Occlusion Boundary Detection via Deep Exploration of Context

Abstract : Occlusion boundaries contain rich perceptual information about the underlying scene structure. They also provide important cues in many visual perception tasks such as scene understanding, object recognition, and segmentation. In this paper, we improve occlusion boundary detection via enhanced exploration of contextual information (e.g., local structural boundary patterns, observations from surrounding regions, and temporal context), and in doing so develop a novel approach based on convolutional neural networks (CNNs) and conditional random fields (CRFs). Experimental results demonstrate that our detector significantly out-performs the state-of-the-art (e.g., improving the F-measure from 0.62 to 0.71 on the commonly used CMU benchmark). Last but not least, we empirically assess the roles of several important components of the proposed detector, so as to validate the rationale behind this approach.
Type de document :
Communication dans un congrès
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2016, Las Vegas, United States. pp.241 - 250, 2016, 〈10.1109/CVPR.2016.33〉
Liste complète des métadonnées

Littérature citée [53 références]  Voir  Masquer  Télécharger

https://hal-upec-upem.archives-ouvertes.fr/hal-01578439
Contributeur : Chaohui Wang <>
Soumis le : mardi 29 août 2017 - 11:17:20
Dernière modification le : dimanche 26 août 2018 - 17:30:01

Fichier

OcclusionBoundaryDetectionDeep...
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Huan Fu, Chaohui Wang, Dacheng Tao, Michael Black. Occlusion Boundary Detection via Deep Exploration of Context. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2016, Las Vegas, United States. pp.241 - 250, 2016, 〈10.1109/CVPR.2016.33〉. 〈hal-01578439〉

Partager

Métriques

Consultations de la notice

115

Téléchargements de fichiers

120