Generating the initial hypothesis using perspective invariants for a 2D image and 3D model matching
Identifieur interne : 000544 ( Crin/Corpus ); précédent : 000543; suivant : 000545Generating the initial hypothesis using perspective invariants for a 2D image and 3D model matching
Auteurs : L. Quan ; R. Mohr ; E. ThirionSource :
English descriptors
- KwdEn :
Abstract
In this paper, we present how to generate the initial matching hypothesis for a model-based monocular vision system. The primitive shape description of images is a set of line segments and the model is automatically constructed from a sequence of stereo views. The key points of our approach are the use of vanishing points and other perspective invariants such as colinearity, connectivity and the use of double ratios to get rid of matching ambiguities.
Links to Exploration step
CRIN:quan88aLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="507">Generating the initial hypothesis using perspective invariants for a 2D image and 3D model matching</title>
</titleStmt>
<publicationStmt><idno type="RBID">CRIN:quan88a</idno>
<date when="1988" year="1988">1988</date>
<idno type="wicri:Area/Crin/Corpus">000544</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Generating the initial hypothesis using perspective invariants for a 2D image and 3D model matching</title>
<author><name sortKey="Quan, L" sort="Quan, L" uniqKey="Quan L" first="L." last="Quan">L. Quan</name>
</author>
<author><name sortKey="Mohr, R" sort="Mohr, R" uniqKey="Mohr R" first="R." last="Mohr">R. Mohr</name>
</author>
<author><name sortKey="Thirion, E" sort="Thirion, E" uniqKey="Thirion E" first="E." last="Thirion">E. Thirion</name>
</author>
</analytic>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>computer vision</term>
<term>model matching</term>
<term>monocular vision</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en" wicri:score="1334">In this paper, we present how to generate the initial matching hypothesis for a model-based monocular vision system. The primitive shape description of images is a set of line segments and the model is automatically constructed from a sequence of stereo views. The key points of our approach are the use of vanishing points and other perspective invariants such as colinearity, connectivity and the use of double ratios to get rid of matching ambiguities.</div>
</front>
</TEI>
<BibTex type="inproceedings"><ref>quan88a</ref>
<crinnumber>87-R-130</crinnumber>
<category>3</category>
<equipe>INCONNUE</equipe>
<author><e>Quan, L.</e>
<e>Mohr, R.</e>
<e>Thirion, E.</e>
</author>
<title>Generating the initial hypothesis using perspective invariants for a 2D image and 3D model matching</title>
<booktitle>{Proceedings 9th International Conference on Pattern Recognition, Rome}</booktitle>
<year>1988</year>
<month>oct</month>
<keywords><e>computer vision</e>
<e>model matching</e>
<e>monocular vision</e>
</keywords>
<abstract>In this paper, we present how to generate the initial matching hypothesis for a model-based monocular vision system. The primitive shape description of images is a set of line segments and the model is automatically constructed from a sequence of stereo views. The key points of our approach are the use of vanishing points and other perspective invariants such as colinearity, connectivity and the use of double ratios to get rid of matching ambiguities.</abstract>
</BibTex>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Crin/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000544 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Crin/Corpus/biblio.hfd -nk 000544 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Lorraine |area= InforLorV4 |flux= Crin |étape= Corpus |type= RBID |clé= CRIN:quan88a |texte= Generating the initial hypothesis using perspective invariants for a 2D image and 3D model matching }}
This area was generated with Dilib version V0.6.33. |