HAL - INRIA :: [inria-00548643, version 1] From images to shape models for object detection

inria-00548643, version 1

From images to shape models for object detection

Vittorio Ferrari () ¹, Frédéric Jurie () ², Cordelia Schmid () ^3, 4

International Journal of Computer Vision 87, 3 (2010) 284--303

Abstract: We present an object class detection approach which fully integrates the complementary strengths offered by shape matchers. Like an object detector, it can learn class models directly from images, and can localize novel instances in the presence of intra-class variations, clutter, and scale changes. Like a shape matcher, it finds the boundaries of objects, rather than just their bounding-boxes. This is achieved by a novel technique for learning a shape model of an object class given images of example instances. Furthermore, we also integrate Hough-style voting with a non-rigid point matching algorithm to localize the model in cluttered images. As demonstrated by an extensive evaluation, our method can localize object boundaries accurately and does not need segmented examples for training (only bounding-boxes).

1: Eldgenössische Technische Hochschule Zürich (ETH Zürich)
ETH Zurich
2: Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen (GREYC)
CNRS : UMR6072 – Université de Caen – Ecole Nationale Supérieure d'Ingénieurs de Caen
3: LEAR (INRIA Grenoble Rhône-Alpes / LJK Laboratoire Jean Kuntzmann)
CNRS : FR71 – CNRS : UMR5527 – INRIA – Laboratoire Jean Kuntzmann – Université Joseph Fourier - Grenoble I – Institut National Polytechnique de Grenoble (INPG)
4: Laboratoire Jean Kuntzmann (LJK)
CNRS : UMR5224 – Université Joseph Fourier - Grenoble I – Université Pierre Mendès-France - Grenoble II – Institut Polytechnique de Grenoble - Grenoble Institute of Technology

inria-00548643, version 1
http://hal.inria.fr/inria-00548643
oai:hal.inria.fr:inria-00548643
From: Team Lear <>
Submitted for: Laure BENAC <>
Submitted on: Monday, 20 December 2010 10:23:55
Updated on: Monday, 10 January 2011 15:44:25

See detailed view

Associated documents

PDF :

DOI: 10.1007/s11263-009-0270-9

Full text from publisher

Export

Bibtex EndNote TEI RefWorks

%% inria-00548643, version 1
%% http://hal.inria.fr/inria-00548643
@article{ferrari:inria-00548643,
    hal_id = {inria-00548643},
    url = {http://hal.inria.fr/inria-00548643},
    title = {{From images to shape models for object detection}},
    author = {Ferrari, Vittorio and Jurie, Fr{\'e}d{\'e}ric and Schmid, Cordelia},
    abstract = {{We present an object class detection approach which fully integrates the complementary strengths offered by shape matchers. Like an object detector, it can learn class models directly from images, and can localize novel instances in the presence of intra-class variations, clutter, and scale changes. Like a shape matcher, it finds the boundaries of objects, rather than just their bounding-boxes. This is achieved by a novel technique for learning a shape model of an object class given images of example instances. Furthermore, we also integrate Hough-style voting with a non-rigid point matching algorithm to localize the model in cluttered images. As demonstrated by an extensive evaluation, our method can localize object boundaries accurately and does not need segmented examples for training (only bounding-boxes).}},
    keywords = {Object class detection; Learning category models; Local contour features; Shape matching},
    language = {English},
    affiliation = {Eldgen{\"o}ssische Technische Hochschule Z{\"u}rich - ETH Z{\"u}rich , Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen - GREYC , LEAR - INRIA Grenoble Rh{\^o}ne-Alpes / LJK Laboratoire Jean Kuntzmann , Laboratoire Jean Kuntzmann - LJK},
    publisher = {Springer-Verlag},
    pages = {284--303},
    journal = {International Journal of Computer Vision},
    volume = {87},
    number = {3 },
    note = {This research was supported by the EADS foundation, INRIA, CNRS, and SNSF. V. Ferrari was funded by a fellowship of the EADS foundation and by SNSF. },
    audience = {international },
    doi = {10.1007/s11263-009-0270-9 },
    year = {2010},
    pdf = {http://hal.inria.fr/inria-00548643/PDF/FJS10.pdf},
}

<?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 in peer-reviewed journal</head>
<biblStruct type="article" xml:id="inria-00548643"><analytic>
<author><persName><forename>Vittorio</forename><surname>Ferrari</surname></persName>
<affiliation>
<orgName type="laboratory">ETH Zürich</orgName>
<orgName type="team">Eldgenössische Technische Hochschule Zürich</orgName>
<country>CH</country>
<orgName type="institution">ETH Zurich</orgName>
</affiliation>
</author>
<author><persName><forename>Frédéric</forename><surname>Jurie</surname></persName>
<affiliation>
<orgName type="laboratory">GREYC</orgName>
<orgName type="team">Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen</orgName>
<country>FR</country>
<orgName type="institution">CNRS : UMR6072</orgName>
<orgName type="institution">Université de Caen</orgName>
<orgName type="institution">Ecole Nationale Supérieure d'Ingénieurs de Caen</orgName>
</affiliation>
</author>
<author><persName><forename>Cordelia</forename><surname>Schmid</surname></persName>
<affiliation>
<orgName type="laboratory">INRIA Grenoble Rhône-Alpes / LJK Laboratoire Jean Kuntzmann</orgName>
<orgName type="team">LEAR</orgName>
<country>FR</country>
<orgName type="institution">CNRS : FR71</orgName>
<orgName type="institution">CNRS : UMR5527</orgName>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">Laboratoire Jean Kuntzmann</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">LJK</orgName>
<orgName type="team">Laboratoire Jean Kuntzmann</orgName>
<country>FR</country>
<orgName type="institution">CNRS : UMR5224</orgName>
<orgName type="institution">Université Joseph Fourier - Grenoble I</orgName>
<orgName type="institution">Université Pierre Mendès-France - Grenoble II</orgName>
<orgName type="institution">Institut Polytechnique de Grenoble - Grenoble Institute of Technology</orgName>
</affiliation>
</author>
<title type="main" level="a">From images to shape models for object detection</title></analytic><monogr><title level="j" type="main">International Journal of Computer Vision</title><imprint><publisher>Springer-Verlag</publisher><biblScope type="publicationDate">2010-00-00</biblScope><biblScope type="vol">87</biblScope><biblScope type="issue">3</biblScope><biblScope type="pp">284--303</biblScope></imprint></monogr><idno type="doi">10.1007/s11263-009-0270-9</idno><idno type="HALid">http://hal.inria.fr/inria-00548643</idno><idno type="HALFile">http://hal.inria.fr/inria-00548643/PDF/FJS10.pdf</idno></biblStruct>
</listBibl>
</listBibl>