Dependent multiple cue integration for robust tracking

We propose a new technique for fusing multiple cues to robustly segment an object from its background in video sequences that suffer from abrupt changes of both illumination and position of the target. Robustness is achieved by the integration of appearance and geometric object features and by their...

Descripción completa

Detalles Bibliográficos
Autores: Moreno-Noguer, Francesc, Sanfeliu, Alberto, Samaras, Dimitris
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2008
País:España
Institución:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/30597
Acceso en línea:http://hdl.handle.net/10261/30597
Access Level:acceso abierto
Palabra clave:Bayesian tracking
Multiple cue integration
Pattern recognition
id ES_488f7e7965e59226fb8f206085a8a2b6
oai_identifier_str oai:digital.csic.es:10261/30597
network_acronym_str ES
network_name_str España
repository_id_str
spelling Dependent multiple cue integration for robust trackingMoreno-Noguer, FrancescSanfeliu, AlbertoSanfeliu, AlbertoSamaras, DimitrisBayesian trackingMultiple cue integrationPattern recognitionWe propose a new technique for fusing multiple cues to robustly segment an object from its background in video sequences that suffer from abrupt changes of both illumination and position of the target. Robustness is achieved by the integration of appearance and geometric object features and by their estimation using Bayesian filters, such as Kalman or particle filters. In particular, each filter estimates the state of a specific object feature, conditionally dependent on another feature estimated by a distinct filter. This dependence provides improved target representations, permitting us to segment it out from the background even in nonstationary sequences. Considering that the procedure of the Bayesian filters may be described by a "hypotheses generation-hypotheses correction" strategy, the major novelty of our methodology compared to previous approaches is that the mutual dependence between filters is considered during the feature observation, that is, into the "hypotheses-correction" stage, instead of considering it when generating the hypotheses. This proves to be much more effective in terms of accuracy and reliability. The proposed method is analytically justified and applied to develop a robust tracking system that adapts online and simultaneously the color space where the image points are represented, the color distributions, the contour of the object, and its bounding box. Results with synthetic data and real video sequences demonstrate the robustness and versatility of our method.This work was supported by projects: 'Integration of robust perception, learning, and navigation systems in mobile robotics' (J-0929), 'Ubiquitous networking robotics in urban settings' (E-00938), 'CONSOLIDER-INGENIO 2010 Multimodal interaction in pattern recognition and computer vision' (V-00069). This research was conducted at the Institut de Robòtica i Informàtica Industrial of the Technical University of Catalonia and Consejo Superior de Investigaciones Científicas. It was partially supported by Consolider Ingenio 2010, project CSD2007-00018, CICYT project DPI2007-614452, and IST-045062 of the European Community Union, by a fellowship from the Spanish Ministry of Science and Technology, and by grants from the US Department of Justice (2004-DD-BX-1224), Department of Energy (MO-068), and US National Science Foundation (ACI-0313184 and IIS-0527585).Peer ReviewedInstitute of Electrical and Electronics Engineers201020102008info:eu-repo/semantics/articlehttp://purl.org/coar/resource_type/c_6501Publisher's versioninfo:eu-repo/semantics/publishedVersionhttp://hdl.handle.net/10261/30597reponame:DIGITAL.CSIC. Repositorio Institucional del CSICinstname:Consejo Superior de Investigaciones Científicas (CSIC)Ingléshttp://dx.doi.org/10.1109/TPAMI.2007.70727info:eu-repo/semantics/openAccessoai:digital.csic.es:10261/305972026-05-22T06:33:51Z
dc.title.none.fl_str_mv Dependent multiple cue integration for robust tracking
title Dependent multiple cue integration for robust tracking
spellingShingle Dependent multiple cue integration for robust tracking
Moreno-Noguer, Francesc
Bayesian tracking
Multiple cue integration
Pattern recognition
title_short Dependent multiple cue integration for robust tracking
title_full Dependent multiple cue integration for robust tracking
title_fullStr Dependent multiple cue integration for robust tracking
title_full_unstemmed Dependent multiple cue integration for robust tracking
title_sort Dependent multiple cue integration for robust tracking
dc.creator.none.fl_str_mv Moreno-Noguer, Francesc
Sanfeliu, Alberto
Sanfeliu, Alberto
Samaras, Dimitris
author Moreno-Noguer, Francesc
author_facet Moreno-Noguer, Francesc
Sanfeliu, Alberto
Samaras, Dimitris
author_role author
author2 Sanfeliu, Alberto
Samaras, Dimitris
author2_role author
author
dc.subject.none.fl_str_mv Bayesian tracking
Multiple cue integration
Pattern recognition
topic Bayesian tracking
Multiple cue integration
Pattern recognition
description We propose a new technique for fusing multiple cues to robustly segment an object from its background in video sequences that suffer from abrupt changes of both illumination and position of the target. Robustness is achieved by the integration of appearance and geometric object features and by their estimation using Bayesian filters, such as Kalman or particle filters. In particular, each filter estimates the state of a specific object feature, conditionally dependent on another feature estimated by a distinct filter. This dependence provides improved target representations, permitting us to segment it out from the background even in nonstationary sequences. Considering that the procedure of the Bayesian filters may be described by a "hypotheses generation-hypotheses correction" strategy, the major novelty of our methodology compared to previous approaches is that the mutual dependence between filters is considered during the feature observation, that is, into the "hypotheses-correction" stage, instead of considering it when generating the hypotheses. This proves to be much more effective in terms of accuracy and reliability. The proposed method is analytically justified and applied to develop a robust tracking system that adapts online and simultaneously the color space where the image points are represented, the color distributions, the contour of the object, and its bounding box. Results with synthetic data and real video sequences demonstrate the robustness and versatility of our method.
publishDate 2008
dc.date.none.fl_str_mv 2008
2010
2010
dc.type.none.fl_str_mv info:eu-repo/semantics/article
http://purl.org/coar/resource_type/c_6501
Publisher's version
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10261/30597
url http://hdl.handle.net/10261/30597
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv http://dx.doi.org/10.1109/TPAMI.2007.70727
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers
publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers
dc.source.none.fl_str_mv reponame:DIGITAL.CSIC. Repositorio Institucional del CSIC
instname:Consejo Superior de Investigaciones Científicas (CSIC)
instname_str Consejo Superior de Investigaciones Científicas (CSIC)
reponame_str DIGITAL.CSIC. Repositorio Institucional del CSIC
collection DIGITAL.CSIC. Repositorio Institucional del CSIC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869407367782727680
score 15.812429

Similares en LA Referencia