Combining Appearance Models and Markov Random Fields for Category Level Object Segmentation

Diane Larlus 1 Frédéric Jurie 2
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
2 Equipe Image - Laboratoire GREYC - UMR6072
GREYC - Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen
Abstract : Object models based on bag-of-words representations can achieve state-of-the-art performance for image classification and object localization tasks. However, as they consider objects as loose collections of local patches they fail to accurately locate object boundaries and are not able to produce accurate object segmentation. On the other hand, Markov random field models used for image segmentation focus on object boundaries but can hardly use the global constraints necessary to deal with object categories whose appearance may vary significantly. In this paper we combine the advantages of both approaches. First, a mechanism based on local regions allows object detection using visual word occurrences and produces a rough image segmentation. Then, a MRF component gives clean boundaries and enforces label consistency, guided by local image cues (color, texture and edge cues) and by long-distance dependencies. Gibbs sampling is used to infer the model. The proposed method successfully segments object categories with highly varying appearances in the presence of cluttered backgrounds and large view point changes. We show that it outperforms published results on the Pascal VOC 2007 dataset.
Type de document :
Communication dans un congrès
CVPR 2008 - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2008, Anchorage, United States. IEEE Computer Society, pp.1-7, 2008, 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4587453〉. 〈10.1109/CVPR.2008.4587453〉
Liste complète des métadonnées

Littérature citée [19 références]  Voir  Masquer  Télécharger


https://hal.inria.fr/inria-00548660
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 10:24:53
Dernière modification le : mardi 26 septembre 2017 - 01:25:20
Document(s) archivé(s) le : lundi 5 novembre 2012 - 14:40:22

Fichiers

versionFinale.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Diane Larlus, Frédéric Jurie. Combining Appearance Models and Markov Random Fields for Category Level Object Segmentation. CVPR 2008 - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2008, Anchorage, United States. IEEE Computer Society, pp.1-7, 2008, 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4587453〉. 〈10.1109/CVPR.2008.4587453〉. 〈inria-00548660〉

Partager

Métriques

Consultations de
la notice

488

Téléchargements du document

844