From images to shape models for object detection

Vittorio Ferrari 1 Frédéric Jurie 1 Cordelia Schmid 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
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 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 made possible by a novel technique for learning a shape model of an object class given {\em 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, while needing no segmented examples for training (only bounding-boxes)
Type de document :
Rapport
[Research Report] RR-6600, INRIA. 2008
Liste complète des métadonnées

Littérature citée [34 références]  Voir  Masquer  Télécharger


https://hal.inria.fr/inria-00308388
Contributeur : Vittorio Ferrari <>
Soumis le : mercredi 30 juillet 2008 - 11:05:26
Dernière modification le : vendredi 24 novembre 2017 - 13:28:32
Document(s) archivé(s) le : samedi 26 novembre 2016 - 00:42:26

Fichiers

RR-6600.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00308388, version 1

Collections

Citation

Vittorio Ferrari, Frédéric Jurie, Cordelia Schmid. From images to shape models for object detection. [Research Report] RR-6600, INRIA. 2008. 〈inria-00308388〉

Partager

Métriques

Consultations de la notice

441

Téléchargements de fichiers

720