A Holistic Visual Place Recognition Approach Using Lightweight CNNs for Significant ViewPoint and Appearance Changes
This article presents a lightweight visual place recognition approach, capable of achieving high performance with low computational cost, and feasible for mobile robotics under significant viewpoint and appearance changes. Results on several benchmark datasets confirm an average boost of 13% in accu...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on robotics 2020-04, Vol.36 (2), p.561-569 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 569 |
|---|---|
| container_issue | 2 |
| container_start_page | 561 |
| container_title | IEEE transactions on robotics |
| container_volume | 36 |
| creator | Khaliq, Ahmad Ehsan, Shoaib Chen, Zetao Milford, Michael McDonald-Maier, Klaus |
| description | This article presents a lightweight visual place recognition approach, capable of achieving high performance with low computational cost, and feasible for mobile robotics under significant viewpoint and appearance changes. Results on several benchmark datasets confirm an average boost of 13% in accuracy, and 12 x average speedup relative to state-of-the-art methods. |
| doi_str_mv | 10.1109/TRO.2019.2956352 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2387070783</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8944012</ieee_id><sourcerecordid>2387070783</sourcerecordid><originalsourceid>FETCH-LOGICAL-c333t-bbb1a9cdd6b94b509961e0f8f03c94c390ae3bf284487ead43c5b9ad1a4f9b93</originalsourceid><addsrcrecordid>eNo9kN9LwzAQx4soOKfvgi8BnzsvP9o1j6OoE8Y25vQ1pGnSRWo6k47hf2_Khhzc3cP3-73jkyT3GCYYA3_ablYTAphPCM9ympGLZIQ5wymwvLiMe5aRlAIvrpObEL4ACONAR0k_Q_OutaG3Cn3acJAtWrdSabTRqmuc7W3n0Gy_951UO_QRrGvQwja7_qiHjsrlMiDTefRuo9pYJV0fg_Rx3dm4SVcPbi29dDG03EnX6HCbXBnZBn13nuNk-_K8LefpYvX6Vs4WqaKU9mlVVVhyVdd5xVmVAec51mAKA1RxpigHqWllSMFYMdWyZlRlFZc1lszwitNx8niKjd__HHToxVd38C5eFIQWU4hV0KiCk0r5LgSvjdh7-y39r8AgBrQiohUDWnFGGy0PJ4vVWv_LC84YYEL_ACF3dio</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2387070783</pqid></control><display><type>article</type><title>A Holistic Visual Place Recognition Approach Using Lightweight CNNs for Significant ViewPoint and Appearance Changes</title><source>IEEE Electronic Library (IEL)</source><creator>Khaliq, Ahmad ; Ehsan, Shoaib ; Chen, Zetao ; Milford, Michael ; McDonald-Maier, Klaus</creator><creatorcontrib>Khaliq, Ahmad ; Ehsan, Shoaib ; Chen, Zetao ; Milford, Michael ; McDonald-Maier, Klaus</creatorcontrib><description>This article presents a lightweight visual place recognition approach, capable of achieving high performance with low computational cost, and feasible for mobile robotics under significant viewpoint and appearance changes. Results on several benchmark datasets confirm an average boost of 13% in accuracy, and 12 x average speedup relative to state-of-the-art methods.</description><identifier>ISSN: 1552-3098</identifier><identifier>EISSN: 1941-0468</identifier><identifier>DOI: 10.1109/TRO.2019.2956352</identifier><identifier>CODEN: ITREAE</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Convolutional neural network (CNN) ; Encoding ; feature encoding ; Feature extraction ; Image recognition ; Image retrieval ; Lightweight ; Recognition ; robot localization ; Robotics ; Robots ; Task analysis ; vector of locally aggregated descriptors (VLADs) ; visual place recognition (VPR) ; Visualization</subject><ispartof>IEEE transactions on robotics, 2020-04, Vol.36 (2), p.561-569</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c333t-bbb1a9cdd6b94b509961e0f8f03c94c390ae3bf284487ead43c5b9ad1a4f9b93</citedby><cites>FETCH-LOGICAL-c333t-bbb1a9cdd6b94b509961e0f8f03c94c390ae3bf284487ead43c5b9ad1a4f9b93</cites><orcidid>0000-0002-7878-9369 ; 0000-0002-5162-1793 ; 0000-0001-9631-1898 ; 0000-0002-6412-8519 ; 0000-0002-5596-5008</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8944012$$EHTML$$P50$$Gieee$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids></links><search><creatorcontrib>Khaliq, Ahmad</creatorcontrib><creatorcontrib>Ehsan, Shoaib</creatorcontrib><creatorcontrib>Chen, Zetao</creatorcontrib><creatorcontrib>Milford, Michael</creatorcontrib><creatorcontrib>McDonald-Maier, Klaus</creatorcontrib><title>A Holistic Visual Place Recognition Approach Using Lightweight CNNs for Significant ViewPoint and Appearance Changes</title><title>IEEE transactions on robotics</title><addtitle>TRO</addtitle><description>This article presents a lightweight visual place recognition approach, capable of achieving high performance with low computational cost, and feasible for mobile robotics under significant viewpoint and appearance changes. Results on several benchmark datasets confirm an average boost of 13% in accuracy, and 12 x average speedup relative to state-of-the-art methods.</description><subject>Convolutional neural network (CNN)</subject><subject>Encoding</subject><subject>feature encoding</subject><subject>Feature extraction</subject><subject>Image recognition</subject><subject>Image retrieval</subject><subject>Lightweight</subject><subject>Recognition</subject><subject>robot localization</subject><subject>Robotics</subject><subject>Robots</subject><subject>Task analysis</subject><subject>vector of locally aggregated descriptors (VLADs)</subject><subject>visual place recognition (VPR)</subject><subject>Visualization</subject><issn>1552-3098</issn><issn>1941-0468</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>ESBDL</sourceid><sourceid>RIE</sourceid><recordid>eNo9kN9LwzAQx4soOKfvgi8BnzsvP9o1j6OoE8Y25vQ1pGnSRWo6k47hf2_Khhzc3cP3-73jkyT3GCYYA3_ablYTAphPCM9ympGLZIQ5wymwvLiMe5aRlAIvrpObEL4ACONAR0k_Q_OutaG3Cn3acJAtWrdSabTRqmuc7W3n0Gy_951UO_QRrGvQwja7_qiHjsrlMiDTefRuo9pYJV0fg_Rx3dm4SVcPbi29dDG03EnX6HCbXBnZBn13nuNk-_K8LefpYvX6Vs4WqaKU9mlVVVhyVdd5xVmVAec51mAKA1RxpigHqWllSMFYMdWyZlRlFZc1lszwitNx8niKjd__HHToxVd38C5eFIQWU4hV0KiCk0r5LgSvjdh7-y39r8AgBrQiohUDWnFGGy0PJ4vVWv_LC84YYEL_ACF3dio</recordid><startdate>202004</startdate><enddate>202004</enddate><creator>Khaliq, Ahmad</creator><creator>Ehsan, Shoaib</creator><creator>Chen, Zetao</creator><creator>Milford, Michael</creator><creator>McDonald-Maier, Klaus</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>ESBDL</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7TB</scope><scope>8FD</scope><scope>FR3</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0002-7878-9369</orcidid><orcidid>https://orcid.org/0000-0002-5162-1793</orcidid><orcidid>https://orcid.org/0000-0001-9631-1898</orcidid><orcidid>https://orcid.org/0000-0002-6412-8519</orcidid><orcidid>https://orcid.org/0000-0002-5596-5008</orcidid></search><sort><creationdate>202004</creationdate><title>A Holistic Visual Place Recognition Approach Using Lightweight CNNs for Significant ViewPoint and Appearance Changes</title><author>Khaliq, Ahmad ; Ehsan, Shoaib ; Chen, Zetao ; Milford, Michael ; McDonald-Maier, Klaus</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c333t-bbb1a9cdd6b94b509961e0f8f03c94c390ae3bf284487ead43c5b9ad1a4f9b93</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Convolutional neural network (CNN)</topic><topic>Encoding</topic><topic>feature encoding</topic><topic>Feature extraction</topic><topic>Image recognition</topic><topic>Image retrieval</topic><topic>Lightweight</topic><topic>Recognition</topic><topic>robot localization</topic><topic>Robotics</topic><topic>Robots</topic><topic>Task analysis</topic><topic>vector of locally aggregated descriptors (VLADs)</topic><topic>visual place recognition (VPR)</topic><topic>Visualization</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Khaliq, Ahmad</creatorcontrib><creatorcontrib>Ehsan, Shoaib</creatorcontrib><creatorcontrib>Chen, Zetao</creatorcontrib><creatorcontrib>Milford, Michael</creatorcontrib><creatorcontrib>McDonald-Maier, Klaus</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE Open Access Journals</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering 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><jtitle>IEEE transactions on robotics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Khaliq, Ahmad</au><au>Ehsan, Shoaib</au><au>Chen, Zetao</au><au>Milford, Michael</au><au>McDonald-Maier, Klaus</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Holistic Visual Place Recognition Approach Using Lightweight CNNs for Significant ViewPoint and Appearance Changes</atitle><jtitle>IEEE transactions on robotics</jtitle><stitle>TRO</stitle><date>2020-04</date><risdate>2020</risdate><volume>36</volume><issue>2</issue><spage>561</spage><epage>569</epage><pages>561-569</pages><issn>1552-3098</issn><eissn>1941-0468</eissn><coden>ITREAE</coden><abstract>This article presents a lightweight visual place recognition approach, capable of achieving high performance with low computational cost, and feasible for mobile robotics under significant viewpoint and appearance changes. Results on several benchmark datasets confirm an average boost of 13% in accuracy, and 12 x average speedup relative to state-of-the-art methods.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TRO.2019.2956352</doi><tpages>9</tpages><orcidid>https://orcid.org/0000-0002-7878-9369</orcidid><orcidid>https://orcid.org/0000-0002-5162-1793</orcidid><orcidid>https://orcid.org/0000-0001-9631-1898</orcidid><orcidid>https://orcid.org/0000-0002-6412-8519</orcidid><orcidid>https://orcid.org/0000-0002-5596-5008</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1552-3098 |
| ispartof | IEEE transactions on robotics, 2020-04, Vol.36 (2), p.561-569 |
| issn | 1552-3098 1941-0468 |
| language | eng |
| recordid | cdi_proquest_journals_2387070783 |
| source | IEEE Electronic Library (IEL) |
| subjects | Convolutional neural network (CNN) Encoding feature encoding Feature extraction Image recognition Image retrieval Lightweight Recognition robot localization Robotics Robots Task analysis vector of locally aggregated descriptors (VLADs) visual place recognition (VPR) Visualization |
| title | A Holistic Visual Place Recognition Approach Using Lightweight CNNs for Significant ViewPoint and Appearance Changes |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-06T04%3A29%3A21IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Holistic%20Visual%20Place%20Recognition%20Approach%20Using%20Lightweight%20CNNs%20for%20Significant%20ViewPoint%20and%20Appearance%20Changes&rft.jtitle=IEEE%20transactions%20on%20robotics&rft.au=Khaliq,%20Ahmad&rft.date=2020-04&rft.volume=36&rft.issue=2&rft.spage=561&rft.epage=569&rft.pages=561-569&rft.issn=1552-3098&rft.eissn=1941-0468&rft.coden=ITREAE&rft_id=info:doi/10.1109/TRO.2019.2956352&rft_dat=%3Cproquest_cross%3E2387070783%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2387070783&rft_id=info:pmid/&rft_ieee_id=8944012&rfr_iscdi=true |