Please use this identifier to cite or link to this item:
Title: GrabCut-Based Human Segmentation in Video Sequences
Author: Hernández-Vela, Antonio
Reyes Estany, Miguel
Ponce López, Víctor
Escalera Guerrero, Sergio
Keywords: Postura humana
Algorismes computacionals
Camps aleatoris
Computer algorithms
Random fields
Issue Date: 9-Nov-2012
Publisher: MDPI
Abstract: In this paper, we present a fully-automatic Spatio-Temporal GrabCut human segmentation methodology that combines tracking and segmentation. GrabCut initialization is performed by a HOG-based subject detection, face detection, and skin color model. Spatial information is included by Mean Shift clustering whereas temporal coherence is considered by the historical of Gaussian Mixture Models. Moreover, full face and pose recovery is obtained by combining human segmentation with Active Appearance Models and Conditional Random Fields. Results over public datasets and in a new Human Limb dataset show a robust segmentation and recovery of both face and pose using the presented methodology.
Note: Reproducció del document publicat a:
It is part of: Sensors, 2012, vol. 12, num. 11, p. 15377-15393
Related resource:
ISSN: 1424-8220
Appears in Collections:Articles publicats en revistes (Matemàtiques i Informàtica)

Files in This Item:
File Description SizeFormat 
618863.pdf1.52 MBAdobe PDFView/Open

This item is licensed under a Creative Commons License Creative Commons