Robust 3-D Object Recognition via View-Specific Constraint
Three-dimensional (3-D) object recognition task focuses on detecting the objects of a scene and estimating their 6-DOF pose via effective feature extraction methods. Most recent feature extraction methods are based on the deep neural networks and show good performances. However, these methods requir...
Saved in:
Published in | IEEE transactions on systems, man, and cybernetics. Systems Vol. 51; no. 11; pp. 7109 - 7119 |
---|---|
Main Authors | , , , |
Format | Journal Article |
Language | English |
Published |
New York
IEEE
01.11.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Three-dimensional (3-D) object recognition task focuses on detecting the objects of a scene and estimating their 6-DOF pose via effective feature extraction methods. Most recent feature extraction methods are based on the deep neural networks and show good performances. However, these methods require rendering engine to assist in generating a large amount of training data, which need much time to converge and further lead to the block in a rapid industrial production line. Besides, for the common hand-crafted features, the lack of discriminant feature-points amongst various texture-less and surface-smooth objects can cause ambiguity in the process of feature-points matching. To address these challenges above, a hand-crafted 3-D feature descriptor with center offset and pose annotations is proposed in this article, which is called view-specific local projection statistics (VSLPSs). By relying on these annotations as seeds, a voting strategy is then used to transform the feature-points matching problem into the problem of voting an optimal model-view in the 6-DOF space. In this way, the ambiguity of feature-points matching caused by poor feature discrimination is eliminated. To the end, various experiments on three public datasets and our built 3-D bin-picking dataset demonstrate that our proposed VSLPS method performs well in comparison with the state-of-the-art. |
---|---|
AbstractList | Three-dimensional (3-D) object recognition task focuses on detecting the objects of a scene and estimating their 6-DOF pose via effective feature extraction methods. Most recent feature extraction methods are based on the deep neural networks and show good performances. However, these methods require rendering engine to assist in generating a large amount of training data, which need much time to converge and further lead to the block in a rapid industrial production line. Besides, for the common hand-crafted features, the lack of discriminant feature-points amongst various texture-less and surface-smooth objects can cause ambiguity in the process of feature-points matching. To address these challenges above, a hand-crafted 3-D feature descriptor with center offset and pose annotations is proposed in this article, which is called view-specific local projection statistics (VSLPSs). By relying on these annotations as seeds, a voting strategy is then used to transform the feature-points matching problem into the problem of voting an optimal model-view in the 6-DOF space. In this way, the ambiguity of feature-points matching caused by poor feature discrimination is eliminated. To the end, various experiments on three public datasets and our built 3-D bin-picking dataset demonstrate that our proposed VSLPS method performs well in comparison with the state-of-the-art. |
Author | Cong, Yang Tang, Yandong Liu, Hongsen Sun, Gan |
Author_xml | – sequence: 1 givenname: Hongsen orcidid: 0000-0003-1097-2535 surname: Liu fullname: Liu, Hongsen email: liuhongsen@sia.cn organization: State Key Laboratory of Robotics, Shenyang Institute of Automation, Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China – sequence: 2 givenname: Yang orcidid: 0000-0002-5102-0189 surname: Cong fullname: Cong, Yang email: congyang81@gmail.com organization: State Key Laboratory of Robotics, Shenyang Institute of Automation, Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China – sequence: 3 givenname: Gan orcidid: 0000-0003-1111-6909 surname: Sun fullname: Sun, Gan email: sungan@sia.cn organization: State Key Laboratory of Robotics, Shenyang Institute of Automation, Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China – sequence: 4 givenname: Yandong orcidid: 0000-0003-3805-7654 surname: Tang fullname: Tang, Yandong email: ytang@sia.cn organization: State Key Laboratory of Robotics, Shenyang Institute of Automation, Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China |
BookMark | eNo9kE1LAzEQhoNUsNb-APGy4HlrMtnNJt5k_YRKoa1ewyablRRNapJV_Pduaelp5vC87wzPORo57wxClwTPCMHiZr16rWeAAc9AsLICcYLGQBjPASiMjjthZ2ga4wZjTIAzitkY3S696mPKaH6fLdTG6JQtjfYfzibrXfZjm-zdmt98tTXadlZntXcxhca6dIFOu-YzmulhTtDb48O6fs7ni6eX-m6eaxA05axtGya4ItAUhhWKEwEdtApEawqmNShFCwakbKliBDNclJiqCrjmbPhR0Qm63vdug__uTUxy4_vghpMSSg5QVKLkA0X2lA4-xmA6uQ32qwl_kmC5syR3luTOkjxYGjJX-4w1xhx5LioGnNJ_5B5iYg |
CODEN | ITSMFE |
CitedBy_id | crossref_primary_10_1109_LRA_2023_3333693 crossref_primary_10_1109_TSMC_2023_3279023 crossref_primary_10_1007_s11760_020_01743_y crossref_primary_10_1109_TCYB_2021_3108165 crossref_primary_10_1109_TIE_2021_3075836 |
Cites_doi | 10.1007/s10514-015-9451-2 10.1109/ICCV.2017.413 10.1007/978-3-319-10599-4_30 10.1109/ICCVW.2009.5457637 10.1007/s11263-013-0627-y 10.1109/CVPR.2016.91 10.1007/978-3-319-46487-9_13 10.1007/978-3-642-37331-2_42 10.1109/IROS.2017.8206488 10.1109/TRO.2016.2596799 10.1016/j.cviu.2007.09.014 10.1109/TCYB.2018.2851666 10.1007/s10514-017-9691-4 10.1109/ICCV.2017.169 10.1177/0278364911401765 10.1109/TSMC.2018.2818184 10.1007/978-3-642-15558-1_26 10.1016/j.patcog.2019.03.025 10.1007/978-3-319-46448-0_2 10.1007/s11263-009-0296-z 10.1109/TIE.2015.2466555 10.1109/TPAMI.2011.206 10.1007/s11263-008-0152-6 10.1145/3147.3165 10.1007/978-3-319-65289-4_42 10.1137/080732730 10.1109/TSMC.2017.2787482 10.1007/s10514-017-9618-0 10.1007/s10514-017-9633-1 10.1023/B:VISI.0000029664.99615.94 10.1109/CVPR.2016.390 10.1007/s10514-017-9654-9 10.1109/CVPR.2018.00038 10.1109/TSMC.2019.2901955 10.1109/ICRA.2019.8793577 |
ContentType | Journal Article |
Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021 |
Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021 |
DBID | 97E RIA RIE AAYXX CITATION 7SC 7SP 7TB 8FD FR3 H8D JQ2 L7M L~C L~D |
DOI | 10.1109/TSMC.2020.2965729 |
DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Xplore CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Mechanical & Transportation Engineering Abstracts Technology Research Database Engineering Research Database Aerospace Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional |
DatabaseTitle | CrossRef Aerospace Database Technology Research Database Computer and Information Systems Abstracts – Academic Mechanical & Transportation Engineering Abstracts Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional |
DatabaseTitleList | Aerospace Database |
Database_xml | – sequence: 1 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 | 2168-2232 |
EndPage | 7119 |
ExternalDocumentID | 10_1109_TSMC_2020_2965729 8976283 |
Genre | orig-research |
GrantInformation_xml | – fundername: National Science and Technology Major Project of the Ministry of Science and Technology of China grantid: 2018AAA0102900 funderid: 10.13039/501100002855 – fundername: Nature Science Foundation of China grantid: 61722311; U1613214 funderid: 10.13039/501100001809 |
GroupedDBID | 0R~ 6IK 97E AAJGR AASAJ ABQJQ ABVLG ACGFS ACIWK AKJIK ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD HZ~ IFIPE IPLJI JAVBF M43 O9- OCL PQQKQ RIA RIE RIG RNS AAYXX CITATION 7SC 7SP 7TB 8FD FR3 H8D JQ2 L7M L~C L~D |
ID | FETCH-LOGICAL-c293t-6dda698b12a4e64b8192f2db29de46cc2bb346215d3b610604503b728c86630b3 |
IEDL.DBID | RIE |
ISSN | 2168-2216 |
IngestDate | Fri Sep 13 02:06:08 EDT 2024 Fri Aug 23 03:30:01 EDT 2024 Wed Jun 26 19:29:16 EDT 2024 |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 11 |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c293t-6dda698b12a4e64b8192f2db29de46cc2bb346215d3b610604503b728c86630b3 |
ORCID | 0000-0002-5102-0189 0000-0003-3805-7654 0000-0003-1111-6909 0000-0003-1097-2535 |
PQID | 2582247958 |
PQPubID | 75739 |
PageCount | 11 |
ParticipantIDs | proquest_journals_2582247958 ieee_primary_8976283 crossref_primary_10_1109_TSMC_2020_2965729 |
PublicationCentury | 2000 |
PublicationDate | 2021-11-01 |
PublicationDateYYYYMMDD | 2021-11-01 |
PublicationDate_xml | – month: 11 year: 2021 text: 2021-11-01 day: 01 |
PublicationDecade | 2020 |
PublicationPlace | New York |
PublicationPlace_xml | – name: New York |
PublicationTitle | IEEE transactions on systems, man, and cybernetics. Systems |
PublicationTitleAbbrev | TSMC |
PublicationYear | 2021 |
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 | ref34 ref15 ref37 ref14 ref36 ref31 Zhou (ref19) 2016; 32 ref30 ref11 ref33 ref10 ref32 ref2 ref1 ref17 ref16 ref38 Tang (ref18) Liu (ref13) 2019 Moenning (ref39) 2003 ref24 ref23 ref26 ref25 ref20 ref22 ref21 ref28 ref27 ref29 ref8 ref7 ref9 Zhang (ref12) 2019 ref4 ref3 ref6 ref5 Rios-Cabrera (ref35) ref40 |
References_xml | – ident: ref2 doi: 10.1007/s10514-015-9451-2 – ident: ref23 doi: 10.1109/ICCV.2017.413 – ident: ref30 doi: 10.1007/978-3-319-10599-4_30 – ident: ref28 doi: 10.1109/ICCVW.2009.5457637 – ident: ref25 doi: 10.1007/s11263-013-0627-y – ident: ref38 doi: 10.1109/CVPR.2016.91 – ident: ref21 doi: 10.1007/978-3-319-46487-9_13 – ident: ref31 doi: 10.1007/978-3-642-37331-2_42 – ident: ref32 doi: 10.1109/IROS.2017.8206488 – volume: 32 start-page: 1347 issue: 6 year: 2016 ident: ref19 article-title: Surface-based detection and 6-DoF pose estimation of 3-D objects in cluttered scenes publication-title: IEEE Trans. Robot. doi: 10.1109/TRO.2016.2596799 contributor: fullname: Zhou – ident: ref16 doi: 10.1016/j.cviu.2007.09.014 – ident: ref29 doi: 10.1109/TCYB.2018.2851666 – start-page: 2048 volume-title: Proc. ICCV ident: ref35 article-title: Discriminatively trained templates for 3D object detection: A real time scalable approach contributor: fullname: Rios-Cabrera – ident: ref9 doi: 10.1007/s10514-017-9691-4 – ident: ref22 doi: 10.1109/ICCV.2017.169 – ident: ref17 doi: 10.1177/0278364911401765 – ident: ref6 doi: 10.1109/TSMC.2018.2818184 – ident: ref27 doi: 10.1007/978-3-642-15558-1_26 – ident: ref33 doi: 10.1016/j.patcog.2019.03.025 – ident: ref36 doi: 10.1007/978-3-319-46448-0_2 – volume-title: L3DOC: Lifelong 3D object classification year: 2019 ident: ref13 contributor: fullname: Liu – ident: ref26 doi: 10.1007/s11263-009-0296-z – ident: ref11 doi: 10.1109/TIE.2015.2466555 – ident: ref34 doi: 10.1109/TPAMI.2011.206 – ident: ref37 doi: 10.1007/s11263-008-0152-6 – ident: ref40 doi: 10.1145/3147.3165 – ident: ref4 doi: 10.1007/978-3-319-65289-4_42 – ident: ref14 doi: 10.1137/080732730 – ident: ref1 doi: 10.1109/TSMC.2017.2787482 – start-page: 3467 volume-title: Proc. IEEE Int. Conf. Robot. Autom. ident: ref18 article-title: A textured object recognition pipeline for color and depth image data contributor: fullname: Tang – ident: ref7 doi: 10.1007/s10514-017-9618-0 – year: 2003 ident: ref39 article-title: Fast marching farthest point sampling for implicit surfaces and point clouds contributor: fullname: Moenning – ident: ref5 doi: 10.1007/s10514-017-9633-1 – ident: ref15 doi: 10.1023/B:VISI.0000029664.99615.94 – ident: ref20 doi: 10.1109/CVPR.2016.390 – ident: ref10 doi: 10.1007/s10514-017-9654-9 – ident: ref24 doi: 10.1109/CVPR.2018.00038 – ident: ref3 doi: 10.1109/TSMC.2019.2901955 – volume-title: Visual tactile fusion object clustering year: 2019 ident: ref12 contributor: fullname: Zhang – ident: ref8 doi: 10.1109/ICRA.2019.8793577 |
SSID | ssj0001286306 |
Score | 2.25891 |
Snippet | Three-dimensional (3-D) object recognition task focuses on detecting the objects of a scene and estimating their 6-DOF pose via effective feature extraction... |
SourceID | proquest crossref ieee |
SourceType | Aggregation Database Publisher |
StartPage | 7109 |
SubjectTerms | Ambiguity Annotations Artificial neural networks Datasets Feature extraction Matching Object recognition robotics bin-picking Robots Surface layers Surface texture Surface treatment Three-dimensional (3-D) object recognition view specific constraint Voting voting strategy |
Title | Robust 3-D Object Recognition via View-Specific Constraint |
URI | https://ieeexplore.ieee.org/document/8976283 https://www.proquest.com/docview/2582247958/abstract/ |
Volume | 51 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3PS8MwFH5MT3rw1xSnU3rwJLbLkjRLvclUhjAF3WS30pekMIRVXKfgX2-SdirqwUtpIYWQl_Z97-V77wM4IcL69AxVqHqK2QBFkRBzY0Iex1IbYp9zl-8Y3orBmN9M4kkDzj5rYYwxnnxmInfrz_J1oRYuVdaR1ndad7gCK5LQqlbrWz5FCualNGlXWOPba32I2SVJZ_Qw7NtgkJKIJiKuAOWXG_K6Kr9-xt7DXG_CcDm3iljyFC1KjNT7j7aN_538FmzUUDO4qPbGNjTMbAfWvzUgbML5fYGLeRmw8DK4Q5eSCe6XjKJiFrxOs-Bxat5Cr1KfT1Xg9D29qkS5C-Prq1F_ENZqCqGyLr0MhdaZSCR2acaN4Og6oeVUI0204Y49jci4sAhAM7SYSlisRxj2qFTSohKCbA9WZ8XM7ENgQywSZypTzCBX2iDmUnFOcppRolncgtPl4qbPVdOM1AcbJEmdJVJnibS2RAuabrE-B9br1IL20hxp_VnNUxo70msvieXB328dwhp1pBNfLNiG1fJlYY4saijx2G-XD_i4vPo |
link.rule.ids | 315,786,790,802,27957,27958,55109 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LS8QwEB5WPagH3-Lqqj14ErtmkzTbehMfrI9V0FW8lU6SwiLsinYV_PVO0q6KevBSWkghZNJ-30y-mQHYYYowPUMd6rYW5KBoFmJubSijKDaW0XPu4h3dK9W5k-cP0UMN9j5zYay1Xnxmm-7Wn-WboR65UNl-TNhJcDgBU4TzLCmztb5FVGIlfDNN3lJkfrpWx5g0dr932z0id5CzJk9UVFLKLyDynVV-_Y49xpzOQ3c8u1Ja8tgcFdjU7z8KN_53-gswV5HN4LDcHYtQs4MlmP1WgnAZDm6GOHopAhEeB9fogjLBzVhTNBwEr_0suO_bt9D3qc_7OnAdPn1fiWIF7k5PekedsOqnEGoC9SJUxmQqibHFM2mVRFcLLecGeWKsdPppRCEVcQAjkFiVIrbHBLZ5rGPiJQzFKkwOhgO7BgE5WSzKdKaFRamNRcxjLSXLecaZEVEddseLmz6VZTNS726wJHWWSJ0l0soSdVh2i_U5sFqnOjTG5kirD-sl5ZGTvbaTKF7_-61tmO70upfp5dnVxQbMcCdB8amDDZgsnkd2kzhEgVt-63wAJC7AUA |
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=Robust+3-D+Object+Recognition+via+View-Specific+Constraint&rft.jtitle=IEEE+transactions+on+systems%2C+man%2C+and+cybernetics.+Systems&rft.au=Liu%2C+Hongsen&rft.au=Cong%2C+Yang&rft.au=Sun%2C+Gan&rft.au=Tang%2C+Yandong&rft.date=2021-11-01&rft.issn=2168-2216&rft.eissn=2168-2232&rft.volume=51&rft.issue=11&rft.spage=7109&rft.epage=7119&rft_id=info:doi/10.1109%2FTSMC.2020.2965729&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TSMC_2020_2965729 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2168-2216&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2168-2216&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2168-2216&client=summon |