Combining Appearance Models and Markov Random Fields for Category Level Object Segmentation - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2008

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

Résumé

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.
Fichier principal
Vignette du fichier
versionFinale.pdf (667.24 Ko) Télécharger le fichier
Vignette du fichier
imageForBiblio.png (263.14 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Format : Figure, Image
Loading...

Dates et versions

inria-00548660 , version 1 (20-12-2010)

Identifiants

Citer

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. pp.1-7, ⟨10.1109/CVPR.2008.4587453⟩. ⟨inria-00548660⟩
392 Consultations
694 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More