Iterative Human Segmentation from Detection Windows Using Contour Segment Analysis

Cyrille Migniot 1 Pascal Bertolino 1 Jean-Marc Chassery 1
1 GIPSA-AGPIG - AGPIG
GIPSA-DIS - Département Images et Signal
Abstract : This paper presents a new algorithm for human segmentation in images. The human silhouette is estimated in positive windows that are already obtained with an existing efficient detection method. This accurate segmentation uses the data previously computed in the detection. First, a pre-segmentation step computes the likelihood of contour segments as being a part of a human silhouette. Then, a contour segment oriented graph is constructed from the shape continuity cue and the prior cue obtained by the pre-segmentation. Segmentation is so posed as the computation of the shortest-path cycle which corresponds to the human silhouette. Additionally, the process is achieved iteratively to eliminate irrelevant paths and to increase the segmentation performance. The approach is tested on a human image database and the segmentation performance is evaluated quantitatively.
Type de document :
Communication dans un congrès
VISAPP 2013 - 8th International Conference on Computer Vision Theory and Applications, Feb 2013, Barcelone, Spain. VISAPP proceedings, pp.CD, 2012
Liste complète des métadonnées


https://hal.archives-ouvertes.fr/hal-00798468
Contributeur : Pascal Bertolino <>
Soumis le : vendredi 8 mars 2013 - 15:39:27
Dernière modification le : vendredi 26 février 2016 - 20:58:34
Document(s) archivé(s) le : dimanche 9 juin 2013 - 09:20:07

Fichier

camera-ready-Migniot-VISAPP201...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00798468, version 1

Collections

Citation

Cyrille Migniot, Pascal Bertolino, Jean-Marc Chassery. Iterative Human Segmentation from Detection Windows Using Contour Segment Analysis. VISAPP 2013 - 8th International Conference on Computer Vision Theory and Applications, Feb 2013, Barcelone, Spain. VISAPP proceedings, pp.CD, 2012. <hal-00798468>

Partager

Métriques

Consultations de
la notice

356

Téléchargements du document

450