Size Does Matter: Improving Object Recognition and 3D Reconstruction with Cross-Media Analysis of Image Clusters
Identifieur interne : 000210 ( Main/Exploration ); précédent : 000209; suivant : 000211Size Does Matter: Improving Object Recognition and 3D Reconstruction with Cross-Media Analysis of Image Clusters
Auteurs : Stephan Gammeter [Suisse] ; Till Quack [Suisse] ; David Tingdahl [Belgique] ; Luc Van Gool [Suisse]Source :
- Lecture Notes in Computer Science [ 0302-9743 ]
Abstract
Abstract: Most of the recent work on image-based object recognition and 3D reconstruction has focused on improving the underlying algorithms. In this paper we present a method to automatically improve the quality of the reference database, which, as we will show, also affects recognition and reconstruction performances significantly. Starting out from a reference database of clustered images we expand small clusters. This is done by exploiting cross-media information, which allows for crawling of additional images. For large clusters redundant information is removed by scene analysis. We show how these techniques make object recognition and 3D reconstruction both more efficient and more precise - we observed up to 14.8% improvement for the recognition task. Furthermore, the methods are completely data-driven and fully automatic.
Url:
DOI: 10.1007/978-3-642-15549-9_53
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000399
- to stream Istex, to step Curation: 000399
- to stream Istex, to step Checkpoint: 000139
- to stream Main, to step Merge: 000209
- to stream Main, to step Curation: 000210
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Size Does Matter: Improving Object Recognition and 3D Reconstruction with Cross-Media Analysis of Image Clusters</title><author><name sortKey="Gammeter, Stephan" sort="Gammeter, Stephan" uniqKey="Gammeter S" first="Stephan" last="Gammeter">Stephan Gammeter</name></author><author><name sortKey="Quack, Till" sort="Quack, Till" uniqKey="Quack T" first="Till" last="Quack">Till Quack</name></author><author><name sortKey="Tingdahl, David" sort="Tingdahl, David" uniqKey="Tingdahl D" first="David" last="Tingdahl">David Tingdahl</name></author><author><name sortKey="Van Gool, Luc" sort="Van Gool, Luc" uniqKey="Van Gool L" first="Luc" last="Van Gool">Luc Van Gool</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:F010BB5C335677A88726C68AF0EC082316831FF3</idno><date when="2010" year="2010">2010</date><idno type="doi">10.1007/978-3-642-15549-9_53</idno><idno type="url">https://api.istex.fr/ark:/67375/HCB-BC0JQ01W-G/fulltext.pdf</idno><idno type="wicri:Area/Istex/Corpus">000399</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">000399</idno><idno type="wicri:Area/Istex/Curation">000399</idno><idno type="wicri:Area/Istex/Checkpoint">000139</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">000139</idno><idno type="wicri:doubleKey">0302-9743:2010:Gammeter S:size:does:matter</idno><idno type="wicri:Area/Main/Merge">000209</idno><idno type="wicri:Area/Main/Curation">000210</idno><idno type="wicri:Area/Main/Exploration">000210</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Size Does Matter: Improving Object Recognition and 3D Reconstruction with Cross-Media Analysis of Image Clusters</title><author><name sortKey="Gammeter, Stephan" sort="Gammeter, Stephan" uniqKey="Gammeter S" first="Stephan" last="Gammeter">Stephan Gammeter</name><affiliation></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Suisse</country></affiliation></author><author><name sortKey="Quack, Till" sort="Quack, Till" uniqKey="Quack T" first="Till" last="Quack">Till Quack</name><affiliation></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Suisse</country></affiliation></author><author><name sortKey="Tingdahl, David" sort="Tingdahl, David" uniqKey="Tingdahl D" first="David" last="Tingdahl">David Tingdahl</name><affiliation></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Belgique</country></affiliation></author><author><name sortKey="Van Gool, Luc" sort="Van Gool, Luc" uniqKey="Van Gool L" first="Luc" last="Van Gool">Luc Van Gool</name><affiliation></affiliation><affiliation></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Suisse</country></affiliation></author></analytic><monogr></monogr><series><title level="s" type="main" xml:lang="en">Lecture Notes in Computer Science</title><idno type="ISSN">0302-9743</idno><idno type="eISSN">1611-3349</idno><idno type="ISSN">0302-9743</idno></series></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0302-9743</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Abstract: Most of the recent work on image-based object recognition and 3D reconstruction has focused on improving the underlying algorithms. In this paper we present a method to automatically improve the quality of the reference database, which, as we will show, also affects recognition and reconstruction performances significantly. Starting out from a reference database of clustered images we expand small clusters. This is done by exploiting cross-media information, which allows for crawling of additional images. For large clusters redundant information is removed by scene analysis. We show how these techniques make object recognition and 3D reconstruction both more efficient and more precise - we observed up to 14.8% improvement for the recognition task. Furthermore, the methods are completely data-driven and fully automatic.</div></front></TEI><affiliations><list><country><li>Belgique</li><li>Suisse</li></country></list><tree><country name="Suisse"><noRegion><name sortKey="Gammeter, Stephan" sort="Gammeter, Stephan" uniqKey="Gammeter S" first="Stephan" last="Gammeter">Stephan Gammeter</name></noRegion><name sortKey="Quack, Till" sort="Quack, Till" uniqKey="Quack T" first="Till" last="Quack">Till Quack</name><name sortKey="Van Gool, Luc" sort="Van Gool, Luc" uniqKey="Van Gool L" first="Luc" last="Van Gool">Luc Van Gool</name></country><country name="Belgique"><noRegion><name sortKey="Tingdahl, David" sort="Tingdahl, David" uniqKey="Tingdahl D" first="David" last="Tingdahl">David Tingdahl</name></noRegion></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Europe/France/explor/NotreDameDeParisV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000210 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000210 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Europe/France
|area= NotreDameDeParisV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= ISTEX:F010BB5C335677A88726C68AF0EC082316831FF3
|texte= Size Does Matter: Improving Object Recognition and 3D Reconstruction with Cross-Media Analysis of Image Clusters
}}
| This area was generated with Dilib version V0.6.33. |  |