Semi-Local Projective Invariants for the Recognition of Smooth Plane Curves

Stefan Carlsson; Roger Mohr; Luce Morin; Charlie Rothwell; Marc Van Diest; Luc Van Gool; Françoise Veillon; Andrew Zisserman

inria-00548380, version 1

Semi-Local Projective Invariants for the Recognition of Smooth Plane Curves

Stefan Carlsson ¹, Roger Mohr ^2, 3, Luce Morin^a^, 3, 4, Charlie Rothwell ⁵, Marc Van Diest ⁶, Luc Van Gool ⁶, Françoise Veillon ³, Andrew Zisserman ()^b^, 5

International Journal of Computer Vision 19, 3 (1996) 211--236

Résumé : Recently, several methods have been proposed for describing plane, non-algebraic curves in a projectively invariant fashion. These curve representations are invariant under changes in viewpoint and therefore ideally suited for recognition. We report the results of a study where the strengths and weaknesses of a number of semi-local methods are compared on the basis of the same images and edge data. All the methods define a distinguished or canonical projective frame for the curve segment which is used for projective normalisation. In this canonical frame the curve has a viewpoint invariant signature. Measurements on the signature are invariants. All the methods presented are designed to work on real images where extracted data will not be ideal, and parts of curves will be missing because of poor contrast or occlusion. We compare the stability and discrimination of the signatures and invariants over a number of example curves and viewpoints. The paper concludes with a discussion of how the various methods can be integrated within a recognition system.

a – Université de Rennes I
b – University of Oxford
1 : Computer Vision & Active Perception lab. (CVAP)
The Royal Institute of Technology (KTH)
2 : MOVI (IMAG-INRIA Rhône-Alpes / GRAVIR)
INRIA – CNRS : UMR5527 – Université Joseph Fourier - Grenoble I – Institut National Polytechnique de Grenoble (INPG)
3 : Laboratoire d'Informatique Fondamentale et d'Intelligence Artificielle (LIFIA)
Institut National Polytechnique de Grenoble (INPG)
4 : TEMIS (INRIA - IRISA)
CNRS : UMR6074 – INRIA – Institut National des Sciences Appliquées (INSA) - Rennes – Université de Rennes 1
5 : Robotics Research Group
University of Oxford
6 : Machine Intelligence and Imaging Research Group (ESAT)
Université Catholique de Louvain (UCL) - Belgique – Katholieke Universiteit Leuven

inria-00548380, version 1
http://hal.inria.fr/inria-00548380
oai:hal.inria.fr:inria-00548380
Contributeur : Team Lear <>
Déposé pour le compte de : Laure BENAC <>
Soumis le : Lundi 20 Décembre 2010, 08:44:06
Dernière modification le : Mardi 1 Février 2011, 09:44:54

Voir la fiche détaillée

Documents associés

DOI : 10.1007/BF00055145

Texte intégral chez l'éditeur

Exporter

Bibtex EndNote TEI RefWorks

%% inria-00548380, version 1
%% http://hal.inria.fr/inria-00548380
@article{carlsson:inria-00548380,
    hal_id = {inria-00548380},
    url = {http://hal.inria.fr/inria-00548380},
    title = {{Semi-Local Projective Invariants for the Recognition of Smooth Plane Curves}},
    author = {Carlsson, Stefan and Mohr, Roger and Morin, Luce and Rothwell, Charlie and Van Diest, Marc and Van Gool, Luc and Veillon, Fran{\c c}oise and Zisserman, Andrew},
    abstract = {{Recently, several methods have been proposed for describing plane, non-algebraic curves in a projectively invariant fashion. These curve representations are invariant under changes in viewpoint and therefore ideally suited for recognition. We report the results of a study where the strengths and weaknesses of a number of semi-local methods are compared on the basis of the same images and edge data. All the methods define a distinguished or canonical projective frame for the curve segment which is used for projective normalisation. In this canonical frame the curve has a viewpoint invariant signature. Measurements on the signature are invariants. All the methods presented are designed to work on real images where extracted data will not be ideal, and parts of curves will be missing because of poor contrast or occlusion. We compare the stability and discrimination of the signatures and invariants over a number of example curves and viewpoints. The paper concludes with a discussion of how the various methods can be integrated within a recognition system.}},
    language = {Anglais},
    affiliation = {Computer Vision \& Active Perception lab. - CVAP , MOVI - IMAG-INRIA Rh{\^o}ne-Alpes / GRAVIR , Laboratoire d'Informatique Fondamentale et d'Intelligence Artificielle - LIFIA , TEMIS - INRIA - IRISA , Robotics Research Group , Machine Intelligence and Imaging Research Group - ESAT},
    publisher = {Springer-Verlag},
    pages = {211--236},
    journal = {International Journal of Computer Vision},
    volume = {19},
    number = {3 },
    audience = {internationale },
    doi = {10.1007/BF00055145 },
    year = {1996},
}

<?xml version="1.0" encoding="UTF-8"?>
<listBibl xmlns="http://www.tei-c.org/ns/1.0" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML">
<listBibl type="article"><head>Articles dans des revues avec comité de lecture</head>
<biblStruct type="article" xml:id="inria-00548380"><analytic>
<author><persName><forename>Stefan</forename><surname>Carlsson</surname></persName>
<affiliation>
<orgName type="laboratory">CVAP</orgName>
<orgName type="team">Computer Vision & Active Perception lab.</orgName>
<country>SE</country>
<orgName type="institution">The Royal Institute of Technology (KTH)</orgName>
</affiliation>
</author>
<author><persName><forename>Roger</forename><surname>Mohr</surname></persName>
<affiliation>
<orgName type="laboratory">IMAG-INRIA Rhône-Alpes / GRAVIR</orgName>
<orgName type="team">MOVI</orgName>
<country>FR</country>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">CNRS : UMR5527</orgName>
<orgName type="institution">Université Joseph Fourier - Grenoble I</orgName>
<orgName type="institution">Institut National Polytechnique de Grenoble (INPG)</orgName>
</affiliation>
<affiliation>
<orgName type="laboratory">LIFIA</orgName>
<orgName type="team">Laboratoire d'Informatique Fondamentale et d'Intelligence Artificielle</orgName>
<country>FR</country>
<orgName type="institution">Institut National Polytechnique de Grenoble (INPG)</orgName>
</affiliation>
</author>
<author><persName><forename>Luce</forename><surname>Morin</surname></persName>
<affiliation>
<orgName type="laboratory">LIFIA</orgName>
<orgName type="team">Laboratoire d'Informatique Fondamentale et d'Intelligence Artificielle</orgName>
<country>FR</country>
<orgName type="institution">Institut National Polytechnique de Grenoble (INPG)</orgName>
</affiliation>
<affiliation>
<orgName type="laboratory">INRIA - IRISA</orgName>
<orgName type="team">TEMIS</orgName>
<country>FR</country>
<orgName type="institution">CNRS : UMR6074</orgName>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">Institut National des Sciences Appliquées (INSA) - Rennes</orgName>
<orgName type="institution">Université de Rennes 1</orgName>
</affiliation>
</author>
<author><persName><forename>Charlie</forename><surname>Rothwell</surname></persName>
<affiliation>
<orgName type="team">Robotics Research Group</orgName>
<country>GB</country>
<orgName type="institution">University of Oxford</orgName>
</affiliation>
</author>
<author><persName><forename>Marc</forename><surname>Van Diest</surname></persName>
<affiliation>
<orgName type="laboratory">ESAT</orgName>
<orgName type="team">Machine Intelligence and Imaging Research Group</orgName>
<country>BE</country>
<orgName type="institution">Université Catholique de Louvain (UCL) - Belgique</orgName>
<orgName type="institution">Katholieke Universiteit Leuven</orgName>
</affiliation>
</author>
<author><persName><forename>Luc</forename><surname>Van Gool</surname></persName>
<affiliation>
<orgName type="laboratory">ESAT</orgName>
<orgName type="team">Machine Intelligence and Imaging Research Group</orgName>
<country>BE</country>
<orgName type="institution">Université Catholique de Louvain (UCL) - Belgique</orgName>
<orgName type="institution">Katholieke Universiteit Leuven</orgName>
</affiliation>
</author>
<author><persName><forename>Françoise</forename><surname>Veillon</surname></persName>
<affiliation>
<orgName type="laboratory">LIFIA</orgName>
<orgName type="team">Laboratoire d'Informatique Fondamentale et d'Intelligence Artificielle</orgName>
<country>FR</country>
<orgName type="institution">Institut National Polytechnique de Grenoble (INPG)</orgName>
</affiliation>
</author>
<author><persName><forename>Andrew</forename><surname>Zisserman</surname></persName>
<affiliation>
<orgName type="team">Robotics Research Group</orgName>
<country>GB</country>
<orgName type="institution">University of Oxford</orgName>
</affiliation>
</author>
<title type="main" level="a">Semi-Local Projective Invariants for the Recognition of Smooth Plane Curves</title></analytic><monogr><title level="j" type="main">International Journal of Computer Vision</title><imprint><publisher>Springer-Verlag</publisher><biblScope type="publicationDate">1996-00-00</biblScope><biblScope type="vol">19</biblScope><biblScope type="issue">3</biblScope><biblScope type="pp">211--236</biblScope></imprint></monogr><idno type="doi">10.1007/BF00055145</idno><idno type="HALid">http://hal.inria.fr/inria-00548380</idno></biblStruct>
</listBibl>
</listBibl>