Serveur d'exploration sur la recherche en informatique en Lorraine

Attention, ce site est en cours de développement !
Attention, site généré par des moyens informatiques à partir de corpus bruts.
Les informations ne sont donc pas validées.

Mixing synthetic and video images of an outdoor urban environment

Identifieur interne : 000974 ( PascalFrancis/Corpus ); précédent : 000973; suivant : 000975

Mixing synthetic and video images of an outdoor urban environment

Auteurs : M. O. Berger ; B. Wrobel Dautcourt ; S. Petitjean ; G. Simon

Source :

RBID : Pascal:01-0162649

Descripteurs français

English descriptors

Abstract

Mixing video and computer-generated images is a new and promising area of research for enhancing reality. It can be used in all the situations when a complete simulation would not be easy to implement. Past work on the subject has relied for a large part on human intervention at key moments of the composition. In this paper, we show that if enough geometric information about the environment is available, then efficient tools developed in the computer vision literature can be used to build a highly automated augmented reality loop. We focus on outdoor urban environments and present an application for the visual assessment of a new lighting project of the bridges of Paris. We present a fully augmented 300-image sequence of a specific bridge, the Pont Neuf. Emphasis is put on the robust calculation of the camera position. We also detail the techniques used for matching 2D and 3D primitives and for tracking features over the sequence. Our system overcomes two major difficulties. First, it is capable of handling poor-quality images, resulting from the fact that images were shot at night since the goal was to simulate a new lighting system. Second, it can deal with important changes in viewpoint position and in appearance along the sequence. Throughout the paper, many results are shown to illustrate the different steps and difficulties encountered.

Notice en format standard (ISO 2709)

Pour connaître la documentation sur le format Inist Standard.

pA  
A01 01  1    @0 0932-8092
A02 01      @0 MVAPEO
A03   1    @0 Mach Vision Appl
A05       @2 11
A06       @2 3
A08 01  1  ENG  @1 Mixing synthetic and video images of an outdoor urban environment
A11 01  1    @1 BERGER (M. O.)
A11 02  1    @1 WROBEL DAUTCOURT (B.)
A11 03  1    @1 PETITJEAN (S.)
A11 04  1    @1 SIMON (G.)
A14 01      @1 LORIA-CNRS & INRIA Lorraine @2 Vandoeuvre-les-Nancy @3 FRA @Z 1 aut.
A20       @1 145-159
A21       @1 1999
A23 01      @0 ENG
A43 01      @1 INIST @2 21507
A44       @0 A100
A45       @0 28 Refs.
A47 01  1    @0 01-0162649
A60       @1 P
A61       @0 A
A64 01  1    @0 Machine Vision and Applications
A66 01      @0 DEU
C01 01    ENG  @0 Mixing video and computer-generated images is a new and promising area of research for enhancing reality. It can be used in all the situations when a complete simulation would not be easy to implement. Past work on the subject has relied for a large part on human intervention at key moments of the composition. In this paper, we show that if enough geometric information about the environment is available, then efficient tools developed in the computer vision literature can be used to build a highly automated augmented reality loop. We focus on outdoor urban environments and present an application for the visual assessment of a new lighting project of the bridges of Paris. We present a fully augmented 300-image sequence of a specific bridge, the Pont Neuf. Emphasis is put on the robust calculation of the camera position. We also detail the techniques used for matching 2D and 3D primitives and for tracking features over the sequence. Our system overcomes two major difficulties. First, it is capable of handling poor-quality images, resulting from the fact that images were shot at night since the goal was to simulate a new lighting system. Second, it can deal with important changes in viewpoint position and in appearance along the sequence. Throughout the paper, many results are shown to illustrate the different steps and difficulties encountered.
C02 01  X    @0 001D02B
C02 02  3    @0 001B40B
C02 03  X    @0 001D02B07B
C02 04  X    @0 001D02B12
C02 05  3    @0 001B00G68
C03 01  1  ENG  @0 Enriched image sequences @4 INC
C03 02  1  FRE  @0 Théorie
C03 02  1  ENG  @0 Theory
C03 03  1  FRE  @0 Analyse image
C03 03  1  ENG  @0 Image analysis
C03 04  1  FRE  @0 Simulation ordinateur
C03 04  1  ENG  @0 Computer simulation
C03 05  1  FRE  @0 Appareil photographique
C03 05  1  ENG  @0 Cameras
C03 06  1  FRE  @0 Réalité virtuelle @3 P
C03 06  1  ENG  @0 Virtual reality @3 P
N21       @1 113

Format Inist (serveur)

NO : PASCAL 01-0162649 EI
ET : Mixing synthetic and video images of an outdoor urban environment
AU : BERGER (M. O.); WROBEL DAUTCOURT (B.); PETITJEAN (S.); SIMON (G.)
AF : LORIA-CNRS & INRIA Lorraine/Vandoeuvre-les-Nancy/France (1 aut.)
DT : Publication en série; Niveau analytique
SO : Machine Vision and Applications; ISSN 0932-8092; Coden MVAPEO; Allemagne; Da. 1999; Vol. 11; No. 3; Pp. 145-159; Bibl. 28 Refs.
LA : Anglais
EA : Mixing video and computer-generated images is a new and promising area of research for enhancing reality. It can be used in all the situations when a complete simulation would not be easy to implement. Past work on the subject has relied for a large part on human intervention at key moments of the composition. In this paper, we show that if enough geometric information about the environment is available, then efficient tools developed in the computer vision literature can be used to build a highly automated augmented reality loop. We focus on outdoor urban environments and present an application for the visual assessment of a new lighting project of the bridges of Paris. We present a fully augmented 300-image sequence of a specific bridge, the Pont Neuf. Emphasis is put on the robust calculation of the camera position. We also detail the techniques used for matching 2D and 3D primitives and for tracking features over the sequence. Our system overcomes two major difficulties. First, it is capable of handling poor-quality images, resulting from the fact that images were shot at night since the goal was to simulate a new lighting system. Second, it can deal with important changes in viewpoint position and in appearance along the sequence. Throughout the paper, many results are shown to illustrate the different steps and difficulties encountered.
CC : 001D02B; 001B40B; 001D02B07B; 001D02B12; 001B00G68
FD : Théorie; Analyse image; Simulation ordinateur; Appareil photographique; Réalité virtuelle
ED : Enriched image sequences; Theory; Image analysis; Computer simulation; Cameras; Virtual reality
LO : INIST-21507
ID : 01-0162649

Links to Exploration step

Pascal:01-0162649

Le document en format XML

<record>
<TEI>
<teiHeader>
<fileDesc>
<titleStmt>
<title xml:lang="en" level="a">Mixing synthetic and video images of an outdoor urban environment</title>
<author>
<name sortKey="Berger, M O" sort="Berger, M O" uniqKey="Berger M" first="M. O." last="Berger">M. O. Berger</name>
<affiliation>
<inist:fA14 i1="01">
<s1>LORIA-CNRS & INRIA Lorraine</s1>
<s2>Vandoeuvre-les-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author>
<name sortKey="Wrobel Dautcourt, B" sort="Wrobel Dautcourt, B" uniqKey="Wrobel Dautcourt B" first="B." last="Wrobel Dautcourt">B. Wrobel Dautcourt</name>
</author>
<author>
<name sortKey="Petitjean, S" sort="Petitjean, S" uniqKey="Petitjean S" first="S." last="Petitjean">S. Petitjean</name>
</author>
<author>
<name sortKey="Simon, G" sort="Simon, G" uniqKey="Simon G" first="G." last="Simon">G. Simon</name>
</author>
</titleStmt>
<publicationStmt>
<idno type="wicri:source">INIST</idno>
<idno type="inist">01-0162649</idno>
<date when="1999">1999</date>
<idno type="stanalyst">PASCAL 01-0162649 EI</idno>
<idno type="RBID">Pascal:01-0162649</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000974</idno>
</publicationStmt>
<sourceDesc>
<biblStruct>
<analytic>
<title xml:lang="en" level="a">Mixing synthetic and video images of an outdoor urban environment</title>
<author>
<name sortKey="Berger, M O" sort="Berger, M O" uniqKey="Berger M" first="M. O." last="Berger">M. O. Berger</name>
<affiliation>
<inist:fA14 i1="01">
<s1>LORIA-CNRS & INRIA Lorraine</s1>
<s2>Vandoeuvre-les-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author>
<name sortKey="Wrobel Dautcourt, B" sort="Wrobel Dautcourt, B" uniqKey="Wrobel Dautcourt B" first="B." last="Wrobel Dautcourt">B. Wrobel Dautcourt</name>
</author>
<author>
<name sortKey="Petitjean, S" sort="Petitjean, S" uniqKey="Petitjean S" first="S." last="Petitjean">S. Petitjean</name>
</author>
<author>
<name sortKey="Simon, G" sort="Simon, G" uniqKey="Simon G" first="G." last="Simon">G. Simon</name>
</author>
</analytic>
<series>
<title level="j" type="main">Machine Vision and Applications</title>
<title level="j" type="abbreviated">Mach Vision Appl</title>
<idno type="ISSN">0932-8092</idno>
<imprint>
<date when="1999">1999</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt>
<title level="j" type="main">Machine Vision and Applications</title>
<title level="j" type="abbreviated">Mach Vision Appl</title>
<idno type="ISSN">0932-8092</idno>
</seriesStmt>
</fileDesc>
<profileDesc>
<textClass>
<keywords scheme="KwdEn" xml:lang="en">
<term>Cameras</term>
<term>Computer simulation</term>
<term>Enriched image sequences</term>
<term>Image analysis</term>
<term>Theory</term>
<term>Virtual reality</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr">
<term>Théorie</term>
<term>Analyse image</term>
<term>Simulation ordinateur</term>
<term>Appareil photographique</term>
<term>Réalité virtuelle</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front>
<div type="abstract" xml:lang="en">Mixing video and computer-generated images is a new and promising area of research for enhancing reality. It can be used in all the situations when a complete simulation would not be easy to implement. Past work on the subject has relied for a large part on human intervention at key moments of the composition. In this paper, we show that if enough geometric information about the environment is available, then efficient tools developed in the computer vision literature can be used to build a highly automated augmented reality loop. We focus on outdoor urban environments and present an application for the visual assessment of a new lighting project of the bridges of Paris. We present a fully augmented 300-image sequence of a specific bridge, the Pont Neuf. Emphasis is put on the robust calculation of the camera position. We also detail the techniques used for matching 2D and 3D primitives and for tracking features over the sequence. Our system overcomes two major difficulties. First, it is capable of handling poor-quality images, resulting from the fact that images were shot at night since the goal was to simulate a new lighting system. Second, it can deal with important changes in viewpoint position and in appearance along the sequence. Throughout the paper, many results are shown to illustrate the different steps and difficulties encountered.</div>
</front>
</TEI>
<inist>
<standard h6="B">
<pA>
<fA01 i1="01" i2="1">
<s0>0932-8092</s0>
</fA01>
<fA02 i1="01">
<s0>MVAPEO</s0>
</fA02>
<fA03 i2="1">
<s0>Mach Vision Appl</s0>
</fA03>
<fA05>
<s2>11</s2>
</fA05>
<fA06>
<s2>3</s2>
</fA06>
<fA08 i1="01" i2="1" l="ENG">
<s1>Mixing synthetic and video images of an outdoor urban environment</s1>
</fA08>
<fA11 i1="01" i2="1">
<s1>BERGER (M. O.)</s1>
</fA11>
<fA11 i1="02" i2="1">
<s1>WROBEL DAUTCOURT (B.)</s1>
</fA11>
<fA11 i1="03" i2="1">
<s1>PETITJEAN (S.)</s1>
</fA11>
<fA11 i1="04" i2="1">
<s1>SIMON (G.)</s1>
</fA11>
<fA14 i1="01">
<s1>LORIA-CNRS & INRIA Lorraine</s1>
<s2>Vandoeuvre-les-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
</fA14>
<fA20>
<s1>145-159</s1>
</fA20>
<fA21>
<s1>1999</s1>
</fA21>
<fA23 i1="01">
<s0>ENG</s0>
</fA23>
<fA43 i1="01">
<s1>INIST</s1>
<s2>21507</s2>
</fA43>
<fA44>
<s0>A100</s0>
</fA44>
<fA45>
<s0>28 Refs.</s0>
</fA45>
<fA47 i1="01" i2="1">
<s0>01-0162649</s0>
</fA47>
<fA60>
<s1>P</s1>
</fA60>
<fA61>
<s0>A</s0>
</fA61>
<fA64 i1="01" i2="1">
<s0>Machine Vision and Applications</s0>
</fA64>
<fA66 i1="01">
<s0>DEU</s0>
</fA66>
<fC01 i1="01" l="ENG">
<s0>Mixing video and computer-generated images is a new and promising area of research for enhancing reality. It can be used in all the situations when a complete simulation would not be easy to implement. Past work on the subject has relied for a large part on human intervention at key moments of the composition. In this paper, we show that if enough geometric information about the environment is available, then efficient tools developed in the computer vision literature can be used to build a highly automated augmented reality loop. We focus on outdoor urban environments and present an application for the visual assessment of a new lighting project of the bridges of Paris. We present a fully augmented 300-image sequence of a specific bridge, the Pont Neuf. Emphasis is put on the robust calculation of the camera position. We also detail the techniques used for matching 2D and 3D primitives and for tracking features over the sequence. Our system overcomes two major difficulties. First, it is capable of handling poor-quality images, resulting from the fact that images were shot at night since the goal was to simulate a new lighting system. Second, it can deal with important changes in viewpoint position and in appearance along the sequence. Throughout the paper, many results are shown to illustrate the different steps and difficulties encountered.</s0>
</fC01>
<fC02 i1="01" i2="X">
<s0>001D02B</s0>
</fC02>
<fC02 i1="02" i2="3">
<s0>001B40B</s0>
</fC02>
<fC02 i1="03" i2="X">
<s0>001D02B07B</s0>
</fC02>
<fC02 i1="04" i2="X">
<s0>001D02B12</s0>
</fC02>
<fC02 i1="05" i2="3">
<s0>001B00G68</s0>
</fC02>
<fC03 i1="01" i2="1" l="ENG">
<s0>Enriched image sequences</s0>
<s4>INC</s4>
</fC03>
<fC03 i1="02" i2="1" l="FRE">
<s0>Théorie</s0>
</fC03>
<fC03 i1="02" i2="1" l="ENG">
<s0>Theory</s0>
</fC03>
<fC03 i1="03" i2="1" l="FRE">
<s0>Analyse image</s0>
</fC03>
<fC03 i1="03" i2="1" l="ENG">
<s0>Image analysis</s0>
</fC03>
<fC03 i1="04" i2="1" l="FRE">
<s0>Simulation ordinateur</s0>
</fC03>
<fC03 i1="04" i2="1" l="ENG">
<s0>Computer simulation</s0>
</fC03>
<fC03 i1="05" i2="1" l="FRE">
<s0>Appareil photographique</s0>
</fC03>
<fC03 i1="05" i2="1" l="ENG">
<s0>Cameras</s0>
</fC03>
<fC03 i1="06" i2="1" l="FRE">
<s0>Réalité virtuelle</s0>
<s3>P</s3>
</fC03>
<fC03 i1="06" i2="1" l="ENG">
<s0>Virtual reality</s0>
<s3>P</s3>
</fC03>
<fN21>
<s1>113</s1>
</fN21>
</pA>
</standard>
<server>
<NO>PASCAL 01-0162649 EI</NO>
<ET>Mixing synthetic and video images of an outdoor urban environment</ET>
<AU>BERGER (M. O.); WROBEL DAUTCOURT (B.); PETITJEAN (S.); SIMON (G.)</AU>
<AF>LORIA-CNRS & INRIA Lorraine/Vandoeuvre-les-Nancy/France (1 aut.)</AF>
<DT>Publication en série; Niveau analytique</DT>
<SO>Machine Vision and Applications; ISSN 0932-8092; Coden MVAPEO; Allemagne; Da. 1999; Vol. 11; No. 3; Pp. 145-159; Bibl. 28 Refs.</SO>
<LA>Anglais</LA>
<EA>Mixing video and computer-generated images is a new and promising area of research for enhancing reality. It can be used in all the situations when a complete simulation would not be easy to implement. Past work on the subject has relied for a large part on human intervention at key moments of the composition. In this paper, we show that if enough geometric information about the environment is available, then efficient tools developed in the computer vision literature can be used to build a highly automated augmented reality loop. We focus on outdoor urban environments and present an application for the visual assessment of a new lighting project of the bridges of Paris. We present a fully augmented 300-image sequence of a specific bridge, the Pont Neuf. Emphasis is put on the robust calculation of the camera position. We also detail the techniques used for matching 2D and 3D primitives and for tracking features over the sequence. Our system overcomes two major difficulties. First, it is capable of handling poor-quality images, resulting from the fact that images were shot at night since the goal was to simulate a new lighting system. Second, it can deal with important changes in viewpoint position and in appearance along the sequence. Throughout the paper, many results are shown to illustrate the different steps and difficulties encountered.</EA>
<CC>001D02B; 001B40B; 001D02B07B; 001D02B12; 001B00G68</CC>
<FD>Théorie; Analyse image; Simulation ordinateur; Appareil photographique; Réalité virtuelle</FD>
<ED>Enriched image sequences; Theory; Image analysis; Computer simulation; Cameras; Virtual reality</ED>
<LO>INIST-21507</LO>
<ID>01-0162649</ID>
</server>
</inist>
</record>

Pour manipuler ce document sous Unix (Dilib)

EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/PascalFrancis/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000974 | SxmlIndent | more

Ou

HfdSelect -h $EXPLOR_AREA/Data/PascalFrancis/Corpus/biblio.hfd -nk 000974 | SxmlIndent | more

Pour mettre un lien sur cette page dans le réseau Wicri

{{Explor lien
   |wiki=    Wicri/Lorraine
   |area=    InforLorV4
   |flux=    PascalFrancis
   |étape=   Corpus
   |type=    RBID
   |clé=     Pascal:01-0162649
   |texte=   Mixing synthetic and video images of an outdoor urban environment
}}

Wicri

This area was generated with Dilib version V0.6.33.
Data generation: Mon Jun 10 21:56:28 2019. Site generation: Fri Feb 25 15:29:27 2022