Burst Imaging for Light-Constrained Structure-From-Motion
Images captured under extremely low light conditions are noise-limited, which can cause existing robotic vision algorithms to fail. In this letter we develop an image processing technique for aiding 3D reconstruction from images acquired in low light conditions. Our technique, based on burst photogr...
Gespeichert in:
| Veröffentlicht in: | IEEE robotics and automation letters 2022-04, Vol.7 (2), p.1040-1047 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1047 |
|---|---|
| container_issue | 2 |
| container_start_page | 1040 |
| container_title | IEEE robotics and automation letters |
| container_volume | 7 |
| creator | Ravendran, Ahalya Bryson, Mitch Dansereau, Donald G. |
| description | Images captured under extremely low light conditions are noise-limited, which can cause existing robotic vision algorithms to fail. In this letter we develop an image processing technique for aiding 3D reconstruction from images acquired in low light conditions. Our technique, based on burst photography, uses direct methods for image registration within bursts of short exposure time images to improve the robustness and accuracy of feature-based structure-from-motion (SfM). We demonstrate improved SfM performance in challenging light-constrained scenes, including quantitative evaluations that show improved feature performance and camera pose estimates. Additionally, we show that our method converges more frequently to correct reconstructions than the state-of-the-art. Our method is a significant step towards allowing robots to operate in low light conditions, with potential applications to robots operating in environments such as underground mines and night time operation. |
| doi_str_mv | 10.1109/LRA.2021.3137520 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_crossref_primary_10_1109_LRA_2021_3137520</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9661324</ieee_id><sourcerecordid>2615511029</sourcerecordid><originalsourceid>FETCH-LOGICAL-c291t-ceb88e040cc250c81772c8cd3887303a598edb9cdce8b5ab62ae15a7751a4e593</originalsourceid><addsrcrecordid>eNpNkE1LAzEURYMoWGr3gpsB16l5STNJlrVYLYwIfqxDJvNap9hJTTIL_71TWsTVu4tz74NDyDWwKQAzd9XrfMoZh6kAoSRnZ2TEhVJUqLI8_5cvySSlLWMMJFfCyBEx931MuVjt3KbtNsU6xKJqN5-ZLkKXcnRth03xlmPvcx-RLmPY0eeQ29BdkYu1-0o4Od0x-Vg-vC-eaPXyuFrMK-q5gUw91lojmzHvuWReg1Lca98IrZVgwkmjsamNbzzqWrq65A5BOqUkuBlKI8bk9ri7j-G7x5TtNvSxG15aXoKUgwB-oNiR8jGkFHFt97HdufhjgdmDIzs4sgdH9uRoqNwcKy0i_uGmLEHwmfgFdTphLg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2615511029</pqid></control><display><type>article</type><title>Burst Imaging for Light-Constrained Structure-From-Motion</title><source>IEEE Electronic Library (IEL)</source><creator>Ravendran, Ahalya ; Bryson, Mitch ; Dansereau, Donald G.</creator><creatorcontrib>Ravendran, Ahalya ; Bryson, Mitch ; Dansereau, Donald G.</creatorcontrib><description>Images captured under extremely low light conditions are noise-limited, which can cause existing robotic vision algorithms to fail. In this letter we develop an image processing technique for aiding 3D reconstruction from images acquired in low light conditions. Our technique, based on burst photography, uses direct methods for image registration within bursts of short exposure time images to improve the robustness and accuracy of feature-based structure-from-motion (SfM). We demonstrate improved SfM performance in challenging light-constrained scenes, including quantitative evaluations that show improved feature performance and camera pose estimates. Additionally, we show that our method converges more frequently to correct reconstructions than the state-of-the-art. Our method is a significant step towards allowing robots to operate in low light conditions, with potential applications to robots operating in environments such as underground mines and night time operation.</description><identifier>ISSN: 2377-3766</identifier><identifier>EISSN: 2377-3766</identifier><identifier>DOI: 10.1109/LRA.2021.3137520</identifier><identifier>CODEN: IRALC6</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Algorithms ; Cameras ; Computer vision ; Computer vision for automation ; Image acquisition ; Image processing ; Image reconstruction ; Image registration ; Machine vision ; Photography ; Robot vision systems ; Robots ; Signal to noise ratio ; SLAM ; Three-dimensional displays ; Underground mines</subject><ispartof>IEEE robotics and automation letters, 2022-04, Vol.7 (2), p.1040-1047</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c291t-ceb88e040cc250c81772c8cd3887303a598edb9cdce8b5ab62ae15a7751a4e593</citedby><cites>FETCH-LOGICAL-c291t-ceb88e040cc250c81772c8cd3887303a598edb9cdce8b5ab62ae15a7751a4e593</cites><orcidid>0000-0003-2540-1639</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9661324$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9661324$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Ravendran, Ahalya</creatorcontrib><creatorcontrib>Bryson, Mitch</creatorcontrib><creatorcontrib>Dansereau, Donald G.</creatorcontrib><title>Burst Imaging for Light-Constrained Structure-From-Motion</title><title>IEEE robotics and automation letters</title><addtitle>LRA</addtitle><description>Images captured under extremely low light conditions are noise-limited, which can cause existing robotic vision algorithms to fail. In this letter we develop an image processing technique for aiding 3D reconstruction from images acquired in low light conditions. Our technique, based on burst photography, uses direct methods for image registration within bursts of short exposure time images to improve the robustness and accuracy of feature-based structure-from-motion (SfM). We demonstrate improved SfM performance in challenging light-constrained scenes, including quantitative evaluations that show improved feature performance and camera pose estimates. Additionally, we show that our method converges more frequently to correct reconstructions than the state-of-the-art. Our method is a significant step towards allowing robots to operate in low light conditions, with potential applications to robots operating in environments such as underground mines and night time operation.</description><subject>Algorithms</subject><subject>Cameras</subject><subject>Computer vision</subject><subject>Computer vision for automation</subject><subject>Image acquisition</subject><subject>Image processing</subject><subject>Image reconstruction</subject><subject>Image registration</subject><subject>Machine vision</subject><subject>Photography</subject><subject>Robot vision systems</subject><subject>Robots</subject><subject>Signal to noise ratio</subject><subject>SLAM</subject><subject>Three-dimensional displays</subject><subject>Underground mines</subject><issn>2377-3766</issn><issn>2377-3766</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpNkE1LAzEURYMoWGr3gpsB16l5STNJlrVYLYwIfqxDJvNap9hJTTIL_71TWsTVu4tz74NDyDWwKQAzd9XrfMoZh6kAoSRnZ2TEhVJUqLI8_5cvySSlLWMMJFfCyBEx931MuVjt3KbtNsU6xKJqN5-ZLkKXcnRth03xlmPvcx-RLmPY0eeQ29BdkYu1-0o4Od0x-Vg-vC-eaPXyuFrMK-q5gUw91lojmzHvuWReg1Lca98IrZVgwkmjsamNbzzqWrq65A5BOqUkuBlKI8bk9ri7j-G7x5TtNvSxG15aXoKUgwB-oNiR8jGkFHFt97HdufhjgdmDIzs4sgdH9uRoqNwcKy0i_uGmLEHwmfgFdTphLg</recordid><startdate>20220401</startdate><enddate>20220401</enddate><creator>Ravendran, Ahalya</creator><creator>Bryson, Mitch</creator><creator>Dansereau, Donald G.</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>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><orcidid>https://orcid.org/0000-0003-2540-1639</orcidid></search><sort><creationdate>20220401</creationdate><title>Burst Imaging for Light-Constrained Structure-From-Motion</title><author>Ravendran, Ahalya ; Bryson, Mitch ; Dansereau, Donald G.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c291t-ceb88e040cc250c81772c8cd3887303a598edb9cdce8b5ab62ae15a7751a4e593</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Algorithms</topic><topic>Cameras</topic><topic>Computer vision</topic><topic>Computer vision for automation</topic><topic>Image acquisition</topic><topic>Image processing</topic><topic>Image reconstruction</topic><topic>Image registration</topic><topic>Machine vision</topic><topic>Photography</topic><topic>Robot vision systems</topic><topic>Robots</topic><topic>Signal to noise ratio</topic><topic>SLAM</topic><topic>Three-dimensional displays</topic><topic>Underground mines</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Ravendran, Ahalya</creatorcontrib><creatorcontrib>Bryson, Mitch</creatorcontrib><creatorcontrib>Dansereau, Donald G.</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</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>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><jtitle>IEEE robotics and automation letters</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Ravendran, Ahalya</au><au>Bryson, Mitch</au><au>Dansereau, Donald G.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Burst Imaging for Light-Constrained Structure-From-Motion</atitle><jtitle>IEEE robotics and automation letters</jtitle><stitle>LRA</stitle><date>2022-04-01</date><risdate>2022</risdate><volume>7</volume><issue>2</issue><spage>1040</spage><epage>1047</epage><pages>1040-1047</pages><issn>2377-3766</issn><eissn>2377-3766</eissn><coden>IRALC6</coden><abstract>Images captured under extremely low light conditions are noise-limited, which can cause existing robotic vision algorithms to fail. In this letter we develop an image processing technique for aiding 3D reconstruction from images acquired in low light conditions. Our technique, based on burst photography, uses direct methods for image registration within bursts of short exposure time images to improve the robustness and accuracy of feature-based structure-from-motion (SfM). We demonstrate improved SfM performance in challenging light-constrained scenes, including quantitative evaluations that show improved feature performance and camera pose estimates. Additionally, we show that our method converges more frequently to correct reconstructions than the state-of-the-art. Our method is a significant step towards allowing robots to operate in low light conditions, with potential applications to robots operating in environments such as underground mines and night time operation.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/LRA.2021.3137520</doi><tpages>8</tpages><orcidid>https://orcid.org/0000-0003-2540-1639</orcidid></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 2377-3766 |
| ispartof | IEEE robotics and automation letters, 2022-04, Vol.7 (2), p.1040-1047 |
| issn | 2377-3766 2377-3766 |
| language | eng |
| recordid | cdi_crossref_primary_10_1109_LRA_2021_3137520 |
| source | IEEE Electronic Library (IEL) |
| subjects | Algorithms Cameras Computer vision Computer vision for automation Image acquisition Image processing Image reconstruction Image registration Machine vision Photography Robot vision systems Robots Signal to noise ratio SLAM Three-dimensional displays Underground mines |
| title | Burst Imaging for Light-Constrained Structure-From-Motion |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T08%3A28%3A17IST&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=Burst%20Imaging%20for%20Light-Constrained%20Structure-From-Motion&rft.jtitle=IEEE%20robotics%20and%20automation%20letters&rft.au=Ravendran,%20Ahalya&rft.date=2022-04-01&rft.volume=7&rft.issue=2&rft.spage=1040&rft.epage=1047&rft.pages=1040-1047&rft.issn=2377-3766&rft.eissn=2377-3766&rft.coden=IRALC6&rft_id=info:doi/10.1109/LRA.2021.3137520&rft_dat=%3Cproquest_RIE%3E2615511029%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=2615511029&rft_id=info:pmid/&rft_ieee_id=9661324&rfr_iscdi=true |