fullname: tao – ident: ref10 doi: 10.1109/CVPR.2017.731 – ident: ref8 doi: 10.1007/s11263-013-0644-x – ident: ref22 doi: 10.1007/s11263-013-0639-7 – ident: ref43 doi: 10.1109/TRO.2015.2463671 – ident: ref38 doi: 10.1137/100799988 – ident: ref35 doi: 10.1016/B978-0-08-051581-6.50070-2 – volume: 29 start-page: 1721 year: 2001 ident: ref15 article-title: The geometry of multiple images: The laws that govern the formation of multiple images of a scene and some of their applications publication-title: Ind Robot contributor: fullname: n – ident: ref5 doi: 10.1007/s11263-006-6616-7 – ident: ref20 doi: 10.1007/3-540-47969-4_48 – ident: ref41 doi: 10.1109/CVPR.2015.7298649 – year: 1991 ident: ref2 publication-title: Computer and Robot Vision contributor: fullname: haralock – ident: ref16 doi: 10.1109/TPAMI.2009.161 – ident: ref7 doi: 10.1109/ICCV.2007.4408903 – ident: ref28 doi: 10.1007/3-540-45103-X_81 – year: 2017 ident: ref25 article-title: Non-feature extraction-based dense SFM three-dimensional reconstruction method contributor: fullname: chen – ident: ref32 doi: 10.1109/TPAMI.2004.54 – ident: ref11 doi: 10.1007/s11263-016-0908-3 – volume: 3024 start-page: 25 year: 2004 ident: ref4 article-title: High accuracy optical flow estimation based on a theory for warping publication-title: Proc ECCV contributor: fullname: brox – ident: ref3 doi: 10.1007/BF00158167 – ident: ref6 doi: 10.1007/s11263-011-0422-6 – ident: ref9 doi: 10.1007/978-3-319-24947-6_2 – ident: ref26 doi: 10.1145/1360612.1360666 – ident: ref29 doi: 10.1109/34.865186 – year: 2009 ident: ref27 article-title: Beyond pixels: Exploring new representations and applications for motion analysis contributor: fullname: liu – ident: ref17 doi: 10.1109/TPAMI.2005.44 – ident: ref36 doi: 10.1109/34.1000236 – ident: ref1 doi: 10.1016/0004-3702(81)90024-2 – ident: ref23 doi: 10.1109/ICCV.2011.6126396 – ident: ref39 doi: 10.1109/CVPR.2012.6248074 – ident: ref30 doi: 10.1109/ICCV.2001.937668 – ident: ref24 doi: 10.1109/WACV.2018.00102 – ident: ref14 doi: 10.1017/S0263574705211621 – ident: ref13 doi: 10.1038/293133a0 – start-page: 1 year: 2004 ident: ref33 article-title: Region-based progressive stereo matching publication-title: Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit contributor: fullname: wei – ident: ref12 doi: 10.1109/ICCV.2017.42 – start-page: 717 year: 2016 ident: ref37 article-title: Fast guided global interpolation for depth and motion publication-title: Proc Eur Conf Comput Vis contributor: fullname: yu – ident: ref19 doi: 10.1109/CCV.1988.590045 – ident: ref42 doi: 10.1023/A:1007941100561 – ident: ref31 doi: 10.1109/TIP.2008.925381 – ident: ref40 doi: 10.1109/CVPR.2017.179 – ident: ref18 doi: 10.1109/CVPR.2016.445 |
| SSID | ssj0000816957 |
| Score | 2.1793654 |
| Snippet | In this paper, a direct computational method is presented which combines optical flow and structure from motion (SfM) by putting the SfM problem in the... |
| SourceID | doaj proquest crossref ieee |
| SourceType | Open Website Aggregation Database Publisher |
| StartPage | 169518 |
| SubjectTerms | Adaptive optics Cameras Datasets Estimation fast guided interpolation Image segmentation Interpolation Linear programming Optical flow Optical flow (image analysis) Optical imaging Optimization Pedestrians Reconstruction structure from motion the left-right consistency constraint the soft segment constraint Three-dimensional displays |
| SummonAdditionalLinks | – databaseName: Directory of Open Access Journals dbid: DOA link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV07T8MwELYQEwwIKIhAQRkYCc3jbJ_HUggVErBQqZtlJ_aE2goq9e9jO-5DYmBhTaIk_i6-h335PkJuc1SNsQwyVFRlAAIy5TtzXCxulJvoTRXk3l7f2HgCL1M63ZH68j1hHT1wB9yAGyhbyivlajhQliFgqTBvUbeCUquD983FTjEVfDAWTFAeaYbc-cFwNHIj8r1c4j7sbQWJsm0oCoz9UWLll18OwaY-JkcxS0yH3dudkD0zOyWHO9yBPfLcOav0fRFWo7P6c77Khiv1ZdJOqSGu8qX1uv0qdflpWj2mvuLc8saekUn99DEaZ1EVIWsgx2XGGlWA9WlZYXiJVlBDwTQGoPWyGYblKCwaBFdoufSmReEws5o22oVq1ebVOdmfzWfmgqSAjf9VVmuLHLQpdaFKblhrFTWWc56QuzVActGRX8hQNORCdnhKj6eMeCbkwYO4udQzV4cDzp4y2lP-Zc-E9LwJNjdB4Tn384T01yaRcZZ9yxKoS98EIrv8j0dfkQM_nG6BpU_2nSHMtUs5lvomfF0_pZ_QDg priority: 102 providerName: Directory of Open Access Journals |
| Title | Direct Optical-Flow-Aware Computational Framework for 3D Reconstruction |
| URI | https://ieeexplore.ieee.org/document/8908750 https://www.proquest.com/docview/2455629886 https://doaj.org/article/7e42d573a7424af68482a80d8bd955fb |
| Volume | 7 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT-MwEB4BJziwLA_RXUA57JGUNB3H42O3bBetBFxA4mbZzvgCaisoQtpfv7bjFgQc9hZFSTSZsT0Pj78P4EdFxrFvsCQjTImosDSxMyf4YmfCRHfDRPd2edVc3OKfO3G3BqerszDMnJrPuB8v015-O3PPsVR2Ririr4cEfV0q1Z3VWtVTIoGEEjIDCw0qdTYaj8M_xO4t1U-7WYmU7NX5JIz-TKryYSVO7mXyBS6XgnVdJff954Xtu7_vMBv_V_Id2M5xZjHqBsZXWOPpLmy9QR_cg9_dcldcz1M9u5w8zF7K0Yt55KLjesh1wmKybOAqQoRbDM-LmLO-Is_uw-3k1834osy8CqXDihZl48wAfQzsBixr8kqwQHaM2EbiDW4qUp6YMKRqIUBqSTWE3gpng7M3bTU8gI3pbMqHUCC5eNjWWk8SLdd2YGrJTeuNYC-l7MHpUuF63sFn6JR2VEp39tHRPjrbpwc_o1FWj0bs63QjKFPnqaQlY90KOTQhq0fjg2xUG6pasq0Swtse7EUDrD6Sdd-Do6WJdZ6nT7pGEQJARdR8-_yt77AZBeyKLkewEVTLxyEMWdiTlL6fpFH4D-bQ2r8 |
| link.rule.ids | 315,783,787,799,867,2109,4032,27936,27937,27938,55087 |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LTxsxEB4hONAe2vKompa2e-iRDZvNeD0-htA0UAIXkLhZtnd8oUpQG4TUX1_b6wRUeuhttdpdzc7YnofH3wfwpSLj2DdYkhGmRFRYmtiZE3yxM2Giu2Gie5tdNNNrPLsRNxtwuD4Lw8yp-Yz78TLt5bcLdx9LZUekIv56SNC3QlxNsjutta6oRAoJJWSGFhpU6mg0Hoe_iP1bqp_2sxIt2aP7SSj9mVbl2VqcHMzkNcxWonV9Jbf9-6Xtu99_oTb-r-xv4FWONItRNzR2YIPnu_DyCf7gHnzrFrzi8i5VtMvJj8VDOXowP7no2B5ypbCYrFq4ihDjFsOTImatj9iz-3A9-Xo1npaZWaF0WNGybJwZoI-h3YBlTV4JFsiOEdtIvcFNRcoTE4ZkLYRILamG0FvhbHD3pq2Gb2FzvpjzOyiQXDxua60niZZrOzC15Kb1RrCXUvbgcKVwfdcBaOiUeFRKd_bR0T4626cHx9Eo60cj-nW6EZSp82TSkrFuhRyakNej8UE2qg1VLdlWCeFtD_aiAdYfybrvwcHKxDrP1F-6RhFCQEXUvP_3W59he3o1O9fnpxffP8CLKGxXgjmAzaBm_hiCkqX9lMbiH1bg3RY |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Direct+Optical-Flow-Aware+Computational+Framework+for+3D+Reconstruction&rft.jtitle=IEEE+access&rft.au=Hu%2C+Huijuan&rft.au=Chen%2C+Pei&rft.date=2019&rft.issn=2169-3536&rft.eissn=2169-3536&rft.volume=7&rft.spage=169518&rft.epage=169527&rft_id=info:doi/10.1109%2FACCESS.2019.2954917&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_ACCESS_2019_2954917 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon |