Identity statement area
Reference TypeConference Proceedings
Last Update2013:
Metadata Last Update2020: administrator
Citation KeyDutraSouAlvSchOli:2013:RePeBa
TitleRe-identifying People based on Indexing Structure and Manifold Appearance Modeling
DateAug. 5-8, 2013
Access Date2020, Dec. 04
Number of Files1
Size10792 KiB
Context area
Author1 Dutra, Cristianne Rodrigues Santos
2 Souza, Tiago
3 Alves, Raul
4 Schwartz, William Robson
5 Oliveira, Luciano
Affiliation1 Universidade Federal de Minas Gerais
2 Federal University of Bahia
3 Federal University of Bahia
4 Universidade Federal de Minas Gerais
5 Federal University of Bahia
EditorBoyer, Kim
Hirata, Nina
Nedel, Luciana
Silva, Claudio
Conference NameConference on Graphics, Patterns and Images, 26 (SIBGRAPI)
Conference LocationArequipa, Peru
Book TitleProceedings
PublisherIEEE Computer Society
Publisher CityLos Alamitos
History2013-07-03 00:18:01 :: -> administrator ::
2020-02-19 03:09:22 :: administrator -> :: 2013
Content and structure area
Is the master or a copy?is the master
Document Stagecompleted
Content TypeExternal Contribution
Tertiary TypeFull Paper
KeywordsPerson re-identification, bag-of-features, predominance filter, inverted lists, mean Riemann covariance.
AbstractThe role of person re-identification has increased in the recent years due to the large camera networks employed in surveillance systems. The goal in this case is to identify individuals that have been previously identified in a different camera. Even though several approaches have been proposed, there are still challenges to be addressed, such as illumination changes, pose variation, low acquisition quality, appearance modeling and the management of the large number of subjects being monitored by the surveillance system. The present work tackles the last problem by developing an indexing structure based on inverted lists and a predominance filter descriptor with the aim of ranking candidates with more probability of being the target search person. With this initial ranking, a more strong classification is done by means of a mean Riemann covariance method, which is based on a appearance strategy. Experimental results show that the proposed indexing structure returns an accurate short-list containing the most likely candidates, and that manifold appearance model is able to set the correct candidate among the initial ranks in the identification process. The proposed method is comparable to other state-of-the-art approaches.
source Directory Contentthere are no files
agreement Directory Content
agreement.html 02/07/2013 21:18 0.7 KiB 
Conditions of access and use area
Target Filepaper_CameraReady.pdf
Allied materials area
Notes area
Empty Fieldsaccessionnumber archivingpolicy archivist area callnumber copyholder copyright creatorhistory descriptionlevel dissemination documentstage doi edition electronicmailaddress group holdercode isbn issn label lineage mark nextedition nexthigherunit notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url versiontype volume