Using projective geometry to recover planar surfaces in stereovision
Identifieur interne : 00C750 ( Main/Merge ); précédent : 00C749; suivant : 00C751Using projective geometry to recover planar surfaces in stereovision
Auteurs : Houda Chabbi [France] ; Marie Odile Berger [France]Source :
- Pattern Recognition [ 0031-3203 ] ; 1996.
English descriptors
- Teeft :
- Chabbi, Characteristic traces, Collinear, Collinear traces, Common point, Conf, Constraint, Coplanar, Coplanar groups, Coplanar segments, Coplanarity, Distinct points, Experimental results, Face builder, Face matcher, First part, First step, Front view, Image plane, Image planes, Last example, More detail, Optical centre, Pattern recognition, Planar, Planar surface, Planar surfaces, Planarity, Polyhedral, Polyhedral scene, Proc, Projective, Projective geometry, Projective invariants, Reconstruction process, Reference plane, Reference planes, Same point, Second part, Segment, Stereoversion, Stereovision, Stereovision system, Straight line, Straight lines, Trace information, Trinocular, Trinocular stereovision system, Triplet.
Abstract
Abstract: Our purpose is to build the planar surfaces [called three-dimensional (3D) faces] of the objects of a polyhedral scene using a stereovision system composed of three cameras. In each image, our system builds structures known as 2D faces (which are 2D polygons), which are supposed to be the projections of 3D faces, and then matches the 2D faces of each given triplet of images. Due to the large errors caused by the stereo reconstruction, it is difficult to check for planar surfaces after the 3D process. Instead, we prefer to search among the set of triplets of matched 2D faces for the triplets which really correspond to planar 3D surfaces, before the reconstruction step. For this purpose, we propose a new approach to validate the 3D coplanarity of a set of 3D segments, working only on their corresponding matched 2D images and using principles of projective geometry. For each triplet of matched 2D segments, new information, known as trace, is computed and added to the triplets. Then using this new characteristic related to each triplet of matched 2D segments, 3D geometric properties such as the planarity and even coplanarity of a 3D structure are established in 2D space. All these 3D properties, 3D planarity and 3D coplanarity, checked in 2D space, lead to an accurate reconstruction of the surfaces. In this paper, we first introduce the required mathematical tools which explain our approach. Then we present our system for building 3D faces which includes a new unit, in its stereovision part, based on projective geometry. Some experimental results are presented at the end of this paper showing the efficiency of our method.
Url:
DOI: 10.1016/0031-3203(95)00087-9
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 002947
- to stream Istex, to step Curation: 002911
- to stream Istex, to step Checkpoint: 002830
Links to Exploration step
ISTEX:AEF9D27E256818BC66512FBEB46104F1E5A2B430Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title>Using projective geometry to recover planar surfaces in stereovision</title><author><name sortKey="Chabbi, Houda" sort="Chabbi, Houda" uniqKey="Chabbi H" first="Houda" last="Chabbi">Houda Chabbi</name></author><author><name sortKey="Berger, Marie Odile" sort="Berger, Marie Odile" uniqKey="Berger M" first="Marie Odile" last="Berger">Marie Odile Berger</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:AEF9D27E256818BC66512FBEB46104F1E5A2B430</idno><date when="1996" year="1996">1996</date><idno type="doi">10.1016/0031-3203(95)00087-9</idno><idno type="url">https://api.istex.fr/ark:/67375/6H6-VWQVNNC2-V/fulltext.pdf</idno><idno type="wicri:Area/Istex/Corpus">002947</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">002947</idno><idno type="wicri:Area/Istex/Curation">002911</idno><idno type="wicri:Area/Istex/Checkpoint">002830</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">002830</idno><idno type="wicri:doubleKey">0031-3203:1996:Chabbi H:using:projective:geometry</idno><idno type="wicri:Area/Main/Merge">00C750</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a">Using projective geometry to recover planar surfaces in stereovision</title><author><name sortKey="Chabbi, Houda" sort="Chabbi, Houda" uniqKey="Chabbi H" first="Houda" last="Chabbi">Houda Chabbi</name><affiliation wicri:level="1"><country xml:lang="fr">France</country><wicri:regionArea>LG12P (EMA/EERIE), 30 000 Nîmes</wicri:regionArea><wicri:noRegion>30 000 Nîmes</wicri:noRegion><wicri:noRegion>30 000 Nîmes</wicri:noRegion></affiliation></author><author><name sortKey="Berger, Marie Odile" sort="Berger, Marie Odile" uniqKey="Berger M" first="Marie Odile" last="Berger">Marie Odile Berger</name><affiliation wicri:level="3"><country xml:lang="fr">France</country><wicri:regionArea>CRIN-CNRS/INRIA Lorraine, 54506 Vandoeuvre-les-Nancy Cedex</wicri:regionArea><placeName><region type="region" nuts="2">Grand Est</region><region type="old region" nuts="2">Lorraine (région)</region><settlement type="city">Vandœuvre-lès-Nancy</settlement></placeName></affiliation></author></analytic><monogr></monogr><series><title level="j">Pattern Recognition</title><title level="j" type="abbrev">PR</title><idno type="ISSN">0031-3203</idno><imprint><publisher>ELSEVIER</publisher><date type="published" when="1996">1996</date><biblScope unit="volume">29</biblScope><biblScope unit="issue">4</biblScope><biblScope unit="page" from="533">533</biblScope><biblScope unit="page" to="548">548</biblScope></imprint><idno type="ISSN">0031-3203</idno></series></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0031-3203</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="Teeft" xml:lang="en"><term>Chabbi</term><term>Characteristic traces</term><term>Collinear</term><term>Collinear traces</term><term>Common point</term><term>Conf</term><term>Constraint</term><term>Coplanar</term><term>Coplanar groups</term><term>Coplanar segments</term><term>Coplanarity</term><term>Distinct points</term><term>Experimental results</term><term>Face builder</term><term>Face matcher</term><term>First part</term><term>First step</term><term>Front view</term><term>Image plane</term><term>Image planes</term><term>Last example</term><term>More detail</term><term>Optical centre</term><term>Pattern recognition</term><term>Planar</term><term>Planar surface</term><term>Planar surfaces</term><term>Planarity</term><term>Polyhedral</term><term>Polyhedral scene</term><term>Proc</term><term>Projective</term><term>Projective geometry</term><term>Projective invariants</term><term>Reconstruction process</term><term>Reference plane</term><term>Reference planes</term><term>Same point</term><term>Second part</term><term>Segment</term><term>Stereoversion</term><term>Stereovision</term><term>Stereovision system</term><term>Straight line</term><term>Straight lines</term><term>Trace information</term><term>Trinocular</term><term>Trinocular stereovision system</term><term>Triplet</term></keywords></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Abstract: Our purpose is to build the planar surfaces [called three-dimensional (3D) faces] of the objects of a polyhedral scene using a stereovision system composed of three cameras. In each image, our system builds structures known as 2D faces (which are 2D polygons), which are supposed to be the projections of 3D faces, and then matches the 2D faces of each given triplet of images. Due to the large errors caused by the stereo reconstruction, it is difficult to check for planar surfaces after the 3D process. Instead, we prefer to search among the set of triplets of matched 2D faces for the triplets which really correspond to planar 3D surfaces, before the reconstruction step. For this purpose, we propose a new approach to validate the 3D coplanarity of a set of 3D segments, working only on their corresponding matched 2D images and using principles of projective geometry. For each triplet of matched 2D segments, new information, known as trace, is computed and added to the triplets. Then using this new characteristic related to each triplet of matched 2D segments, 3D geometric properties such as the planarity and even coplanarity of a 3D structure are established in 2D space. All these 3D properties, 3D planarity and 3D coplanarity, checked in 2D space, lead to an accurate reconstruction of the surfaces. In this paper, we first introduce the required mathematical tools which explain our approach. Then we present our system for building 3D faces which includes a new unit, in its stereovision part, based on projective geometry. Some experimental results are presented at the end of this paper showing the efficiency of our method.</div></front></TEI></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Main/Merge
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 00C750 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 00C750 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Lorraine
|area= InforLorV4
|flux= Main
|étape= Merge
|type= RBID
|clé= ISTEX:AEF9D27E256818BC66512FBEB46104F1E5A2B430
|texte= Using projective geometry to recover planar surfaces in stereovision
}}
| This area was generated with Dilib version V0.6.33. |  |