HAL - INRIA :: [inria-00548682, version 1] Flexible Object Models for Category-Level 3D Object Recognition

inria-00548682, version 1

Flexible Object Models for Category-Level 3D Object Recognition

Akash Kushal ^1, 2, Cordelia Schmid () ^3, 4, Jean Ponce () ^5, 6

IEEE Conference on Computer Vision & Pattern Recognition (CVPR '07) (2007) 1--8

Abstract: Today's category-level object recognition systems largely focus on fronto-parallel views of objects with characteristic texture patterns. To overcome these limitations, we propose a novel framework for visual object recognition where object classes are represented by assemblies of partial surface models (PSMs) obeying loose local geometric constraints. The PSMs themselves are formed of dense, locally rigid assemblies of image features. Since our model only enforces local geometric consistency, both at the level of model parts and at the level of individual features within the parts, it is robust to viewpoint changes and intra-class variability. The proposed approach has been implemented, and it outperforms the state-of-the-art algorithms for object detection and localization recently compared in [14] on the Pascal 2005 VOC Challenge Cars Test 1 data.

1: Department of Computer Science [UIUC] (UIUC)
University of Illinois at Urbana-Champaign
2: The Beckman Institute for Advanced Science and Technology (Beckman Institute)
University of Illinois
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
5: WILLOW (INRIA Paris - Rocquencourt)
INRIA – Ecole Normale Supérieure de Paris - ENS Paris – CNRS : UMR8548
6: Laboratoire d'informatique de l'école normale supérieure (LIENS)
CNRS : UMR8548 – Ecole Normale Supérieure de Paris - ENS Paris

inria-00548682, version 1
http://hal.inria.fr/inria-00548682
oai:hal.inria.fr:inria-00548682
From: Team Lear <>
Submitted for: Laure BENAC <>
Submitted on: Monday, 20 December 2010 10:28:57
Updated on: Monday, 10 January 2011 17:37:16

See detailed view

Associated documents

PDF :

DOI: 10.1109/CVPR.2007.383149

Full text from publisher

Export

Bibtex EndNote TEI RefWorks

%% inria-00548682, version 1
%% http://hal.inria.fr/inria-00548682
@inproceedings{kushal:inria-00548682,
    hal_id = {inria-00548682},
    url = {http://hal.inria.fr/inria-00548682},
    title = {{Flexible Object Models for Category-Level 3D Object Recognition}},
    author = {Kushal, Akash and Schmid, Cordelia and Ponce, Jean},
    abstract = {{Today's category-level object recognition systems largely focus on fronto-parallel views of objects with characteristic texture patterns. To overcome these limitations, we propose a novel framework for visual object recognition where object classes are represented by assemblies of partial surface models (PSMs) obeying loose local geometric constraints. The PSMs themselves are formed of dense, locally rigid assemblies of image features. Since our model only enforces local geometric consistency, both at the level of model parts and at the level of individual features within the parts, it is robust to viewpoint changes and intra-class variability. The proposed approach has been implemented, and it outperforms the state-of-the-art algorithms for object detection and localization recently compared in [14] on the Pascal 2005 VOC Challenge Cars Test 1 data.}},
    keywords = {feature extraction; image texture; object recognition},
    language = {English},
    affiliation = {Department of Computer Science [UIUC] - UIUC , The Beckman Institute for Advanced Science and Technology - Beckman Institute , LEAR - INRIA Grenoble Rh{\^o}ne-Alpes / LJK Laboratoire Jean Kuntzmann , Laboratoire Jean Kuntzmann - LJK , WILLOW - INRIA Paris - Rocquencourt , Laboratoire d'informatique de l'{\'e}cole normale sup{\'e}rieure - LIENS},
    booktitle = {{IEEE Conference on Computer Vision \& Pattern Recognition (CVPR '07)}},
    publisher = {IEEE Computer Society},
    pages = {1--8},
    address = {Minneapolis, United States},
    audience = {international },
    doi = {10.1109/CVPR.2007.383149 },
    year = {2007},
    pdf = {http://hal.inria.fr/inria-00548682/PDF/akash\_cvpr.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="inproceedings"><head>Peer-reviewed conferences/proceedings</head>
<biblStruct type="inproceedings" xml:id="inria-00548682"><analytic>
<author><persName><forename>Akash</forename><surname>Kushal</surname></persName>
<affiliation>
<orgName type="laboratory">UIUC</orgName>
<orgName type="team">Department of Computer Science [UIUC]</orgName>
<country>US</country>
<orgName type="institution">University of Illinois at Urbana-Champaign</orgName>
</affiliation>
<affiliation>
<orgName type="laboratory">Beckman Institute</orgName>
<orgName type="team">The Beckman Institute for Advanced Science and Technology</orgName>
<country>US</country>
<orgName type="institution">University of Illinois</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>
<author><persName><forename>Jean</forename><surname>Ponce</surname></persName>
<affiliation>
<orgName type="laboratory">INRIA Paris - Rocquencourt</orgName>
<orgName type="team">WILLOW</orgName>
<country>FR</country>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">Ecole Normale Supérieure de Paris - ENS Paris</orgName>
<orgName type="institution">CNRS : UMR8548</orgName>
</affiliation>
<affiliation>
<orgName type="laboratory">LIENS</orgName>
<orgName type="team">Laboratoire d'informatique de l'école normale supérieure</orgName>
<country>FR</country>
<orgName type="institution">CNRS : UMR8548</orgName>
<orgName type="institution">Ecole Normale Supérieure de Paris - ENS Paris</orgName>
</affiliation>
</author>
<title type="main" level="a">Flexible Object Models for Category-Level 3D Object Recognition</title></analytic><monogr><meeting>IEEE Conference on Computer Vision & Pattern Recognition (CVPR '07)</meeting><imprint><publisher>IEEE Computer Society</publisher><pubPlace><settlement>Minneapolis</settlement><country>United States</country></pubPlace><biblScope type="publicationDate">2007-00-00</biblScope><biblScope type="pp">1--8</biblScope></imprint></monogr><idno type="doi">10.1109/CVPR.2007.383149</idno><idno type="HALid">http://hal.inria.fr/inria-00548682</idno><idno type="HALFile">http://hal.inria.fr/inria-00548682/PDF/akash_cvpr.pdf</idno></biblStruct>
</listBibl>
</listBibl>