High-quality region-based foreground segmentation using a spatial grid of SVM classifiers

Zhang, Xiaohan and Blanco Adán, Carlos Roberto del and Cuevas Rodríguez, Carlos and Jaureguizar Núñez, Fernando and García Santos, Narciso (2014). High-quality region-based foreground segmentation using a spatial grid of SVM classifiers. In: "IEEE International Conference on Consumer Electronics (ICCE 2014)", 10/01/2014 - 13/01/2014, Las Vegas, Nevada, USA. pp. 488-489.

Description

Title: High-quality region-based foreground segmentation using a spatial grid of SVM classifiers
Author/s:
  • Zhang, Xiaohan
  • Blanco Adán, Carlos Roberto del
  • Cuevas Rodríguez, Carlos
  • Jaureguizar Núñez, Fernando
  • García Santos, Narciso
Item Type: Presentation at Congress or Conference (Article)
Event Title: IEEE International Conference on Consumer Electronics (ICCE 2014)
Event Dates: 10/01/2014 - 13/01/2014
Event Location: Las Vegas, Nevada, USA
Title of Book: IEEE International Conference on Consumer Electronics (ICCE 2014)
Título de Revista/Publicación: 2014 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS (ICCE)
Date: 2014
ISSN: 2158-3994
Subjects:
Faculty: E.T.S.I. Telecomunicación (UPM)
Department: Señales, Sistemas y Radiocomunicaciones
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (1MB) | Preview

Abstract

This paper presents a novel background modeling system that uses a spatial grid of Support Vector Machines classifiers for segmenting moving objects, which is a key step in many video-based consumer applications. The system is able to adapt to a large range of dynamic background situations since no parametric model or statistical distribution are assumed. This is achieved by using a different classifier per image region that learns the specific appearance of that scene region and its variations (illumination changes, dynamic backgrounds, etc.). The proposed system has been tested with a recent public database, outperforming other state-of-the-art algorithms.

More information

Item ID: 36202
DC Identifier: http://oa.upm.es/36202/
OAI Identifier: oai:oa.upm.es:36202
Official URL: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6776098
Deposited by: Memoria Investigacion
Deposited on: 04 Jul 2015 07:46
Last Modified: 04 Jul 2015 07:46
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM