Fast Semantic Scene Segmentation with Conditional Random Field - AI Accéder directement au contenu
Communication Dans Un Congrès Année : 2010

Fast Semantic Scene Segmentation with Conditional Random Field

Wen Yang
  • Fonction : Auteur
  • PersonId : 864837
Chu He
  • Fonction : Auteur
William Triggs

Résumé

In this paper, we present a fast approach to obtain semantic scene segmentation with high precision. We employ a two-stage classifier to label all image pixels. First, we use the regularized logistic regression to combine different appearance-based features and the improved spatial layout of labeling information. In the second stage, we incorporate the local, regional and global cues into a conditional random field model to provide a final segmentation, and a fast max-margin training method is employed to learn the parameters of the model quickly. The comparison experiments on four multiclass image segmentation databases show that our approach can achieve comparable semantic segmentation results and work faster than that of the state-of-the-art approaches
Fichier non déposé

Dates et versions

hal-00851736 , version 1 (17-08-2013)

Identifiants

Citer

Wen Yang, Dengxin Dai, Chu He, William Triggs, Gui-Song Xia. Fast Semantic Scene Segmentation with Conditional Random Field. ICIP 2010 - International Conference on Image Processing, Sep 2010, Hong-Kong, China. pp.229-232, ⟨10.1109/ICIP.2010.5652023⟩. ⟨hal-00851736⟩
199 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More