Joint Optimization for Object Class Segmentation and Dense Stereo Reconstruction
The problems of dense stereo reconstruction and object class segmentation can both be formulated as Random Field labeling problems, in which every pixel in the image is assigned a label corresponding to either its disparity, or an object class such as road or building. While these two problems are m...
Gespeichert in:
| Veröffentlicht in: | International journal of computer vision 2012-11, Vol.100 (2), p.122-133 |
|---|---|
| Hauptverfasser: | , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 133 |
|---|---|
| container_issue | 2 |
| container_start_page | 122 |
| container_title | International journal of computer vision |
| container_volume | 100 |
| creator | Ladický, Lubor Sturgess, Paul Russell, Chris Sengupta, Sunando Bastanlar, Yalin Clocksin, William Torr, Philip H. S. |
| description | The problems of
dense stereo reconstruction
and
object class segmentation
can both be formulated as Random Field labeling problems, in which every pixel in the image is assigned a label corresponding to either its disparity, or an object class such as road or building. While these two problems are mutually informative, no attempt has been made to jointly optimize their labelings. In this work we provide a flexible framework configured via cross-validation that unifies the two problems and demonstrate that, by resolving ambiguities, which would be present in real world data if the two problems were considered separately, joint optimization of the two problems substantially improves performance. To evaluate our method, we augment the Leuven data set (
http://cms.brookes.ac.uk/research/visiongroup/files/Leuven.zip
), which is a stereo video shot from a car driving around the streets of Leuven, with 70 hand labeled object class and disparity maps. We hope that the release of these annotations will stimulate further work in the challenging domain of street-view analysis. Complete source code is publicly available (
http://cms.brookes.ac.uk/staff/Philip-Torr/ale.htm
). |
| doi_str_mv | 10.1007/s11263-011-0489-0 |
| format | Article |
| fullrecord | <record><control><sourceid>gale_proqu</sourceid><recordid>TN_cdi_proquest_journals_1419826130</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A378558159</galeid><sourcerecordid>A378558159</sourcerecordid><originalsourceid>FETCH-LOGICAL-c498t-6a7d91465ddeb2f7b9b59c425f57a69f2af3149c6597b1f77571675c2115956c3</originalsourceid><addsrcrecordid>eNp1kU9rGzEQxUVJoE7SD9DbQk89bKrRrqTV0Thp_hBwsZOz0GpHZo0tuZIMST99ZbaH5hDmMDDzezMPHiFfgV4DpfJHAmCiqSlATdtO1fQTmQGXTQ0t5WdkRhWjNRcKPpOLlLaUUtaxZkZ-PYbR52p5yON-_GPyGHzlQqyW_RZtrhY7k1K1xs0efZ62xg_VDfqE1TpjxFCt0Aafcjza0_6KnDuzS_jlX78kLz9vnxf39dPy7mExf6ptq7pcCyMHBa3gw4A9c7JXPVe2ZdxxaYRyzLgGWmUFV7IHJyWXICS3DIArLmxzSb5Ndw8x_D5iynobjtGXlxpaUB0T0NBCXU_UxuxQj96FHI0tNeB-LLbRjWU-b2THeVcuF8H3d4LCZHzNG3NMST-sV-9ZmFgbQ0oRnT7EcW_imwaqT6noKRVdUtGnVPTJEJs0qbB-g_E_2x-K_gKpHI1k</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1419826130</pqid></control><display><type>article</type><title>Joint Optimization for Object Class Segmentation and Dense Stereo Reconstruction</title><source>SpringerLink Journals - AutoHoldings</source><creator>Ladický, Lubor ; Sturgess, Paul ; Russell, Chris ; Sengupta, Sunando ; Bastanlar, Yalin ; Clocksin, William ; Torr, Philip H. S.</creator><creatorcontrib>Ladický, Lubor ; Sturgess, Paul ; Russell, Chris ; Sengupta, Sunando ; Bastanlar, Yalin ; Clocksin, William ; Torr, Philip H. S.</creatorcontrib><description>The problems of
dense stereo reconstruction
and
object class segmentation
can both be formulated as Random Field labeling problems, in which every pixel in the image is assigned a label corresponding to either its disparity, or an object class such as road or building. While these two problems are mutually informative, no attempt has been made to jointly optimize their labelings. In this work we provide a flexible framework configured via cross-validation that unifies the two problems and demonstrate that, by resolving ambiguities, which would be present in real world data if the two problems were considered separately, joint optimization of the two problems substantially improves performance. To evaluate our method, we augment the Leuven data set (
http://cms.brookes.ac.uk/research/visiongroup/files/Leuven.zip
), which is a stereo video shot from a car driving around the streets of Leuven, with 70 hand labeled object class and disparity maps. We hope that the release of these annotations will stimulate further work in the challenging domain of street-view analysis. Complete source code is publicly available (
http://cms.brookes.ac.uk/staff/Philip-Torr/ale.htm
).</description><identifier>ISSN: 0920-5691</identifier><identifier>EISSN: 1573-1405</identifier><identifier>DOI: 10.1007/s11263-011-0489-0</identifier><language>eng</language><publisher>Boston: Springer US</publisher><subject>Algorithms ; Artificial Intelligence ; Cameras ; Computer Imaging ; Computer Science ; Datasets ; Image Processing and Computer Vision ; International ; Labeling ; Optimization ; Pattern Recognition ; Pattern Recognition and Graphics ; Studies ; Vision ; Vision systems</subject><ispartof>International journal of computer vision, 2012-11, Vol.100 (2), p.122-133</ispartof><rights>Springer Science+Business Media, LLC 2011</rights><rights>COPYRIGHT 2012 Springer</rights><rights>Springer Science+Business Media, LLC 2012</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c498t-6a7d91465ddeb2f7b9b59c425f57a69f2af3149c6597b1f77571675c2115956c3</citedby><cites>FETCH-LOGICAL-c498t-6a7d91465ddeb2f7b9b59c425f57a69f2af3149c6597b1f77571675c2115956c3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s11263-011-0489-0$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s11263-011-0489-0$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,777,781,27905,27906,41469,42538,51300</link.rule.ids></links><search><creatorcontrib>Ladický, Lubor</creatorcontrib><creatorcontrib>Sturgess, Paul</creatorcontrib><creatorcontrib>Russell, Chris</creatorcontrib><creatorcontrib>Sengupta, Sunando</creatorcontrib><creatorcontrib>Bastanlar, Yalin</creatorcontrib><creatorcontrib>Clocksin, William</creatorcontrib><creatorcontrib>Torr, Philip H. S.</creatorcontrib><title>Joint Optimization for Object Class Segmentation and Dense Stereo Reconstruction</title><title>International journal of computer vision</title><addtitle>Int J Comput Vis</addtitle><description>The problems of
dense stereo reconstruction
and
object class segmentation
can both be formulated as Random Field labeling problems, in which every pixel in the image is assigned a label corresponding to either its disparity, or an object class such as road or building. While these two problems are mutually informative, no attempt has been made to jointly optimize their labelings. In this work we provide a flexible framework configured via cross-validation that unifies the two problems and demonstrate that, by resolving ambiguities, which would be present in real world data if the two problems were considered separately, joint optimization of the two problems substantially improves performance. To evaluate our method, we augment the Leuven data set (
http://cms.brookes.ac.uk/research/visiongroup/files/Leuven.zip
), which is a stereo video shot from a car driving around the streets of Leuven, with 70 hand labeled object class and disparity maps. We hope that the release of these annotations will stimulate further work in the challenging domain of street-view analysis. Complete source code is publicly available (
http://cms.brookes.ac.uk/staff/Philip-Torr/ale.htm
).</description><subject>Algorithms</subject><subject>Artificial Intelligence</subject><subject>Cameras</subject><subject>Computer Imaging</subject><subject>Computer Science</subject><subject>Datasets</subject><subject>Image Processing and Computer Vision</subject><subject>International</subject><subject>Labeling</subject><subject>Optimization</subject><subject>Pattern Recognition</subject><subject>Pattern Recognition and Graphics</subject><subject>Studies</subject><subject>Vision</subject><subject>Vision systems</subject><issn>0920-5691</issn><issn>1573-1405</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2012</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><recordid>eNp1kU9rGzEQxUVJoE7SD9DbQk89bKrRrqTV0Thp_hBwsZOz0GpHZo0tuZIMST99ZbaH5hDmMDDzezMPHiFfgV4DpfJHAmCiqSlATdtO1fQTmQGXTQ0t5WdkRhWjNRcKPpOLlLaUUtaxZkZ-PYbR52p5yON-_GPyGHzlQqyW_RZtrhY7k1K1xs0efZ62xg_VDfqE1TpjxFCt0Aafcjza0_6KnDuzS_jlX78kLz9vnxf39dPy7mExf6ptq7pcCyMHBa3gw4A9c7JXPVe2ZdxxaYRyzLgGWmUFV7IHJyWXICS3DIArLmxzSb5Ndw8x_D5iynobjtGXlxpaUB0T0NBCXU_UxuxQj96FHI0tNeB-LLbRjWU-b2THeVcuF8H3d4LCZHzNG3NMST-sV-9ZmFgbQ0oRnT7EcW_imwaqT6noKRVdUtGnVPTJEJs0qbB-g_E_2x-K_gKpHI1k</recordid><startdate>20121101</startdate><enddate>20121101</enddate><creator>Ladický, Lubor</creator><creator>Sturgess, Paul</creator><creator>Russell, Chris</creator><creator>Sengupta, Sunando</creator><creator>Bastanlar, Yalin</creator><creator>Clocksin, William</creator><creator>Torr, Philip H. S.</creator><general>Springer US</general><general>Springer</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><scope>ISR</scope><scope>3V.</scope><scope>7SC</scope><scope>7WY</scope><scope>7WZ</scope><scope>7XB</scope><scope>87Z</scope><scope>8AL</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>8FK</scope><scope>8FL</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BEZIV</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FRNLG</scope><scope>F~G</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>JQ2</scope><scope>K60</scope><scope>K6~</scope><scope>K7-</scope><scope>L.-</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>M0C</scope><scope>M0N</scope><scope>P5Z</scope><scope>P62</scope><scope>PQBIZ</scope><scope>PQBZA</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PYYUZ</scope><scope>Q9U</scope></search><sort><creationdate>20121101</creationdate><title>Joint Optimization for Object Class Segmentation and Dense Stereo Reconstruction</title><author>Ladický, Lubor ; Sturgess, Paul ; Russell, Chris ; Sengupta, Sunando ; Bastanlar, Yalin ; Clocksin, William ; Torr, Philip H. S.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c498t-6a7d91465ddeb2f7b9b59c425f57a69f2af3149c6597b1f77571675c2115956c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2012</creationdate><topic>Algorithms</topic><topic>Artificial Intelligence</topic><topic>Cameras</topic><topic>Computer Imaging</topic><topic>Computer Science</topic><topic>Datasets</topic><topic>Image Processing and Computer Vision</topic><topic>International</topic><topic>Labeling</topic><topic>Optimization</topic><topic>Pattern Recognition</topic><topic>Pattern Recognition and Graphics</topic><topic>Studies</topic><topic>Vision</topic><topic>Vision systems</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Ladický, Lubor</creatorcontrib><creatorcontrib>Sturgess, Paul</creatorcontrib><creatorcontrib>Russell, Chris</creatorcontrib><creatorcontrib>Sengupta, Sunando</creatorcontrib><creatorcontrib>Bastanlar, Yalin</creatorcontrib><creatorcontrib>Clocksin, William</creatorcontrib><creatorcontrib>Torr, Philip H. S.</creatorcontrib><collection>CrossRef</collection><collection>Gale In Context: Science</collection><collection>ProQuest Central (Corporate)</collection><collection>Computer and Information Systems Abstracts</collection><collection>ABI/INFORM Collection</collection><collection>ABI/INFORM Global (PDF only)</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>ABI/INFORM Global (Alumni Edition)</collection><collection>Computing Database (Alumni Edition)</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ABI/INFORM Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>Advanced Technologies & Aerospace Collection</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Business Premium Collection</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>Business Premium Collection (Alumni)</collection><collection>ABI/INFORM Global (Corporate)</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Computer Science Collection</collection><collection>ProQuest Business Collection (Alumni Edition)</collection><collection>ProQuest Business Collection</collection><collection>Computer Science Database</collection><collection>ABI/INFORM Professional Advanced</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>ABI/INFORM Global</collection><collection>Computing Database</collection><collection>Advanced Technologies & Aerospace Database</collection><collection>ProQuest Advanced Technologies & Aerospace Collection</collection><collection>ProQuest One Business</collection><collection>ProQuest One Business (Alumni)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ABI/INFORM Collection China</collection><collection>ProQuest Central Basic</collection><jtitle>International journal of computer vision</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Ladický, Lubor</au><au>Sturgess, Paul</au><au>Russell, Chris</au><au>Sengupta, Sunando</au><au>Bastanlar, Yalin</au><au>Clocksin, William</au><au>Torr, Philip H. S.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Joint Optimization for Object Class Segmentation and Dense Stereo Reconstruction</atitle><jtitle>International journal of computer vision</jtitle><stitle>Int J Comput Vis</stitle><date>2012-11-01</date><risdate>2012</risdate><volume>100</volume><issue>2</issue><spage>122</spage><epage>133</epage><pages>122-133</pages><issn>0920-5691</issn><eissn>1573-1405</eissn><abstract>The problems of
dense stereo reconstruction
and
object class segmentation
can both be formulated as Random Field labeling problems, in which every pixel in the image is assigned a label corresponding to either its disparity, or an object class such as road or building. While these two problems are mutually informative, no attempt has been made to jointly optimize their labelings. In this work we provide a flexible framework configured via cross-validation that unifies the two problems and demonstrate that, by resolving ambiguities, which would be present in real world data if the two problems were considered separately, joint optimization of the two problems substantially improves performance. To evaluate our method, we augment the Leuven data set (
http://cms.brookes.ac.uk/research/visiongroup/files/Leuven.zip
), which is a stereo video shot from a car driving around the streets of Leuven, with 70 hand labeled object class and disparity maps. We hope that the release of these annotations will stimulate further work in the challenging domain of street-view analysis. Complete source code is publicly available (
http://cms.brookes.ac.uk/staff/Philip-Torr/ale.htm
).</abstract><cop>Boston</cop><pub>Springer US</pub><doi>10.1007/s11263-011-0489-0</doi><tpages>12</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0920-5691 |
| ispartof | International journal of computer vision, 2012-11, Vol.100 (2), p.122-133 |
| issn | 0920-5691 1573-1405 |
| language | eng |
| recordid | cdi_proquest_journals_1419826130 |
| source | SpringerLink Journals - AutoHoldings |
| subjects | Algorithms Artificial Intelligence Cameras Computer Imaging Computer Science Datasets Image Processing and Computer Vision International Labeling Optimization Pattern Recognition Pattern Recognition and Graphics Studies Vision Vision systems |
| title | Joint Optimization for Object Class Segmentation and Dense Stereo Reconstruction |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-17T22%3A26%3A34IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_proqu&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Joint%20Optimization%20for%20Object%20Class%20Segmentation%20and%20Dense%20Stereo%20Reconstruction&rft.jtitle=International%20journal%20of%20computer%20vision&rft.au=Ladick%C3%BD,%20Lubor&rft.date=2012-11-01&rft.volume=100&rft.issue=2&rft.spage=122&rft.epage=133&rft.pages=122-133&rft.issn=0920-5691&rft.eissn=1573-1405&rft_id=info:doi/10.1007/s11263-011-0489-0&rft_dat=%3Cgale_proqu%3EA378558159%3C/gale_proqu%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1419826130&rft_id=info:pmid/&rft_galeid=A378558159&rfr_iscdi=true |