View management for lifelong visual maps

View management for lifelong visual maps

The time complexity of making observations and loop closures in a graph-based visual SLAM system is a function of the number of views stored. Clever algorithms, such as approximate nearest neighbor search, can make this function sub-linear. Despite this, over time the number of views can still grow...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Banerjee, Nandan, Connolly, Ryan C, Lisin, Dimitri, Briggs, Jimmy, Narayana, Manjunath, Munich, Mario E
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Robotics
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Banerjee, Nandan
Connolly, Ryan C
Lisin, Dimitri
Briggs, Jimmy
Narayana, Manjunath
Munich, Mario E
description The time complexity of making observations and loop closures in a graph-based visual SLAM system is a function of the number of views stored. Clever algorithms, such as approximate nearest neighbor search, can make this function sub-linear. Despite this, over time the number of views can still grow to a point at which the speed and/or accuracy of the system becomes unacceptable, especially in computation- and memory-constrained SLAM systems. However, not all views are created equal. Some views are rarely observed, because they have been created in an unusual lighting condition, or from low quality images, or in a location whose appearance has changed. These views can be removed to improve the overall performance of a SLAM system. In this paper, we propose a method for pruning views in a visual SLAM system to maintain its speed and accuracy for long term use.
doi_str_mv 10.48550/arxiv.1908.03605
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1908_03605</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1908_03605</sourcerecordid><originalsourceid>FETCH-LOGICAL-a675-71f68dbfae46c3876f7a335d3d127c9d3b9fcfefc6efc571091e2d82fba34cd93</originalsourceid><addsrcrecordid>eNotzjuLwkAUBeBpthDXH2C1KbdJnMnNvMpF1gcINmHbcDMzVwaSKIm6-u99FodTHDh8jE0FzwojJZ9hf4nnTFhuMg6KyxH7_ovhP2mxw11oQ3dMaN8nTaTQ7Ltdco7DCZv7fBg-2QdhM4TJu8esXPyW81W62S7X859NikrLVAtSxteEoVAOjFakEUB68CLXznqoLTkK5NQ9UgtuRci9yalGKJy3MGZfr9sntTr0scX-Wj3I1ZMMNzGXPB4</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>View management for lifelong visual maps</title><source>arXiv.org</source><creator>Banerjee, Nandan ; Connolly, Ryan C ; Lisin, Dimitri ; Briggs, Jimmy ; Narayana, Manjunath ; Munich, Mario E</creator><creatorcontrib>Banerjee, Nandan ; Connolly, Ryan C ; Lisin, Dimitri ; Briggs, Jimmy ; Narayana, Manjunath ; Munich, Mario E</creatorcontrib><description>The time complexity of making observations and loop closures in a graph-based visual SLAM system is a function of the number of views stored. Clever algorithms, such as approximate nearest neighbor search, can make this function sub-linear. Despite this, over time the number of views can still grow to a point at which the speed and/or accuracy of the system becomes unacceptable, especially in computation- and memory-constrained SLAM systems. However, not all views are created equal. Some views are rarely observed, because they have been created in an unusual lighting condition, or from low quality images, or in a location whose appearance has changed. These views can be removed to improve the overall performance of a SLAM system. In this paper, we propose a method for pruning views in a visual SLAM system to maintain its speed and accuracy for long term use.</description><identifier>DOI: 10.48550/arxiv.1908.03605</identifier><language>eng</language><subject>Computer Science - Robotics</subject><creationdate>2019-08</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1908.03605$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1908.03605$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Banerjee, Nandan</creatorcontrib><creatorcontrib>Connolly, Ryan C</creatorcontrib><creatorcontrib>Lisin, Dimitri</creatorcontrib><creatorcontrib>Briggs, Jimmy</creatorcontrib><creatorcontrib>Narayana, Manjunath</creatorcontrib><creatorcontrib>Munich, Mario E</creatorcontrib><title>View management for lifelong visual maps</title><description>The time complexity of making observations and loop closures in a graph-based visual SLAM system is a function of the number of views stored. Clever algorithms, such as approximate nearest neighbor search, can make this function sub-linear. Despite this, over time the number of views can still grow to a point at which the speed and/or accuracy of the system becomes unacceptable, especially in computation- and memory-constrained SLAM systems. However, not all views are created equal. Some views are rarely observed, because they have been created in an unusual lighting condition, or from low quality images, or in a location whose appearance has changed. These views can be removed to improve the overall performance of a SLAM system. In this paper, we propose a method for pruning views in a visual SLAM system to maintain its speed and accuracy for long term use.</description><subject>Computer Science - Robotics</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotzjuLwkAUBeBpthDXH2C1KbdJnMnNvMpF1gcINmHbcDMzVwaSKIm6-u99FodTHDh8jE0FzwojJZ9hf4nnTFhuMg6KyxH7_ovhP2mxw11oQ3dMaN8nTaTQ7Ltdco7DCZv7fBg-2QdhM4TJu8esXPyW81W62S7X859NikrLVAtSxteEoVAOjFakEUB68CLXznqoLTkK5NQ9UgtuRci9yalGKJy3MGZfr9sntTr0scX-Wj3I1ZMMNzGXPB4</recordid><startdate>20190809</startdate><enddate>20190809</enddate><creator>Banerjee, Nandan</creator><creator>Connolly, Ryan C</creator><creator>Lisin, Dimitri</creator><creator>Briggs, Jimmy</creator><creator>Narayana, Manjunath</creator><creator>Munich, Mario E</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20190809</creationdate><title>View management for lifelong visual maps</title><author>Banerjee, Nandan ; Connolly, Ryan C ; Lisin, Dimitri ; Briggs, Jimmy ; Narayana, Manjunath ; Munich, Mario E</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a675-71f68dbfae46c3876f7a335d3d127c9d3b9fcfefc6efc571091e2d82fba34cd93</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Computer Science - Robotics</topic><toplevel>online_resources</toplevel><creatorcontrib>Banerjee, Nandan</creatorcontrib><creatorcontrib>Connolly, Ryan C</creatorcontrib><creatorcontrib>Lisin, Dimitri</creatorcontrib><creatorcontrib>Briggs, Jimmy</creatorcontrib><creatorcontrib>Narayana, Manjunath</creatorcontrib><creatorcontrib>Munich, Mario E</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Banerjee, Nandan</au><au>Connolly, Ryan C</au><au>Lisin, Dimitri</au><au>Briggs, Jimmy</au><au>Narayana, Manjunath</au><au>Munich, Mario E</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>View management for lifelong visual maps</atitle><date>2019-08-09</date><risdate>2019</risdate><abstract>The time complexity of making observations and loop closures in a graph-based visual SLAM system is a function of the number of views stored. Clever algorithms, such as approximate nearest neighbor search, can make this function sub-linear. Despite this, over time the number of views can still grow to a point at which the speed and/or accuracy of the system becomes unacceptable, especially in computation- and memory-constrained SLAM systems. However, not all views are created equal. Some views are rarely observed, because they have been created in an unusual lighting condition, or from low quality images, or in a location whose appearance has changed. These views can be removed to improve the overall performance of a SLAM system. In this paper, we propose a method for pruning views in a visual SLAM system to maintain its speed and accuracy for long term use.</abstract><doi>10.48550/arxiv.1908.03605</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.1908.03605
ispartof
issn
language eng
recordid cdi_arxiv_primary_1908_03605
source arXiv.org
subjects Computer Science - Robotics
title View management for lifelong visual maps
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T16%3A42%3A27IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=View%20management%20for%20lifelong%20visual%20maps&rft.au=Banerjee,%20Nandan&rft.date=2019-08-09&rft_id=info:doi/10.48550/arxiv.1908.03605&rft_dat=%3Carxiv_GOX%3E1908_03605%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true